diff --git "a/8b7178b35b/3430973.out" "b/8b7178b35b/3430973.out" new file mode 100644--- /dev/null +++ "b/8b7178b35b/3430973.out" @@ -0,0 +1,51797 @@ +Model parameters: d_model 4096 ffw_size 16384 kv_size 128 n_heads 32 n_layers 42 +Megatron-DeepSpeed/pretrain_gpt.py --tensor-model-parallel-size 2 --pipeline-model-parallel-size 2 --num-layers 42 --hidden-size 4096 --num-attention-heads 32 --kv-channels 128 --ffn-hidden-size 16384 --seq-length 2048 --max-position-embeddings 2048 --micro-batch-size 1 --global-batch-size 512 --train-samples 1 --vocab-file gpt2/vocab.json --merge-file gpt2/merges.txt --clip-grad 1.0 --kill-switch-path kill-switch-8b7178b35bval --bf16 --optimizer adam --adam-beta1 0.9 --adam-beta2 0.999 --adam-eps 1e-8 --lr 2e-4 --min-lr 2e-5 --lr-decay-style cosine --lr-decay-samples 1 --lr-warmup-samples 0 --clip-grad 1.0 --weight-decay 1e-1 --override-lr-scheduler --reset-progress --no-load-optim --log-interval 10 --save-interval 5000 --eval-interval 1 --eval-iters 100 --eval-only true --tensorboard-dir tensorboard_8b7178b35bval --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save lm1-8b7-178b-c4-repetitions/8b7178b35b --load lm1-8b7-178b-c4-repetitions/8b7178b35b --train-weighted-split-paths-path train400m.txt --valid-weighted-split-paths-path val.txt --data-impl mmap --num-workers 0 --valid-num-workers 0 --deepspeed --deepspeed_config ds_configs/3430973.json --zero-stage 0 +START 3430973: Sat 29 Apr 2023 11:33:29 AM EEST + 0: + 0: + 0: ======================= ROCm System Management Interface ======================= + 0: ================================= Concise Info ================================= + 0: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 0: 0 41.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 0: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 0: 2 42.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 0: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 0: 4 46.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 0: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 0: 6 39.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 0: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 0: ================================================================================ + 0: ============================= End of ROCm SMI Log ============================== +61: +61: +61: ======================= ROCm System Management Interface ======================= +61: ================================= Concise Info ================================= +61: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +61: 0 47.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +61: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +61: 2 41.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +61: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +61: 4 50.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +61: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +61: 6 43.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +61: 7 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +61: ================================================================================ +61: ============================= End of ROCm SMI Log ============================== +53: +53: +53: ======================= ROCm System Management Interface ======================= +53: ================================= Concise Info ================================= +53: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +53: 0 47.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +53: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +53: 2 42.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +53: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +53: 4 42.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +53: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +53: 6 40.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +53: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +53: ================================================================================ +53: ============================= End of ROCm SMI Log ============================== + 9: + 9: + 9: ======================= ROCm System Management Interface ======================= + 9: ================================= Concise Info ================================= + 9: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 9: 0 46.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 9: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 9: 2 43.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 9: 3 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 9: 4 42.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 9: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 9: 6 40.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 9: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 9: ================================================================================ + 9: ============================= End of ROCm SMI Log ============================== +58: +58: +58: ======================= ROCm System Management Interface ======================= +58: ================================= Concise Info ================================= +58: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +58: 0 54.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +58: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +58: 2 43.0c 100.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +58: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +58: 4 46.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +58: 5 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +58: 6 41.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +58: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +58: ================================================================================ +58: ============================= End of ROCm SMI Log ============================== +51: +51: +51: ======================= ROCm System Management Interface ======================= +51: ================================= Concise Info ================================= +51: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +51: 0 49.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +51: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +51: 2 42.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +51: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +51: 4 47.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +51: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +51: 6 42.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +51: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +51: ================================================================================ +51: ============================= End of ROCm SMI Log ============================== +59: +59: +59: ======================= ROCm System Management Interface ======================= +59: ================================= Concise Info ================================= +59: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +59: 0 49.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +59: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +59: 2 41.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +59: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +59: 4 43.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +59: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +59: 6 39.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +59: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +59: ================================================================================ +59: ============================= End of ROCm SMI Log ============================== +63: +63: +63: ======================= ROCm System Management Interface ======================= +63: ================================= Concise Info ================================= +63: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +63: 0 49.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +63: 1 52.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +63: 2 43.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +63: 3 51.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +63: 4 42.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +63: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +63: 6 37.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +63: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +63: ================================================================================ +63: ============================= End of ROCm SMI Log ============================== +57: +57: +57: ======================= ROCm System Management Interface ======================= +57: ================================= Concise Info ================================= +57: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +57: 0 50.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +57: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +57: 2 43.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +57: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +57: 4 52.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +57: 5 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +57: 6 38.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +57: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +57: ================================================================================ +57: ============================= End of ROCm SMI Log ============================== +19: +19: +19: ======================= ROCm System Management Interface ======================= +19: ================================= Concise Info ================================= +19: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +19: 0 44.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +19: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +19: 2 39.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +19: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +19: 4 39.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +19: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +19: 6 44.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +19: 7 39.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +19: ================================================================================ +19: ============================= End of ROCm SMI Log ============================== +56: +56: +56: ======================= ROCm System Management Interface ======================= +56: ================================= Concise Info ================================= +56: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +56: 0 45.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +56: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +56: 2 43.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +56: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +56: 4 43.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +56: 5 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +56: 6 45.0c 81.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +56: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +56: ================================================================================ +56: ============================= End of ROCm SMI Log ============================== +22: +22: +22: ======================= ROCm System Management Interface ======================= +22: ================================= Concise Info ================================= +22: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +22: 0 47.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +22: 1 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +22: 2 38.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +22: 3 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +22: 4 43.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +22: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +22: 6 42.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +22: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +22: ================================================================================ +22: ============================= End of ROCm SMI Log ============================== +18: +18: +18: ======================= ROCm System Management Interface ======================= +18: ================================= Concise Info ================================= +18: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +18: 0 43.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +18: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +18: 2 43.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +18: 3 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +18: 4 43.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +18: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +18: 6 41.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +18: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +18: ================================================================================ +18: ============================= End of ROCm SMI Log ============================== +60: +60: +60: ======================= ROCm System Management Interface ======================= +60: ================================= Concise Info ================================= +60: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +60: 0 41.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +60: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +60: 2 41.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +60: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +60: 4 42.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +60: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +60: 6 48.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +60: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +60: ================================================================================ +60: ============================= End of ROCm SMI Log ============================== +24: +24: +24: ======================= ROCm System Management Interface ======================= +24: ================================= Concise Info ================================= +24: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +24: 0 45.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +24: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +24: 2 41.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +24: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +24: 4 44.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +24: 5 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +24: 6 44.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +24: 7 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +24: ================================================================================ +24: ============================= End of ROCm SMI Log ============================== +12: +12: +12: ======================= ROCm System Management Interface ======================= +12: ================================= Concise Info ================================= +12: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +12: 0 45.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +12: 1 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +12: 2 43.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +12: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +12: 4 40.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +12: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +12: 6 42.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +12: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +12: ================================================================================ +12: ============================= End of ROCm SMI Log ============================== +54: +54: +54: ======================= ROCm System Management Interface ======================= +54: ================================= Concise Info ================================= +54: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +54: 0 49.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +54: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +54: 2 40.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +54: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +54: 4 50.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +54: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +54: 6 42.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +54: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +54: ================================================================================ +54: ============================= End of ROCm SMI Log ============================== +34: +34: +34: ======================= ROCm System Management Interface ======================= +34: ================================= Concise Info ================================= +34: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +34: 0 52.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +34: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +34: 2 45.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +34: 3 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +34: 4 47.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +34: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +34: 6 41.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +34: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +34: ================================================================================ +34: ============================= End of ROCm SMI Log ============================== +27: +27: +27: ======================= ROCm System Management Interface ======================= +27: ================================= Concise Info ================================= +27: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +27: 0 46.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +27: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +27: 2 44.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +27: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +27: 4 45.0c 82.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +27: 5 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +27: 6 41.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +27: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +27: ================================================================================ +27: ============================= End of ROCm SMI Log ============================== +25: +25: +25: ======================= ROCm System Management Interface ======================= +25: ================================= Concise Info ================================= +25: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +25: 0 42.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +25: 1 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +25: 2 39.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +25: 3 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +25: 4 36.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +25: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +25: 6 47.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +25: 7 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +25: ================================================================================ +25: ============================= End of ROCm SMI Log ============================== +48: +48: +48: ======================= ROCm System Management Interface ======================= +48: ================================= Concise Info ================================= +48: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +48: 0 48.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +48: 1 54.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +48: 2 42.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +48: 3 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +48: 4 50.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +48: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +48: 6 41.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +48: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +48: ================================================================================ +48: ============================= End of ROCm SMI Log ============================== + 3: + 3: + 3: ======================= ROCm System Management Interface ======================= + 3: ================================= Concise Info ================================= + 3: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 3: 0 41.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 3: 1 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 3: 2 42.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 3: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 3: 4 45.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 3: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 3: 6 43.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 3: 7 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 3: ================================================================================ + 3: ============================= End of ROCm SMI Log ============================== +26: +26: +26: ======================= ROCm System Management Interface ======================= +26: ================================= Concise Info ================================= +26: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +26: 0 48.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +26: 1 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +26: 2 36.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +26: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +26: 4 37.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +26: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +26: 6 36.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +26: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +26: ================================================================================ +26: ============================= End of ROCm SMI Log ============================== +33: +33: +33: ======================= ROCm System Management Interface ======================= +33: ================================= Concise Info ================================= +33: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +33: 0 52.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +33: 1 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +33: 2 40.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +33: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +33: 4 45.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +33: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +33: 6 45.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +33: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +33: ================================================================================ +33: ============================= End of ROCm SMI Log ============================== +37: +37: +37: ======================= ROCm System Management Interface ======================= +37: ================================= Concise Info ================================= +37: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +37: 0 46.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +37: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +37: 2 41.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +37: 3 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +37: 4 44.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +37: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +37: 6 41.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +37: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +37: ================================================================================ +37: ============================= End of ROCm SMI Log ============================== + 5: + 5: + 5: ======================= ROCm System Management Interface ======================= + 5: ================================= Concise Info ================================= + 5: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 5: 0 42.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 5: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 5: 2 47.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 5: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 5: 4 47.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 5: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 5: 6 51.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 5: 7 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 5: ================================================================================ + 5: ============================= End of ROCm SMI Log ============================== +47: +47: +47: ======================= ROCm System Management Interface ======================= +47: ================================= Concise Info ================================= +47: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +47: 0 50.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +47: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +47: 2 45.0c 82.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +47: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +47: 4 44.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +47: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +47: 6 44.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +47: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +47: ================================================================================ +47: ============================= End of ROCm SMI Log ============================== + 2: + 2: + 2: ======================= ROCm System Management Interface ======================= + 2: ================================= Concise Info ================================= + 2: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 2: 0 48.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 2: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 2: 2 41.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 2: 3 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 2: 4 41.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 2: 5 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 2: 6 38.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 2: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 2: ================================================================================ + 2: ============================= End of ROCm SMI Log ============================== +43: +43: +43: ======================= ROCm System Management Interface ======================= +43: ================================= Concise Info ================================= +43: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +43: 0 42.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +43: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +43: 2 42.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +43: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +43: 4 43.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +43: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +43: 6 38.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +43: 7 51.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +43: ================================================================================ +43: ============================= End of ROCm SMI Log ============================== + 1: + 1: + 1: ======================= ROCm System Management Interface ======================= + 1: ================================= Concise Info ================================= + 1: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 1: 0 52.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 1: 1 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 1: 2 42.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 1: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 1: 4 45.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 1: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 1: 6 35.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 1: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 1: ================================================================================ + 1: ============================= End of ROCm SMI Log ============================== +10: +10: +10: ======================= ROCm System Management Interface ======================= +10: ================================= Concise Info ================================= +10: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +10: 0 47.0c 98.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +10: 1 52.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +10: 2 39.0c 81.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +10: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +10: 4 43.0c 80.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +10: 5 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +10: 6 44.0c 81.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +10: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +10: ================================================================================ +10: ============================= End of ROCm SMI Log ============================== +55: +55: +55: ======================= ROCm System Management Interface ======================= +55: ================================= Concise Info ================================= +55: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +55: 0 42.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +55: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +55: 2 46.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +55: 3 37.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +55: 4 43.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +55: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +55: 6 40.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +55: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +55: ================================================================================ +55: ============================= End of ROCm SMI Log ============================== +62: +62: +62: ======================= ROCm System Management Interface ======================= +62: ================================= Concise Info ================================= +62: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +62: 0 54.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +62: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +62: 2 47.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +62: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +62: 4 47.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +62: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +62: 6 50.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +62: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +62: ================================================================================ +62: ============================= End of ROCm SMI Log ============================== +16: +16: +16: ======================= ROCm System Management Interface ======================= +16: ================================= Concise Info ================================= +16: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +16: 0 48.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +16: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +16: 2 42.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +16: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +16: 4 40.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +16: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +16: 6 41.0c 82.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +16: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +16: ================================================================================ +16: ============================= End of ROCm SMI Log ============================== +23: +23: +23: ======================= ROCm System Management Interface ======================= +23: ================================= Concise Info ================================= +23: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +23: 0 46.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +23: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +23: 2 39.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +23: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +23: 4 39.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +23: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +23: 6 40.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +23: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +23: ================================================================================ +23: ============================= End of ROCm SMI Log ============================== +15: +15: +15: ======================= ROCm System Management Interface ======================= +15: ================================= Concise Info ================================= +15: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +15: 0 47.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +15: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +15: 2 45.0c 82.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +15: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +15: 4 40.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +15: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +15: 6 38.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +15: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +15: ================================================================================ +15: ============================= End of ROCm SMI Log ============================== +21: +21: +21: ======================= ROCm System Management Interface ======================= +21: ================================= Concise Info ================================= +21: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +21: 0 44.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +21: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +21: 2 43.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +21: 3 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +21: 4 42.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +21: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +21: 6 42.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +21: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +21: ================================================================================ +21: ============================= End of ROCm SMI Log ============================== +46: +46: +46: ======================= ROCm System Management Interface ======================= +46: ================================= Concise Info ================================= +46: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +46: 0 44.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +46: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +46: 2 42.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +46: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +46: 4 44.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +46: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +46: 6 44.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +46: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +46: ================================================================================ +46: ============================= End of ROCm SMI Log ============================== +35: +35: +35: ======================= ROCm System Management Interface ======================= +35: ================================= Concise Info ================================= +35: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +35: 0 42.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +35: 1 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +35: 2 43.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +35: 3 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +35: 4 45.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +35: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +35: 6 46.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +35: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +35: ================================================================================ +35: ============================= End of ROCm SMI Log ============================== +30: +30: +30: ======================= ROCm System Management Interface ======================= +30: ================================= Concise Info ================================= +30: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +30: 0 44.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +30: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +30: 2 46.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +30: 3 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +30: 4 45.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +30: 5 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +30: 6 43.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +30: 7 53.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +30: ================================================================================ +30: ============================= End of ROCm SMI Log ============================== +29: +29: +29: ======================= ROCm System Management Interface ======================= +29: ================================= Concise Info ================================= +29: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +29: 0 49.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +29: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +29: 2 44.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +29: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +29: 4 44.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +29: 5 52.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +29: 6 43.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +29: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +29: ================================================================================ +29: ============================= End of ROCm SMI Log ============================== +17: +17: +17: ======================= ROCm System Management Interface ======================= +17: ================================= Concise Info ================================= +17: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +17: 0 43.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +17: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +17: 2 42.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +17: 3 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +17: 4 43.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +17: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +17: 6 39.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +17: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +17: ================================================================================ +17: ============================= End of ROCm SMI Log ============================== +42: +42: +42: ======================= ROCm System Management Interface ======================= +42: ================================= Concise Info ================================= +42: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +42: 0 47.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +42: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +42: 2 44.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +42: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +42: 4 47.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +42: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +42: 6 43.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +42: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +42: ================================================================================ +42: ============================= End of ROCm SMI Log ============================== +13: +13: +13: ======================= ROCm System Management Interface ======================= +13: ================================= Concise Info ================================= +13: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +13: 0 45.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +13: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +13: 2 35.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +13: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +13: 4 41.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +13: 5 52.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +13: 6 42.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +13: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +13: ================================================================================ +13: ============================= End of ROCm SMI Log ============================== +49: +49: +49: ======================= ROCm System Management Interface ======================= +49: ================================= Concise Info ================================= +49: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +49: 0 45.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +49: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +49: 2 48.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +49: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +49: 4 47.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +49: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +49: 6 42.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +49: 7 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +49: ================================================================================ +49: ============================= End of ROCm SMI Log ============================== +44: +44: +44: ======================= ROCm System Management Interface ======================= +44: ================================= Concise Info ================================= +44: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +44: 0 45.0c 98.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +44: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +44: 2 38.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +44: 3 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +44: 4 48.0c 80.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +44: 5 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +44: 6 41.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +44: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +44: ================================================================================ +44: ============================= End of ROCm SMI Log ============================== + 8: + 8: + 8: ======================= ROCm System Management Interface ======================= + 8: ================================= Concise Info ================================= + 8: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 8: 0 47.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 8: 1 52.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 8: 2 39.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 8: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 8: 4 45.0c 81.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 8: 5 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 8: 6 39.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 8: 7 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 8: ================================================================================ + 8: ============================= End of ROCm SMI Log ============================== +38: +38: +38: ======================= ROCm System Management Interface ======================= +38: ================================= Concise Info ================================= +38: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +38: 0 48.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +38: 1 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +38: 2 40.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +38: 3 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +38: 4 45.0c 82.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +38: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +38: 6 46.0c 82.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +38: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +38: ================================================================================ +38: ============================= End of ROCm SMI Log ============================== + 4: + 4: + 4: ======================= ROCm System Management Interface ======================= + 4: ================================= Concise Info ================================= + 4: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 4: 0 41.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 4: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 4: 2 42.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 4: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 4: 4 40.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 4: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 4: 6 39.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 4: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 4: ================================================================================ + 4: ============================= End of ROCm SMI Log ============================== +41: +41: +41: ======================= ROCm System Management Interface ======================= +41: ================================= Concise Info ================================= +41: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +41: 0 48.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +41: 1 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +41: 2 45.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +41: 3 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +41: 4 49.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +41: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +41: 6 45.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +41: 7 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +41: ================================================================================ +41: ============================= End of ROCm SMI Log ============================== +20: +20: +20: ======================= ROCm System Management Interface ======================= +20: ================================= Concise Info ================================= +20: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +20: 0 48.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +20: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +20: 2 37.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +20: 3 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +20: 4 43.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +20: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +20: 6 40.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +20: 7 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +20: ================================================================================ +20: ============================= End of ROCm SMI Log ============================== +31: +31: +31: ======================= ROCm System Management Interface ======================= +31: ================================= Concise Info ================================= +31: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +31: 0 50.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +31: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +31: 2 45.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +31: 3 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +31: 4 44.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +31: 5 51.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +31: 6 43.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +31: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +31: ================================================================================ +31: ============================= End of ROCm SMI Log ============================== +28: +28: +28: ======================= ROCm System Management Interface ======================= +28: ================================= Concise Info ================================= +28: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +28: 0 55.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +28: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +28: 2 39.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +28: 3 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +28: 4 40.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +28: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +28: 6 41.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +28: 7 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +28: ================================================================================ +28: ============================= End of ROCm SMI Log ============================== +40: +40: +40: ======================= ROCm System Management Interface ======================= +40: ================================= Concise Info ================================= +40: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +40: 0 45.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +40: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +40: 2 38.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +40: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +40: 4 44.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +40: 5 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +40: 6 41.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +40: 7 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +40: ================================================================================ +40: ============================= End of ROCm SMI Log ============================== +52: +52: +52: ======================= ROCm System Management Interface ======================= +52: ================================= Concise Info ================================= +52: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +52: 0 45.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +52: 1 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +52: 2 40.0c 98.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +52: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +52: 4 39.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +52: 5 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +52: 6 43.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +52: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +52: ================================================================================ +52: ============================= End of ROCm SMI Log ============================== +50: +50: +50: ======================= ROCm System Management Interface ======================= +50: ================================= Concise Info ================================= +50: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +50: 0 51.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +50: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +50: 2 44.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +50: 3 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +50: 4 44.0c 82.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +50: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +50: 6 37.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +50: 7 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +50: ================================================================================ +50: ============================= End of ROCm SMI Log ============================== +32: +32: +32: ======================= ROCm System Management Interface ======================= +32: ================================= Concise Info ================================= +32: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +32: 0 49.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +32: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +32: 2 45.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +32: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +32: 4 55.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +32: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +32: 6 42.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +32: 7 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +32: ================================================================================ +32: ============================= End of ROCm SMI Log ============================== +36: +36: +36: ======================= ROCm System Management Interface ======================= +36: ================================= Concise Info ================================= +36: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +36: 0 47.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +36: 1 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +36: 2 44.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +36: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +36: 4 42.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +36: 5 51.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +36: 6 46.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +36: 7 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +36: ================================================================================ +36: ============================= End of ROCm SMI Log ============================== + 7: + 7: + 7: ======================= ROCm System Management Interface ======================= + 7: ================================= Concise Info ================================= + 7: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 7: 0 44.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 7: 1 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 7: 2 37.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 7: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 7: 4 42.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 7: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 7: 6 43.0c 81.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 7: 7 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 7: ================================================================================ + 7: ============================= End of ROCm SMI Log ============================== + 6: + 6: + 6: ======================= ROCm System Management Interface ======================= + 6: ================================= Concise Info ================================= + 6: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 6: 0 47.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 6: 1 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 6: 2 40.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 6: 3 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 6: 4 40.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 6: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 6: 6 41.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 6: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 6: ================================================================================ + 6: ============================= End of ROCm SMI Log ============================== +39: +39: +39: ======================= ROCm System Management Interface ======================= +39: ================================= Concise Info ================================= +39: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +39: 0 47.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +39: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +39: 2 52.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +39: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +39: 4 38.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +39: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +39: 6 47.0c 81.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +39: 7 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +39: ================================================================================ +39: ============================= End of ROCm SMI Log ============================== +14: +14: +14: ======================= ROCm System Management Interface ======================= +14: ================================= Concise Info ================================= +14: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +14: 0 49.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +14: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +14: 2 40.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +14: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +14: 4 44.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +14: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +14: 6 48.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +14: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +14: ================================================================================ +14: ============================= End of ROCm SMI Log ============================== +11: +11: +11: ======================= ROCm System Management Interface ======================= +11: ================================= Concise Info ================================= +11: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +11: 0 37.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +11: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +11: 2 36.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +11: 3 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +11: 4 44.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +11: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +11: 6 38.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +11: 7 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +11: ================================================================================ +11: ============================= End of ROCm SMI Log ============================== +45: +45: +45: ======================= ROCm System Management Interface ======================= +45: ================================= Concise Info ================================= +45: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +45: 0 47.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +45: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +45: 2 39.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +45: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +45: 4 43.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +45: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +45: 6 37.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +45: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +45: ================================================================================ +45: ============================= End of ROCm SMI Log ============================== +14: Launching on nid006085 (14/64), master nid006071 port 9999, GPUs 8, CUDA: True +16: Launching on nid006087 (16/64), master nid006071 port 9999, GPUs 8, CUDA: True +24: Launching on nid006095 (24/64), master nid006071 port 9999, GPUs 8, CUDA: True +21: Launching on nid006092 (21/64), master nid006071 port 9999, GPUs 8, CUDA: True +28: Launching on nid006773 (28/64), master nid006071 port 9999, GPUs 8, CUDA: True +22: Launching on nid006093 (22/64), master nid006071 port 9999, GPUs 8, CUDA: True +13: Launching on nid006084 (13/64), master nid006071 port 9999, GPUs 8, CUDA: True +10: Launching on nid006081 (10/64), master nid006071 port 9999, GPUs 8, CUDA: True + 0: Launching on nid006071 (0/64), master nid006071 port 9999, GPUs 8, CUDA: True +37: Launching on nid006782 (37/64), master nid006071 port 9999, GPUs 8, CUDA: True +19: Launching on nid006090 (19/64), master nid006071 port 9999, GPUs 8, CUDA: True +62: Launching on nid006807 (62/64), master nid006071 port 9999, GPUs 8, CUDA: True +46: Launching on nid006791 (46/64), master nid006071 port 9999, GPUs 8, CUDA: True + 9: Launching on nid006080 (9/64), master nid006071 port 9999, GPUs 8, CUDA: True +25: Launching on nid006096 (25/64), master nid006071 port 9999, GPUs 8, CUDA: True +61: Launching on nid006806 (61/64), master nid006071 port 9999, GPUs 8, CUDA: True +15: Launching on nid006086 (15/64), master nid006071 port 9999, GPUs 8, CUDA: True +18: Launching on nid006089 (18/64), master nid006071 port 9999, GPUs 8, CUDA: True +48: Launching on nid006793 (48/64), master nid006071 port 9999, GPUs 8, CUDA: True +47: Launching on nid006792 (47/64), master nid006071 port 9999, GPUs 8, CUDA: True +55: Launching on nid006800 (55/64), master nid006071 port 9999, GPUs 8, CUDA: True +44: Launching on nid006789 (44/64), master nid006071 port 9999, GPUs 8, CUDA: True +42: Launching on nid006787 (42/64), master nid006071 port 9999, GPUs 8, CUDA: True +53: Launching on nid006798 (53/64), master nid006071 port 9999, GPUs 8, CUDA: True +63: Launching on nid006808 (63/64), master nid006071 port 9999, GPUs 8, CUDA: True +58: Launching on nid006803 (58/64), master nid006071 port 9999, GPUs 8, CUDA: True +54: Launching on nid006799 (54/64), master nid006071 port 9999, GPUs 8, CUDA: True + 3: Launching on nid006074 (3/64), master nid006071 port 9999, GPUs 8, CUDA: True +23: Launching on nid006094 (23/64), master nid006071 port 9999, GPUs 8, CUDA: True +26: Launching on nid006097 (26/64), master nid006071 port 9999, GPUs 8, CUDA: True +27: Launching on nid006772 (27/64), master nid006071 port 9999, GPUs 8, CUDA: True + 8: Launching on nid006079 (8/64), master nid006071 port 9999, GPUs 8, CUDA: True +29: Launching on nid006774 (29/64), master nid006071 port 9999, GPUs 8, CUDA: True +17: Launching on nid006088 (17/64), master nid006071 port 9999, GPUs 8, CUDA: True + 1: Launching on nid006072 (1/64), master nid006071 port 9999, GPUs 8, CUDA: True +56: Launching on nid006801 (56/64), master nid006071 port 9999, GPUs 8, CUDA: True +30: Launching on nid006775 (30/64), master nid006071 port 9999, GPUs 8, CUDA: True +12: Launching on nid006083 (12/64), master nid006071 port 9999, GPUs 8, CUDA: True + 2: Launching on nid006073 (2/64), master nid006071 port 9999, GPUs 8, CUDA: True +57: Launching on nid006802 (57/64), master nid006071 port 9999, GPUs 8, CUDA: True +60: Launching on nid006805 (60/64), master nid006071 port 9999, GPUs 8, CUDA: True +43: Launching on nid006788 (43/64), master nid006071 port 9999, GPUs 8, CUDA: True +34: Launching on nid006779 (34/64), master nid006071 port 9999, GPUs 8, CUDA: True +33: Launching on nid006778 (33/64), master nid006071 port 9999, GPUs 8, CUDA: True +38: Launching on nid006783 (38/64), master nid006071 port 9999, GPUs 8, CUDA: True +51: Launching on nid006796 (51/64), master nid006071 port 9999, GPUs 8, CUDA: True + 5: Launching on nid006076 (5/64), master nid006071 port 9999, GPUs 8, CUDA: True +41: Launching on nid006786 (41/64), master nid006071 port 9999, GPUs 8, CUDA: True +35: Launching on nid006780 (35/64), master nid006071 port 9999, GPUs 8, CUDA: True +59: Launching on nid006804 (59/64), master nid006071 port 9999, GPUs 8, CUDA: True + 4: Launching on nid006075 (4/64), master nid006071 port 9999, GPUs 8, CUDA: True + 7: Launching on nid006078 (7/64), master nid006071 port 9999, GPUs 8, CUDA: True +36: Launching on nid006781 (36/64), master nid006071 port 9999, GPUs 8, CUDA: True +20: Launching on nid006091 (20/64), master nid006071 port 9999, GPUs 8, CUDA: True +32: Launching on nid006777 (32/64), master nid006071 port 9999, GPUs 8, CUDA: True +50: Launching on nid006795 (50/64), master nid006071 port 9999, GPUs 8, CUDA: True +40: Launching on nid006785 (40/64), master nid006071 port 9999, GPUs 8, CUDA: True +49: Launching on nid006794 (49/64), master nid006071 port 9999, GPUs 8, CUDA: True + 6: Launching on nid006077 (6/64), master nid006071 port 9999, GPUs 8, CUDA: True +45: Launching on nid006790 (45/64), master nid006071 port 9999, GPUs 8, CUDA: True +11: Launching on nid006082 (11/64), master nid006071 port 9999, GPUs 8, CUDA: True +31: Launching on nid006776 (31/64), master nid006071 port 9999, GPUs 8, CUDA: True +39: Launching on nid006784 (39/64), master nid006071 port 9999, GPUs 8, CUDA: True +52: Launching on nid006797 (52/64), master nid006071 port 9999, GPUs 8, CUDA: True + 0: using world size: 512, data-parallel-size: 128, tensor-model-parallel size: 2, pipeline-model-parallel size: 2 + 0: accumulate and all-reduce gradients in fp32 for bfloat16 data type. + 0: using torch.bfloat16 for parameters ... + 0: ------------------------ arguments ------------------------ + 0: abort_on_unmet_fused_kernel_constraints ......... False + 0: accumulate_allreduce_grads_in_fp32 .............. True + 0: adam_beta1 ...................................... 0.9 + 0: adam_beta2 ...................................... 0.999 + 0: adam_eps ........................................ 1e-08 + 0: adlr_autoresume ................................. False + 0: adlr_autoresume_interval ........................ 1000 + 0: apply_query_key_layer_scaling ................... True + 0: apply_residual_connection_post_layernorm ........ False + 0: attention_dropout ............................... 0.1 + 0: attention_softmax_in_fp32 ....................... False + 0: bert_binary_head ................................ True + 0: bert_load ....................................... None + 0: bf16 ............................................ True + 0: bias_dropout_fusion ............................. True + 0: bias_gelu_fusion ................................ True + 0: biencoder_projection_dim ........................ 0 + 0: biencoder_shared_query_context_model ............ False + 0: block_data_path ................................. None + 0: checkpoint_activations .......................... False + 0: checkpoint_in_cpu ............................... False + 0: checkpoint_num_layers ........................... 1 + 0: clip_grad ....................................... 1.0 + 0: codecarbon_dir .................................. None + 0: consumed_train_samples .......................... 0 + 0: consumed_train_tokens ........................... 0 + 0: consumed_valid_samples .......................... 0 + 0: contigious_checkpointing ........................ False + 0: cpu_optimizer ................................... False + 0: cpu_torch_adam .................................. False + 0: curriculum_learning ............................. False + 0: data_impl ....................................... mmap + 0: data_parallel_size .............................. 128 + 0: data_path ....................................... None + 0: dataloader_type ................................. single + 0: DDP_impl ........................................ local + 0: decoder_seq_length .............................. None + 0: deepscale ....................................... False + 0: deepscale_config ................................ None + 0: deepspeed ....................................... True + 0: deepspeed_activation_checkpointing .............. False + 0: deepspeed_config ................................ ds_configs/3430973.json + 0: deepspeed_mpi ................................... False + 0: distribute_checkpointed_activations ............. False + 0: distributed_backend ............................. nccl + 0: embed_layernorm ................................. False + 0: embedding_path .................................. None + 0: encoder_seq_length .............................. 2048 + 0: eod_mask_loss ................................... False + 0: eval_interval ................................... 1 + 0: eval_iters ...................................... 100 + 0: eval_only ....................................... True + 0: evidence_data_path .............................. None + 0: exit_duration_in_mins ........................... None + 0: exit_interval ................................... None + 0: ffn_hidden_size ................................. 16384 + 0: finetune ........................................ False + 0: fp16 ............................................ False + 0: fp16_lm_cross_entropy ........................... False + 0: fp32_residual_connection ........................ False + 0: gigaflos_no_embeds .............................. 0 + 0: global_batch_size ............................... 512 + 0: glu_activation .................................. None + 0: hidden_dropout .................................. 0.1 + 0: hidden_size ..................................... 4096 + 0: hysteresis ...................................... 2 + 0: ict_head_size ................................... None + 0: ict_load ........................................ None + 0: img_dim ......................................... 224 + 0: indexer_batch_size .............................. 128 + 0: indexer_log_interval ............................ 1000 + 0: inference ....................................... False + 0: init_method_std ................................. 0.02 + 0: init_method_xavier_uniform ...................... False + 0: initial_loss_scale .............................. 4294967296 + 0: kill_switch_path ................................ kill-switch-8b7178b35bval + 0: kv_channels ..................................... 128 + 0: layer_norm_fusion ............................... True + 0: layernorm_epsilon ............................... 1e-05 + 0: lazy_mpu_init ................................... None + 0: load ............................................ lm1-8b7-178b-c4-repetitions/8b7178b35b + 0: local_rank ...................................... None + 0: log_batch_size_to_tensorboard ................... True + 0: log_interval .................................... 10 + 0: log_learning_rate_to_tensorboard ................ True + 0: log_level ....................................... None + 0: log_level_replica ............................... None + 0: log_loss_scale_to_tensorboard ................... True + 0: log_num_zeros_in_grad ........................... False + 0: log_params_norm ................................. False + 0: log_path ........................................ None + 0: log_timers_to_tensorboard ....................... True + 0: log_validation_ppl_to_tensorboard ............... True + 0: loss_on_targets_only ............................ False + 0: loss_scale ...................................... None + 0: loss_scale_window ............................... 1000 + 0: lr .............................................. 0.0002 + 0: lr_decay_iters .................................. None + 0: lr_decay_samples ................................ 1 + 0: lr_decay_style .................................. cosine + 0: lr_decay_tokens ................................. None + 0: lr_warmup_fraction .............................. None + 0: lr_warmup_iters ................................. 0 + 0: lr_warmup_samples ............................... 0 + 0: make_vocab_size_divisible_by .................... 128 + 0: mask_prob ....................................... 0.15 + 0: masked_softmax_fusion ........................... True + 0: max_position_embeddings ......................... 2048 + 0: mean_noise_span_length .......................... None + 0: memory_centric_tiled_linear ..................... False + 0: merge_file ...................................... gpt2/merges.txt + 0: micro_batch_size ................................ 1 + 0: min_loss_scale .................................. 1.0 + 0: min_lr .......................................... 2e-05 + 0: mmap_warmup ..................................... False + 0: no_load_optim ................................... True + 0: no_load_rng ..................................... None + 0: no_save_optim ................................... None + 0: no_save_rng ..................................... None + 0: noise_density ................................... None + 0: num_attention_heads ............................. 32 + 0: num_channels .................................... 3 + 0: num_classes ..................................... 1000 + 0: num_layers ...................................... 42 + 0: num_layers_per_virtual_pipeline_stage ........... None + 0: num_workers ..................................... 0 + 0: onnx_safe ....................................... None + 0: openai_gelu ..................................... False + 0: optimizer ....................................... adam + 0: optimizer_fusion ................................ True + 0: override_lr_scheduler ........................... True + 0: pad_vocab_size_to ............................... None + 0: params_dtype .................................... torch.bfloat16 + 0: partition_activations ........................... False + 0: patch_dim ....................................... 16 + 0: pipeline_model_parallel_size .................... 2 + 0: position_embedding_type ......................... PositionEmbeddingType.absolute + 0: pp_partition_method ............................. None + 0: profile_backward ................................ False + 0: query_in_block_prob ............................. 0.1 + 0: rampup_batch_size ............................... None + 0: rank ............................................ 0 + 0: remote_device ................................... none + 0: reset_attention_mask ............................ False + 0: reset_position_ids .............................. False + 0: reset_progress .................................. True + 0: retriever_report_topk_accuracies ................ [] + 0: retriever_score_scaling ......................... False + 0: retriever_seq_length ............................ 256 + 0: reweight_loss_based_on_position_frequency ....... False + 0: sample_rate ..................................... 1.0 + 0: save ............................................ lm1-8b7-178b-c4-repetitions/8b7178b35b + 0: save_interval ................................... 5000 + 0: scatter_gather_tensors_in_pipeline .............. True + 0: scattered_embeddings ............................ False + 0: seed ............................................ 1234 + 0: seq_length ...................................... 2048 + 0: sgd_momentum .................................... 0.9 + 0: short_seq_prob .................................. 0.1 + 0: skip_train_iteration_range ...................... None + 0: split ........................................... None + 0: split_transformers .............................. False + 0: sync_tp_duplicated_parameters ................... False + 0: synchronize_each_layer .......................... False + 0: tensor_model_parallel_size ...................... 2 + 0: tensorboard_dir ................................. tensorboard_8b7178b35bval + 0: tensorboard_log_interval ........................ 1 + 0: tensorboard_queue_size .......................... 5 + 0: test_weighted_split_paths ....................... None + 0: test_weighted_split_paths_path .................. None + 0: tile_factor ..................................... 1 + 0: titles_data_path ................................ None + 0: tokenizer_name_or_path .......................... None + 0: tokenizer_type .................................. GPT2BPETokenizer + 0: train_iters ..................................... None + 0: train_samples ................................... 1 + 0: train_tokens .................................... None + 0: train_weighted_split_names ...................... ['train'] + 0: train_weighted_split_paths ...................... [['/scratch/project_462000119/data/c4_subsampled/gpt2tok_c4_en_400M_text_document']] + 0: train_weighted_split_paths_path ................. None + 0: train_weighted_split_splits ..................... [['0:1']] + 0: train_weighted_split_weights .................... [['1.0']] + 0: universal_checkpoint ............................ False + 0: use_bnb_optimizer ............................... False + 0: use_checkpoint_lr_scheduler ..................... False + 0: use_contiguous_buffers_in_ddp ................... True + 0: use_cpu_initialization .......................... None + 0: use_one_sent_docs ............................... False + 0: use_pin_memory .................................. False + 0: valid_num_workers ............................... 0 + 0: valid_weighted_split_names ...................... ['validation'] + 0: valid_weighted_split_paths ...................... [['/scratch/project_462000119/data/c4_validation/gpt2tok_c4validation_rerun_text_document']] + 0: valid_weighted_split_paths_path ................. None + 0: valid_weighted_split_splits ..................... [['0:1']] + 0: valid_weighted_split_weights .................... [['1.0']] + 0: virtual_pipeline_model_parallel_size ............ None + 0: vocab_extra_ids ................................. 0 + 0: vocab_file ...................................... gpt2/vocab.json + 0: weight_decay .................................... 0.1 + 0: world_size ...................................... 512 + 0: zero_allgather_bucket_size ...................... 0.0 + 0: zero_contigious_gradients ....................... False + 0: zero_reduce_bucket_size ......................... 0.0 + 0: zero_reduce_scatter ............................. False + 0: zero_stage ...................................... 0 + 0: -------------------- end of arguments --------------------- + 0: setting number of micro-batches to constant 4 + 0: > building GPT2BPETokenizer tokenizer ... + 0: > padded vocab (size: 50257) with 175 dummy tokens (new size: 50432) + 0: DeepSpeed general environment info: + 0: torch install path ............... ['/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch'] + 0: torch version .................... 1.13.0+rocm5.2 + 0: torch cuda version ............... None + 0: torch hip version ................ 5.2.21151-afdc89f8 + 0: nvcc version ..................... None + 0: deepspeed install path ........... ['/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed'] + 0: deepspeed info ................... 0.7.5, unknown, unknown + 0: deepspeed wheel compiled w. ...... torch 1.13, hip 5.1 + 0: **** Git info for Megatron: git_hash=unknown git_branch=unknown **** + 0: > initializing torch distributed ... + 0: [2023-04-29 11:36:24,814] [INFO] [comm.py:633:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +63: > setting tensorboard ... + 0: > initializing tensor model parallel with size 2 + 0: > initializing pipeline model parallel with size 2 + 0: > setting random seeds to 1234 ... + 0: > initializing model parallel cuda seeds on global rank 0, model parallel rank 0, and data parallel rank 0 with model parallel seed: 3952 and data parallel seed: 1234 + 0: > compiling dataset index builder ... + 0: make: Entering directory '/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/data' + 0: make: Nothing to be done for 'default'. + 0: make: Leaving directory '/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/data' + 0: >>> done with dataset index builder. Compilation time: 0.112 seconds + 0: > compiling and loading fused kernels ... + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.cpp [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_cuda.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.hip [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] + 0: Total number of unsupported CUDA function calls: 0 + 0: + 0: + 0: Total number of replaced kernel launches: 87 + 0: ninja: no work to do. + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.cpp [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_cuda.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.hip [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] + 0: Total number of unsupported CUDA function calls: 0 + 0: + 0: + 0: Total number of replaced kernel launches: 63 + 0: [1/1] c++ scaled_masked_softmax_hip.o scaled_masked_softmax_hip.cuda.o -shared -L/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/lib -lc10 -lc10_hip -ltorch_cpu -ltorch_hip -ltorch -ltorch_python -L/opt/rocm/lib -lamdhip64 -o scaled_masked_softmax_cuda.so + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda.cpp [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda_kernel.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_hip_kernel.hip [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] + 0: Total number of unsupported CUDA function calls: 0 + 0: + 0: + 0: Total number of replaced kernel launches: 67 + 0: ninja: no work to do. + 0: >>> done with compiling and loading fused kernels. Compilation time: 27.423 seconds + 0: time to initialize megatron (seconds): 47.672 + 0: [after megatron is initialized] datetime: 2023-04-29 11:37:03 + 0: building GPT model ... + 0: [2023-04-29 11:37:03,817] [INFO] [utils.py:827:see_memory_usage] Before Building Model + 0: [2023-04-29 11:37:03,817] [INFO] [utils.py:828:see_memory_usage] MA 0.0 GB Max_MA 0.0 GB CA 0.0 GB Max_CA 0 GB + 0: [2023-04-29 11:37:03,818] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 38.59 GB, percent = 7.7% + 0: SEED_LAYERS=False BASE_SEED=1234 SEED_FN=None + 0: Using topology: {ProcessCoord(pipe=0, data=0, model=0): 0, ProcessCoord(pipe=0, data=0, model=1): 1, ProcessCoord(pipe=0, data=1, model=0): 2, ProcessCoord(pipe=0, data=1, model=1): 3, ProcessCoord(pipe=0, data=2, model=0): 4, ProcessCoord(pipe=0, data=2, model=1): 5, ProcessCoord(pipe=0, data=3, model=0): 6, ProcessCoord(pipe=0, data=3, model=1): 7, ProcessCoord(pipe=0, data=4, model=0): 8, ProcessCoord(pipe=0, data=4, model=1): 9, ProcessCoord(pipe=0, data=5, model=0): 10, ProcessCoord(pipe=0, data=5, model=1): 11, ProcessCoord(pipe=0, data=6, model=0): 12, ProcessCoord(pipe=0, data=6, model=1): 13, ProcessCoord(pipe=0, data=7, model=0): 14, ProcessCoord(pipe=0, data=7, model=1): 15, ProcessCoord(pipe=0, data=8, model=0): 16, ProcessCoord(pipe=0, data=8, model=1): 17, ProcessCoord(pipe=0, data=9, model=0): 18, ProcessCoord(pipe=0, data=9, model=1): 19, ProcessCoord(pipe=0, data=10, model=0): 20, ProcessCoord(pipe=0, data=10, model=1): 21, ProcessCoord(pipe=0, data=11, model=0): 22, ProcessCoord(pipe=0, data + 0: =11, model=1): 23, ProcessCoord(pipe=0, data=12, model=0): 24, ProcessCoord(pipe=0, data=12, model=1): 25, ProcessCoord(pipe=0, data=13, model=0): 26, ProcessCoord(pipe=0, data=13, model=1): 27, ProcessCoord(pipe=0, data=14, model=0): 28, ProcessCoord(pipe=0, data=14, model=1): 29, ProcessCoord(pipe=0, data=15, model=0): 30, ProcessCoord(pipe=0, data=15, model=1): 31, ProcessCoord(pipe=0, data=16, model=0): 32, ProcessCoord(pipe=0, data=16, model=1): 33, ProcessCoord(pipe=0, data=17, model=0): 34, ProcessCoord(pipe=0, data=17, model=1): 35, ProcessCoord(pipe=0, data=18, model=0): 36, ProcessCoord(pipe=0, data=18, model=1): 37, ProcessCoord(pipe=0, data=19, model=0): 38, ProcessCoord(pipe=0, data=19, model=1): 39, ProcessCoord(pipe=0, data=20, model=0): 40, ProcessCoord(pipe=0, data=20, model=1): 41, ProcessCoord(pipe=0, data=21, model=0): 42, ProcessCoord(pipe=0, data=21, model=1): 43, ProcessCoord(pipe=0, data=22, model=0): 44, ProcessCoord(pipe=0, data=22, model=1): 45, ProcessCoord(pipe=0, data=23, model=0 + 0: ): 46, ProcessCoord(pipe=0, data=23, model=1): 47, ProcessCoord(pipe=0, data=24, model=0): 48, ProcessCoord(pipe=0, data=24, model=1): 49, ProcessCoord(pipe=0, data=25, model=0): 50, ProcessCoord(pipe=0, data=25, model=1): 51, ProcessCoord(pipe=0, data=26, model=0): 52, ProcessCoord(pipe=0, data=26, model=1): 53, ProcessCoord(pipe=0, data=27, model=0): 54, ProcessCoord(pipe=0, data=27, model=1): 55, ProcessCoord(pipe=0, data=28, model=0): 56, ProcessCoord(pipe=0, data=28, model=1): 57, ProcessCoord(pipe=0, data=29, model=0): 58, ProcessCoord(pipe=0, data=29, model=1): 59, ProcessCoord(pipe=0, data=30, model=0): 60, ProcessCoord(pipe=0, data=30, model=1): 61, ProcessCoord(pipe=0, data=31, model=0): 62, ProcessCoord(pipe=0, data=31, model=1): 63, ProcessCoord(pipe=0, data=32, model=0): 64, ProcessCoord(pipe=0, data=32, model=1): 65, ProcessCoord(pipe=0, data=33, model=0): 66, ProcessCoord(pipe=0, data=33, model=1): 67, ProcessCoord(pipe=0, data=34, model=0): 68, ProcessCoord(pipe=0, data=34, model=1): 69, Proce + 0: ssCoord(pipe=0, data=35, model=0): 70, ProcessCoord(pipe=0, data=35, model=1): 71, ProcessCoord(pipe=0, data=36, model=0): 72, ProcessCoord(pipe=0, data=36, model=1): 73, ProcessCoord(pipe=0, data=37, model=0): 74, ProcessCoord(pipe=0, data=37, model=1): 75, ProcessCoord(pipe=0, data=38, model=0): 76, ProcessCoord(pipe=0, data=38, model=1): 77, ProcessCoord(pipe=0, data=39, model=0): 78, ProcessCoord(pipe=0, data=39, model=1): 79, ProcessCoord(pipe=0, data=40, model=0): 80, ProcessCoord(pipe=0, data=40, model=1): 81, ProcessCoord(pipe=0, data=41, model=0): 82, ProcessCoord(pipe=0, data=41, model=1): 83, ProcessCoord(pipe=0, data=42, model=0): 84, ProcessCoord(pipe=0, data=42, model=1): 85, ProcessCoord(pipe=0, data=43, model=0): 86, ProcessCoord(pipe=0, data=43, model=1): 87, ProcessCoord(pipe=0, data=44, model=0): 88, ProcessCoord(pipe=0, data=44, model=1): 89, ProcessCoord(pipe=0, data=45, model=0): 90, ProcessCoord(pipe=0, data=45, model=1): 91, ProcessCoord(pipe=0, data=46, model=0): 92, ProcessCoord(pipe + 0: =0, data=46, model=1): 93, ProcessCoord(pipe=0, data=47, model=0): 94, ProcessCoord(pipe=0, data=47, model=1): 95, ProcessCoord(pipe=0, data=48, model=0): 96, ProcessCoord(pipe=0, data=48, model=1): 97, ProcessCoord(pipe=0, data=49, model=0): 98, ProcessCoord(pipe=0, data=49, model=1): 99, ProcessCoord(pipe=0, data=50, model=0): 100, ProcessCoord(pipe=0, data=50, model=1): 101, ProcessCoord(pipe=0, data=51, model=0): 102, ProcessCoord(pipe=0, data=51, model=1): 103, ProcessCoord(pipe=0, data=52, model=0): 104, ProcessCoord(pipe=0, data=52, model=1): 105, ProcessCoord(pipe=0, data=53, model=0): 106, ProcessCoord(pipe=0, data=53, model=1): 107, ProcessCoord(pipe=0, data=54, model=0): 108, ProcessCoord(pipe=0, data=54, model=1): 109, ProcessCoord(pipe=0, data=55, model=0): 110, ProcessCoord(pipe=0, data=55, model=1): 111, ProcessCoord(pipe=0, data=56, model=0): 112, ProcessCoord(pipe=0, data=56, model=1): 113, ProcessCoord(pipe=0, data=57, model=0): 114, ProcessCoord(pipe=0, data=57, model=1): 115, ProcessCoord( + 0: pipe=0, data=58, model=0): 116, ProcessCoord(pipe=0, data=58, model=1): 117, ProcessCoord(pipe=0, data=59, model=0): 118, ProcessCoord(pipe=0, data=59, model=1): 119, ProcessCoord(pipe=0, data=60, model=0): 120, ProcessCoord(pipe=0, data=60, model=1): 121, ProcessCoord(pipe=0, data=61, model=0): 122, ProcessCoord(pipe=0, data=61, model=1): 123, ProcessCoord(pipe=0, data=62, model=0): 124, ProcessCoord(pipe=0, data=62, model=1): 125, ProcessCoord(pipe=0, data=63, model=0): 126, ProcessCoord(pipe=0, data=63, model=1): 127, ProcessCoord(pipe=0, data=64, model=0): 128, ProcessCoord(pipe=0, data=64, model=1): 129, ProcessCoord(pipe=0, data=65, model=0): 130, ProcessCoord(pipe=0, data=65, model=1): 131, ProcessCoord(pipe=0, data=66, model=0): 132, ProcessCoord(pipe=0, data=66, model=1): 133, ProcessCoord(pipe=0, data=67, model=0): 134, ProcessCoord(pipe=0, data=67, model=1): 135, ProcessCoord(pipe=0, data=68, model=0): 136, ProcessCoord(pipe=0, data=68, model=1): 137, ProcessCoord(pipe=0, data=69, model=0): 138, Pr + 0: ocessCoord(pipe=0, data=69, model=1): 139, ProcessCoord(pipe=0, data=70, model=0): 140, ProcessCoord(pipe=0, data=70, model=1): 141, ProcessCoord(pipe=0, data=71, model=0): 142, ProcessCoord(pipe=0, data=71, model=1): 143, ProcessCoord(pipe=0, data=72, model=0): 144, ProcessCoord(pipe=0, data=72, model=1): 145, ProcessCoord(pipe=0, data=73, model=0): 146, ProcessCoord(pipe=0, data=73, model=1): 147, ProcessCoord(pipe=0, data=74, model=0): 148, ProcessCoord(pipe=0, data=74, model=1): 149, ProcessCoord(pipe=0, data=75, model=0): 150, ProcessCoord(pipe=0, data=75, model=1): 151, ProcessCoord(pipe=0, data=76, model=0): 152, ProcessCoord(pipe=0, data=76, model=1): 153, ProcessCoord(pipe=0, data=77, model=0): 154, ProcessCoord(pipe=0, data=77, model=1): 155, ProcessCoord(pipe=0, data=78, model=0): 156, ProcessCoord(pipe=0, data=78, model=1): 157, ProcessCoord(pipe=0, data=79, model=0): 158, ProcessCoord(pipe=0, data=79, model=1): 159, ProcessCoord(pipe=0, data=80, model=0): 160, ProcessCoord(pipe=0, data=80, model= + 0: 1): 161, ProcessCoord(pipe=0, data=81, model=0): 162, ProcessCoord(pipe=0, data=81, model=1): 163, ProcessCoord(pipe=0, data=82, model=0): 164, ProcessCoord(pipe=0, data=82, model=1): 165, ProcessCoord(pipe=0, data=83, model=0): 166, ProcessCoord(pipe=0, data=83, model=1): 167, ProcessCoord(pipe=0, data=84, model=0): 168, ProcessCoord(pipe=0, data=84, model=1): 169, ProcessCoord(pipe=0, data=85, model=0): 170, ProcessCoord(pipe=0, data=85, model=1): 171, ProcessCoord(pipe=0, data=86, model=0): 172, ProcessCoord(pipe=0, data=86, model=1): 173, ProcessCoord(pipe=0, data=87, model=0): 174, ProcessCoord(pipe=0, data=87, model=1): 175, ProcessCoord(pipe=0, data=88, model=0): 176, ProcessCoord(pipe=0, data=88, model=1): 177, ProcessCoord(pipe=0, data=89, model=0): 178, ProcessCoord(pipe=0, data=89, model=1): 179, ProcessCoord(pipe=0, data=90, model=0): 180, ProcessCoord(pipe=0, data=90, model=1): 181, ProcessCoord(pipe=0, data=91, model=0): 182, ProcessCoord(pipe=0, data=91, model=1): 183, ProcessCoord(pipe=0, data + 0: =92, model=0): 184, ProcessCoord(pipe=0, data=92, model=1): 185, ProcessCoord(pipe=0, data=93, model=0): 186, ProcessCoord(pipe=0, data=93, model=1): 187, ProcessCoord(pipe=0, data=94, model=0): 188, ProcessCoord(pipe=0, data=94, model=1): 189, ProcessCoord(pipe=0, data=95, model=0): 190, ProcessCoord(pipe=0, data=95, model=1): 191, ProcessCoord(pipe=0, data=96, model=0): 192, ProcessCoord(pipe=0, data=96, model=1): 193, ProcessCoord(pipe=0, data=97, model=0): 194, ProcessCoord(pipe=0, data=97, model=1): 195, ProcessCoord(pipe=0, data=98, model=0): 196, ProcessCoord(pipe=0, data=98, model=1): 197, ProcessCoord(pipe=0, data=99, model=0): 198, ProcessCoord(pipe=0, data=99, model=1): 199, ProcessCoord(pipe=0, data=100, model=0): 200, ProcessCoord(pipe=0, data=100, model=1): 201, ProcessCoord(pipe=0, data=101, model=0): 202, ProcessCoord(pipe=0, data=101, model=1): 203, ProcessCoord(pipe=0, data=102, model=0): 204, ProcessCoord(pipe=0, data=102, model=1): 205, ProcessCoord(pipe=0, data=103, model=0): 206, Process + 0: Coord(pipe=0, data=103, model=1): 207, ProcessCoord(pipe=0, data=104, model=0): 208, ProcessCoord(pipe=0, data=104, model=1): 209, ProcessCoord(pipe=0, data=105, model=0): 210, ProcessCoord(pipe=0, data=105, model=1): 211, ProcessCoord(pipe=0, data=106, model=0): 212, ProcessCoord(pipe=0, data=106, model=1): 213, ProcessCoord(pipe=0, data=107, model=0): 214, ProcessCoord(pipe=0, data=107, model=1): 215, ProcessCoord(pipe=0, data=108, model=0): 216, ProcessCoord(pipe=0, data=108, model=1): 217, ProcessCoord(pipe=0, data=109, model=0): 218, ProcessCoord(pipe=0, data=109, model=1): 219, ProcessCoord(pipe=0, data=110, model=0): 220, ProcessCoord(pipe=0, data=110, model=1): 221, ProcessCoord(pipe=0, data=111, model=0): 222, ProcessCoord(pipe=0, data=111, model=1): 223, ProcessCoord(pipe=0, data=112, model=0): 224, ProcessCoord(pipe=0, data=112, model=1): 225, ProcessCoord(pipe=0, data=113, model=0): 226, ProcessCoord(pipe=0, data=113, model=1): 227, ProcessCoord(pipe=0, data=114, model=0): 228, ProcessCoord(pipe=0 + 0: , data=114, model=1): 229, ProcessCoord(pipe=0, data=115, model=0): 230, ProcessCoord(pipe=0, data=115, model=1): 231, ProcessCoord(pipe=0, data=116, model=0): 232, ProcessCoord(pipe=0, data=116, model=1): 233, ProcessCoord(pipe=0, data=117, model=0): 234, ProcessCoord(pipe=0, data=117, model=1): 235, ProcessCoord(pipe=0, data=118, model=0): 236, ProcessCoord(pipe=0, data=118, model=1): 237, ProcessCoord(pipe=0, data=119, model=0): 238, ProcessCoord(pipe=0, data=119, model=1): 239, ProcessCoord(pipe=0, data=120, model=0): 240, ProcessCoord(pipe=0, data=120, model=1): 241, ProcessCoord(pipe=0, data=121, model=0): 242, ProcessCoord(pipe=0, data=121, model=1): 243, ProcessCoord(pipe=0, data=122, model=0): 244, ProcessCoord(pipe=0, data=122, model=1): 245, ProcessCoord(pipe=0, data=123, model=0): 246, ProcessCoord(pipe=0, data=123, model=1): 247, ProcessCoord(pipe=0, data=124, model=0): 248, ProcessCoord(pipe=0, data=124, model=1): 249, ProcessCoord(pipe=0, data=125, model=0): 250, ProcessCoord(pipe=0, data=125, + 0: model=1): 251, ProcessCoord(pipe=0, data=126, model=0): 252, ProcessCoord(pipe=0, data=126, model=1): 253, ProcessCoord(pipe=0, data=127, model=0): 254, ProcessCoord(pipe=0, data=127, model=1): 255, ProcessCoord(pipe=1, data=0, model=0): 256, ProcessCoord(pipe=1, data=0, model=1): 257, ProcessCoord(pipe=1, data=1, model=0): 258, ProcessCoord(pipe=1, data=1, model=1): 259, ProcessCoord(pipe=1, data=2, model=0): 260, ProcessCoord(pipe=1, data=2, model=1): 261, ProcessCoord(pipe=1, data=3, model=0): 262, ProcessCoord(pipe=1, data=3, model=1): 263, ProcessCoord(pipe=1, data=4, model=0): 264, ProcessCoord(pipe=1, data=4, model=1): 265, ProcessCoord(pipe=1, data=5, model=0): 266, ProcessCoord(pipe=1, data=5, model=1): 267, ProcessCoord(pipe=1, data=6, model=0): 268, ProcessCoord(pipe=1, data=6, model=1): 269, ProcessCoord(pipe=1, data=7, model=0): 270, ProcessCoord(pipe=1, data=7, model=1): 271, ProcessCoord(pipe=1, data=8, model=0): 272, ProcessCoord(pipe=1, data=8, model=1): 273, ProcessCoord(pipe=1, data=9, mode + 0: l=0): 274, ProcessCoord(pipe=1, data=9, model=1): 275, ProcessCoord(pipe=1, data=10, model=0): 276, ProcessCoord(pipe=1, data=10, model=1): 277, ProcessCoord(pipe=1, data=11, model=0): 278, ProcessCoord(pipe=1, data=11, model=1): 279, ProcessCoord(pipe=1, data=12, model=0): 280, ProcessCoord(pipe=1, data=12, model=1): 281, ProcessCoord(pipe=1, data=13, model=0): 282, ProcessCoord(pipe=1, data=13, model=1): 283, ProcessCoord(pipe=1, data=14, model=0): 284, ProcessCoord(pipe=1, data=14, model=1): 285, ProcessCoord(pipe=1, data=15, model=0): 286, ProcessCoord(pipe=1, data=15, model=1): 287, ProcessCoord(pipe=1, data=16, model=0): 288, ProcessCoord(pipe=1, data=16, model=1): 289, ProcessCoord(pipe=1, data=17, model=0): 290, ProcessCoord(pipe=1, data=17, model=1): 291, ProcessCoord(pipe=1, data=18, model=0): 292, ProcessCoord(pipe=1, data=18, model=1): 293, ProcessCoord(pipe=1, data=19, model=0): 294, ProcessCoord(pipe=1, data=19, model=1): 295, ProcessCoord(pipe=1, data=20, model=0): 296, ProcessCoord(pipe=1, dat + 0: a=20, model=1): 297, ProcessCoord(pipe=1, data=21, model=0): 298, ProcessCoord(pipe=1, data=21, model=1): 299, ProcessCoord(pipe=1, data=22, model=0): 300, ProcessCoord(pipe=1, data=22, model=1): 301, ProcessCoord(pipe=1, data=23, model=0): 302, ProcessCoord(pipe=1, data=23, model=1): 303, ProcessCoord(pipe=1, data=24, model=0): 304, ProcessCoord(pipe=1, data=24, model=1): 305, ProcessCoord(pipe=1, data=25, model=0): 306, ProcessCoord(pipe=1, data=25, model=1): 307, ProcessCoord(pipe=1, data=26, model=0): 308, ProcessCoord(pipe=1, data=26, model=1): 309, ProcessCoord(pipe=1, data=27, model=0): 310, ProcessCoord(pipe=1, data=27, model=1): 311, ProcessCoord(pipe=1, data=28, model=0): 312, ProcessCoord(pipe=1, data=28, model=1): 313, ProcessCoord(pipe=1, data=29, model=0): 314, ProcessCoord(pipe=1, data=29, model=1): 315, ProcessCoord(pipe=1, data=30, model=0): 316, ProcessCoord(pipe=1, data=30, model=1): 317, ProcessCoord(pipe=1, data=31, model=0): 318, ProcessCoord(pipe=1, data=31, model=1): 319, ProcessCoord( + 0: pipe=1, data=32, model=0): 320, ProcessCoord(pipe=1, data=32, model=1): 321, ProcessCoord(pipe=1, data=33, model=0): 322, ProcessCoord(pipe=1, data=33, model=1): 323, ProcessCoord(pipe=1, data=34, model=0): 324, ProcessCoord(pipe=1, data=34, model=1): 325, ProcessCoord(pipe=1, data=35, model=0): 326, ProcessCoord(pipe=1, data=35, model=1): 327, ProcessCoord(pipe=1, data=36, model=0): 328, ProcessCoord(pipe=1, data=36, model=1): 329, ProcessCoord(pipe=1, data=37, model=0): 330, ProcessCoord(pipe=1, data=37, model=1): 331, ProcessCoord(pipe=1, data=38, model=0): 332, ProcessCoord(pipe=1, data=38, model=1): 333, ProcessCoord(pipe=1, data=39, model=0): 334, ProcessCoord(pipe=1, data=39, model=1): 335, ProcessCoord(pipe=1, data=40, model=0): 336, ProcessCoord(pipe=1, data=40, model=1): 337, ProcessCoord(pipe=1, data=41, model=0): 338, ProcessCoord(pipe=1, data=41, model=1): 339, ProcessCoord(pipe=1, data=42, model=0): 340, ProcessCoord(pipe=1, data=42, model=1): 341, ProcessCoord(pipe=1, data=43, model=0): 342, Pr + 0: ocessCoord(pipe=1, data=43, model=1): 343, ProcessCoord(pipe=1, data=44, model=0): 344, ProcessCoord(pipe=1, data=44, model=1): 345, ProcessCoord(pipe=1, data=45, model=0): 346, ProcessCoord(pipe=1, data=45, model=1): 347, ProcessCoord(pipe=1, data=46, model=0): 348, ProcessCoord(pipe=1, data=46, model=1): 349, ProcessCoord(pipe=1, data=47, model=0): 350, ProcessCoord(pipe=1, data=47, model=1): 351, ProcessCoord(pipe=1, data=48, model=0): 352, ProcessCoord(pipe=1, data=48, model=1): 353, ProcessCoord(pipe=1, data=49, model=0): 354, ProcessCoord(pipe=1, data=49, model=1): 355, ProcessCoord(pipe=1, data=50, model=0): 356, ProcessCoord(pipe=1, data=50, model=1): 357, ProcessCoord(pipe=1, data=51, model=0): 358, ProcessCoord(pipe=1, data=51, model=1): 359, ProcessCoord(pipe=1, data=52, model=0): 360, ProcessCoord(pipe=1, data=52, model=1): 361, ProcessCoord(pipe=1, data=53, model=0): 362, ProcessCoord(pipe=1, data=53, model=1): 363, ProcessCoord(pipe=1, data=54, model=0): 364, ProcessCoord(pipe=1, data=54, model= + 0: 1): 365, ProcessCoord(pipe=1, data=55, model=0): 366, ProcessCoord(pipe=1, data=55, model=1): 367, ProcessCoord(pipe=1, data=56, model=0): 368, ProcessCoord(pipe=1, data=56, model=1): 369, ProcessCoord(pipe=1, data=57, model=0): 370, ProcessCoord(pipe=1, data=57, model=1): 371, ProcessCoord(pipe=1, data=58, model=0): 372, ProcessCoord(pipe=1, data=58, model=1): 373, ProcessCoord(pipe=1, data=59, model=0): 374, ProcessCoord(pipe=1, data=59, model=1): 375, ProcessCoord(pipe=1, data=60, model=0): 376, ProcessCoord(pipe=1, data=60, model=1): 377, ProcessCoord(pipe=1, data=61, model=0): 378, ProcessCoord(pipe=1, data=61, model=1): 379, ProcessCoord(pipe=1, data=62, model=0): 380, ProcessCoord(pipe=1, data=62, model=1): 381, ProcessCoord(pipe=1, data=63, model=0): 382, ProcessCoord(pipe=1, data=63, model=1): 383, ProcessCoord(pipe=1, data=64, model=0): 384, ProcessCoord(pipe=1, data=64, model=1): 385, ProcessCoord(pipe=1, data=65, model=0): 386, ProcessCoord(pipe=1, data=65, model=1): 387, ProcessCoord(pipe=1, data + 0: =66, model=0): 388, ProcessCoord(pipe=1, data=66, model=1): 389, ProcessCoord(pipe=1, data=67, model=0): 390, ProcessCoord(pipe=1, data=67, model=1): 391, ProcessCoord(pipe=1, data=68, model=0): 392, ProcessCoord(pipe=1, data=68, model=1): 393, ProcessCoord(pipe=1, data=69, model=0): 394, ProcessCoord(pipe=1, data=69, model=1): 395, ProcessCoord(pipe=1, data=70, model=0): 396, ProcessCoord(pipe=1, data=70, model=1): 397, ProcessCoord(pipe=1, data=71, model=0): 398, ProcessCoord(pipe=1, data=71, model=1): 399, ProcessCoord(pipe=1, data=72, model=0): 400, ProcessCoord(pipe=1, data=72, model=1): 401, ProcessCoord(pipe=1, data=73, model=0): 402, ProcessCoord(pipe=1, data=73, model=1): 403, ProcessCoord(pipe=1, data=74, model=0): 404, ProcessCoord(pipe=1, data=74, model=1): 405, ProcessCoord(pipe=1, data=75, model=0): 406, ProcessCoord(pipe=1, data=75, model=1): 407, ProcessCoord(pipe=1, data=76, model=0): 408, ProcessCoord(pipe=1, data=76, model=1): 409, ProcessCoord(pipe=1, data=77, model=0): 410, ProcessCoord(p + 0: ipe=1, data=77, model=1): 411, ProcessCoord(pipe=1, data=78, model=0): 412, ProcessCoord(pipe=1, data=78, model=1): 413, ProcessCoord(pipe=1, data=79, model=0): 414, ProcessCoord(pipe=1, data=79, model=1): 415, ProcessCoord(pipe=1, data=80, model=0): 416, ProcessCoord(pipe=1, data=80, model=1): 417, ProcessCoord(pipe=1, data=81, model=0): 418, ProcessCoord(pipe=1, data=81, model=1): 419, ProcessCoord(pipe=1, data=82, model=0): 420, ProcessCoord(pipe=1, data=82, model=1): 421, ProcessCoord(pipe=1, data=83, model=0): 422, ProcessCoord(pipe=1, data=83, model=1): 423, ProcessCoord(pipe=1, data=84, model=0): 424, ProcessCoord(pipe=1, data=84, model=1): 425, ProcessCoord(pipe=1, data=85, model=0): 426, ProcessCoord(pipe=1, data=85, model=1): 427, ProcessCoord(pipe=1, data=86, model=0): 428, ProcessCoord(pipe=1, data=86, model=1): 429, ProcessCoord(pipe=1, data=87, model=0): 430, ProcessCoord(pipe=1, data=87, model=1): 431, ProcessCoord(pipe=1, data=88, model=0): 432, ProcessCoord(pipe=1, data=88, model=1): 433, Pro + 0: cessCoord(pipe=1, data=89, model=0): 434, ProcessCoord(pipe=1, data=89, model=1): 435, ProcessCoord(pipe=1, data=90, model=0): 436, ProcessCoord(pipe=1, data=90, model=1): 437, ProcessCoord(pipe=1, data=91, model=0): 438, ProcessCoord(pipe=1, data=91, model=1): 439, ProcessCoord(pipe=1, data=92, model=0): 440, ProcessCoord(pipe=1, data=92, model=1): 441, ProcessCoord(pipe=1, data=93, model=0): 442, ProcessCoord(pipe=1, data=93, model=1): 443, ProcessCoord(pipe=1, data=94, model=0): 444, ProcessCoord(pipe=1, data=94, model=1): 445, ProcessCoord(pipe=1, data=95, model=0): 446, ProcessCoord(pipe=1, data=95, model=1): 447, ProcessCoord(pipe=1, data=96, model=0): 448, ProcessCoord(pipe=1, data=96, model=1): 449, ProcessCoord(pipe=1, data=97, model=0): 450, ProcessCoord(pipe=1, data=97, model=1): 451, ProcessCoord(pipe=1, data=98, model=0): 452, ProcessCoord(pipe=1, data=98, model=1): 453, ProcessCoord(pipe=1, data=99, model=0): 454, ProcessCoord(pipe=1, data=99, model=1): 455, ProcessCoord(pipe=1, data=100, model= + 0: 0): 456, ProcessCoord(pipe=1, data=100, model=1): 457, ProcessCoord(pipe=1, data=101, model=0): 458, ProcessCoord(pipe=1, data=101, model=1): 459, ProcessCoord(pipe=1, data=102, model=0): 460, ProcessCoord(pipe=1, data=102, model=1): 461, ProcessCoord(pipe=1, data=103, model=0): 462, ProcessCoord(pipe=1, data=103, model=1): 463, ProcessCoord(pipe=1, data=104, model=0): 464, ProcessCoord(pipe=1, data=104, model=1): 465, ProcessCoord(pipe=1, data=105, model=0): 466, ProcessCoord(pipe=1, data=105, model=1): 467, ProcessCoord(pipe=1, data=106, model=0): 468, ProcessCoord(pipe=1, data=106, model=1): 469, ProcessCoord(pipe=1, data=107, model=0): 470, ProcessCoord(pipe=1, data=107, model=1): 471, ProcessCoord(pipe=1, data=108, model=0): 472, ProcessCoord(pipe=1, data=108, model=1): 473, ProcessCoord(pipe=1, data=109, model=0): 474, ProcessCoord(pipe=1, data=109, model=1): 475, ProcessCoord(pipe=1, data=110, model=0): 476, ProcessCoord(pipe=1, data=110, model=1): 477, ProcessCoord(pipe=1, data=111, model=0): 478, Pro + 0: cessCoord(pipe=1, data=111, model=1): 479, ProcessCoord(pipe=1, data=112, model=0): 480, ProcessCoord(pipe=1, data=112, model=1): 481, ProcessCoord(pipe=1, data=113, model=0): 482, ProcessCoord(pipe=1, data=113, model=1): 483, ProcessCoord(pipe=1, data=114, model=0): 484, ProcessCoord(pipe=1, data=114, model=1): 485, ProcessCoord(pipe=1, data=115, model=0): 486, ProcessCoord(pipe=1, data=115, model=1): 487, ProcessCoord(pipe=1, data=116, model=0): 488, ProcessCoord(pipe=1, data=116, model=1): 489, ProcessCoord(pipe=1, data=117, model=0): 490, ProcessCoord(pipe=1, data=117, model=1): 491, ProcessCoord(pipe=1, data=118, model=0): 492, ProcessCoord(pipe=1, data=118, model=1): 493, ProcessCoord(pipe=1, data=119, model=0): 494, ProcessCoord(pipe=1, data=119, model=1): 495, ProcessCoord(pipe=1, data=120, model=0): 496, ProcessCoord(pipe=1, data=120, model=1): 497, ProcessCoord(pipe=1, data=121, model=0): 498, ProcessCoord(pipe=1, data=121, model=1): 499, ProcessCoord(pipe=1, data=122, model=0): 500, ProcessCoord(pi + 0: pe=1, data=122, model=1): 501, ProcessCoord(pipe=1, data=123, model=0): 502, ProcessCoord(pipe=1, data=123, model=1): 503, ProcessCoord(pipe=1, data=124, model=0): 504, ProcessCoord(pipe=1, data=124, model=1): 505, ProcessCoord(pipe=1, data=125, model=0): 506, ProcessCoord(pipe=1, data=125, model=1): 507, ProcessCoord(pipe=1, data=126, model=0): 508, ProcessCoord(pipe=1, data=126, model=1): 509, ProcessCoord(pipe=1, data=127, model=0): 510, ProcessCoord(pipe=1, data=127, model=1): 511} + 0: [2023-04-29 11:37:11,805] [INFO] [module.py:366:_partition_layers] Partitioning pipeline stages with method type:transformer + 0: stage=0 layers=24 + 0: 0: _to_float16 + 0: 1: EmbeddingPipe + 0: 2: + 0: 3: ParallelTransformerLayerPipe + 0: 4: ParallelTransformerLayerPipe + 0: 5: ParallelTransformerLayerPipe + 0: 6: ParallelTransformerLayerPipe + 0: 7: ParallelTransformerLayerPipe + 0: 8: ParallelTransformerLayerPipe + 0: 9: ParallelTransformerLayerPipe + 0: 10: ParallelTransformerLayerPipe + 0: 11: ParallelTransformerLayerPipe + 0: 12: ParallelTransformerLayerPipe + 0: 13: ParallelTransformerLayerPipe + 0: 14: ParallelTransformerLayerPipe + 0: 15: ParallelTransformerLayerPipe + 0: 16: ParallelTransformerLayerPipe + 0: 17: ParallelTransformerLayerPipe + 0: 18: ParallelTransformerLayerPipe + 0: 19: ParallelTransformerLayerPipe + 0: 20: ParallelTransformerLayerPipe + 0: 21: ParallelTransformerLayerPipe + 0: 22: ParallelTransformerLayerPipe + 0: 23: ParallelTransformerLayerPipe + 0: stage=1 layers=25 + 0: 24: ParallelTransformerLayerPipe + 0: 25: ParallelTransformerLayerPipe + 0: 26: ParallelTransformerLayerPipe + 0: 27: ParallelTransformerLayerPipe + 0: 28: ParallelTransformerLayerPipe + 0: 29: ParallelTransformerLayerPipe + 0: 30: ParallelTransformerLayerPipe + 0: 31: ParallelTransformerLayerPipe + 0: 32: ParallelTransformerLayerPipe + 0: 33: ParallelTransformerLayerPipe + 0: 34: ParallelTransformerLayerPipe + 0: 35: ParallelTransformerLayerPipe + 0: 36: ParallelTransformerLayerPipe + 0: 37: ParallelTransformerLayerPipe + 0: 38: ParallelTransformerLayerPipe + 0: 39: ParallelTransformerLayerPipe + 0: 40: ParallelTransformerLayerPipe + 0: 41: ParallelTransformerLayerPipe + 0: 42: ParallelTransformerLayerPipe + 0: 43: ParallelTransformerLayerPipe + 0: 44: ParallelTransformerLayerPipe + 0: 45: undo + 0: 46: MixedFusedLayerNorm + 0: 47: EmbeddingPipe + 0: 48: float16_to_fp32 + 0: loss: CrossEntropy + 0: [2023-04-29 11:37:15,544] [INFO] [utils.py:827:see_memory_usage] After Building Model + 0: [2023-04-29 11:37:15,545] [INFO] [utils.py:828:see_memory_usage] MA 4.16 GB Max_MA 4.16 GB CA 4.17 GB Max_CA 4 GB + 0: [2023-04-29 11:37:15,545] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 39.39 GB, percent = 7.8% + 0: setting training iterations to 0 + 0: > learning rate decay style: cosine + 0: DeepSpeed is enabled. + 0: [2023-04-29 11:37:15,547] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed info: version=0.7.5, git-hash=unknown, git-branch=unknown + 0: [2023-04-29 11:37:19,481] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Flops Profiler Enabled: False + 0: [2023-04-29 11:37:19,482] [INFO] [logging.py:68:log_dist] [Rank 0] Removing param_group that has no 'params' in the client Optimizer + 0: [2023-04-29 11:37:19,482] [INFO] [logging.py:68:log_dist] [Rank 0] Using client Optimizer as basic optimizer + 0: [2023-04-29 11:37:19,490] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Basic Optimizer = FusedAdam + 0: [2023-04-29 11:37:19,490] [INFO] [logging.py:68:log_dist] [Rank 0] Creating BF16 optimizer + 0: [2023-04-29 11:37:19,621] [INFO] [utils.py:827:see_memory_usage] begin bf16_optimizer + 0: [2023-04-29 11:37:19,621] [INFO] [utils.py:828:see_memory_usage] MA 4.15 GB Max_MA 4.18 GB CA 4.18 GB Max_CA 4 GB + 0: [2023-04-29 11:37:19,621] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 39.97 GB, percent = 7.9% + 0: ninja: no work to do. +12: Time to load utils op: 0.2922217845916748 seconds +12: Time to load utils op: 0.29224467277526855 seconds +12: Time to load utils op: 0.29225611686706543 seconds +12: Time to load utils op: 0.29227161407470703 seconds +16: Time to load utils op: 0.29840517044067383 seconds +16: Time to load utils op: 0.29841065406799316 secondsTime to load utils op: 0.2984120845794678 seconds +16: +16: Time to load utils op: 0.2984168529510498 seconds + 7: Time to load utils op: 0.3065919876098633 seconds + 7: Time to load utils op: 0.306713342666626 secondsTime to load utils op: 0.3069620132446289 seconds + 7: + 7: Time to load utils op: 0.30657958984375 seconds + 3: Time to load utils op: 0.30606651306152344 seconds + 3: Time to load utils op: 0.30606675148010254 seconds + 3: Time to load utils op: 0.3060777187347412 seconds + 3: Time to load utils op: 0.30606698989868164 seconds +15: Time to load utils op: 0.3001739978790283 secondsTime to load utils op: 0.3001875877380371 secondsTime to load utils op: 0.3001892566680908 secondsTime to load utils op: 0.3001856803894043 seconds +15: +15: +15: + 6: Time to load utils op: 0.3052363395690918 secondsTime to load utils op: 0.3052394390106201 seconds + 6: + 6: Time to load utils op: 0.30526304244995117 seconds +18: Time to load utils op: 0.29953718185424805 secondsTime to load utils op: 0.2995426654815674 seconds +18: + 6: Time to load utils op: 0.3052659034729004 seconds +18: Time to load utils op: 0.2995591163635254 seconds +18: Time to load utils op: 0.29956936836242676 seconds + 1: Time to load utils op: 0.3072793483734131 secondsTime to load utils op: 0.3072810173034668 seconds + 1: + 1: Time to load utils op: 0.3072819709777832 seconds + 1: Time to load utils op: 0.3073005676269531 seconds + 0: Time to load utils op: 0.3123962879180908 seconds + 0: Time to load utils op: 0.31354737281799316 seconds + 9: Time to load utils op: 0.30365824699401855 secondsTime to load utils op: 0.30365538597106934 seconds + 9: + 9: Time to load utils op: 0.30367493629455566 seconds + 0: Time to load utils op: 0.31305837631225586 seconds + 9: Time to load utils op: 0.3036794662475586 seconds +11: Time to load utils op: 0.3028411865234375 seconds +11: Time to load utils op: 0.3028426170349121 secondsTime to load utils op: 0.3028545379638672 seconds +11: + 2: Time to load utils op: 0.30753636360168457 secondsTime to load utils op: 0.3075430393218994 secondsTime to load utils op: 0.3075542449951172 seconds + 2: + 2: +11: Time to load utils op: 0.3028719425201416 seconds +20: Time to load utils op: 0.29867982864379883 secondsTime to load utils op: 0.29868531227111816 secondsTime to load utils op: 0.29869985580444336 seconds +20: +20: + 8: Time to load utils op: 0.30521202087402344 secondsTime to load utils op: 0.30523681640625 seconds + 8: + 8: Time to load utils op: 0.30524468421936035 seconds + 8: Time to load utils op: 0.3052561283111572 seconds + 2: Time to load utils op: 0.3075742721557617 seconds +28: Time to load utils op: 0.29231953620910645 seconds +28: Time to load utils op: 0.29232120513916016 seconds +28: Time to load utils op: 0.2923402786254883 secondsTime to load utils op: 0.2923402786254883 seconds +28: +20: Time to load utils op: 0.2987210750579834 seconds +21: Time to load utils op: 0.2976799011230469 seconds +21: Time to load utils op: 0.2976861000061035 seconds +21: Time to load utils op: 0.29769062995910645 seconds +10: Time to load utils op: 0.3039429187774658 secondsTime to load utils op: 0.3039510250091553 secondsTime to load utils op: 0.30394458770751953 seconds +10: +10: +10: Time to load utils op: 0.30397558212280273 seconds +23: Time to load utils op: 0.29700708389282227 seconds +23: Time to load utils op: 0.29701924324035645 seconds +21: Time to load utils op: 0.2977008819580078 seconds +25: Time to load utils op: 0.3011660575866699 secondsTime to load utils op: 0.30019354820251465 seconds +25: +25: Time to load utils op: 0.2998371124267578 seconds +23: Time to load utils op: 0.29699015617370605 seconds +23: Time to load utils op: 0.2970395088195801 seconds +25: Time to load utils op: 0.29961514472961426 seconds +22: Time to load utils op: 0.2978694438934326 seconds +22: Time to load utils op: 0.2978808879852295 secondsTime to load utils op: 0.29787135124206543 seconds +22: +22: Time to load utils op: 0.29788947105407715 seconds +17: Time to load utils op: 0.3003532886505127 secondsTime to load utils op: 0.30036139488220215 seconds +17: +17: Time to load utils op: 0.30036163330078125 seconds +31: Time to load utils op: 0.2932400703430176 secondsTime to load utils op: 0.2932474613189697 seconds +31: +31: Time to load utils op: 0.29325199127197266 seconds +17: Time to load utils op: 0.30039048194885254 seconds +30: Time to load utils op: 0.29344725608825684 seconds +30: Time to load utils op: 0.2934553623199463 secondsTime to load utils op: 0.29345703125 seconds +30: +31: Time to load utils op: 0.29326438903808594 seconds +24: Time to load utils op: 0.29694652557373047 seconds +24: Time to load utils op: 0.2969663143157959 seconds +24: Time to load utils op: 0.29695868492126465 secondsTime to load utils op: 0.29697751998901367 seconds +30: Time to load utils op: 0.29344844818115234 seconds +24: + 5: Time to load utils op: 0.30764007568359375 seconds + 5: Time to load utils op: 0.30763697624206543 seconds + 5: Time to load utils op: 0.30765438079833984 seconds + 5: Time to load utils op: 0.30762696266174316 seconds +29: Time to load utils op: 0.2949516773223877 secondsTime to load utils op: 0.2949516773223877 seconds +29: +29: Time to load utils op: 0.2949645519256592 seconds +13: Time to load utils op: 0.3030221462249756 secondsTime to load utils op: 0.30310988426208496 seconds +13: +13: Time to load utils op: 0.303114652633667 seconds +13: Time to load utils op: 0.3031294345855713 seconds +27: Time to load utils op: 0.295443058013916 seconds +27: Time to load utils op: 0.29546642303466797 secondsTime to load utils op: 0.29546332359313965 seconds +27: +29: Time to load utils op: 0.29497742652893066 seconds +27: Time to load utils op: 0.29547786712646484 seconds +26: Time to load utils op: 0.295849084854126 seconds +19: Time to load utils op: 0.2998204231262207 secondsTime to load utils op: 0.2998340129852295 seconds +19: +19: Time to load utils op: 0.29984545707702637 seconds +19: Time to load utils op: 0.29987406730651855 seconds +26: Time to load utils op: 0.2958641052246094 seconds +26: Time to load utils op: 0.2958698272705078 seconds + 4: Time to load utils op: 0.30847859382629395 secondsTime to load utils op: 0.308485746383667 secondsTime to load utils op: 0.3084883689880371 seconds + 4: + 4: + 4: Time to load utils op: 0.30849218368530273 seconds +14: Time to load utils op: 0.302060604095459 secondsTime to load utils op: 0.3020598888397217 seconds +14: +14: Time to load utils op: 0.30208539962768555 seconds +26: Time to load utils op: 0.29587864875793457 seconds +14: Time to load utils op: 0.3020946979522705 seconds +32: ninja: no work to do. +32: Time to load utils op: 0.17025184631347656 seconds + 7: Time to load utils op: 0.0005853176116943359 seconds + 7: Time to load utils op: 0.0005507469177246094 seconds + 7: Time to load utils op: 0.0006387233734130859 seconds + 7: Time to load utils op: 0.0006747245788574219 seconds + 0: Time to load utils op: 0.0005164146423339844 seconds + 0: Time to load utils op: 0.0005676746368408203 seconds + 0: Time to load utils op: 0.0005061626434326172 seconds + 6: Time to load utils op: 0.0004863739013671875 seconds + 6: Time to load utils op: 0.0004863739013671875 seconds + 6: Time to load utils op: 0.0005092620849609375 secondsTime to load utils op: 0.0005152225494384766 seconds + 6: + 0: Time to load utils op: 0.10146880149841309 seconds + 0: Time to load utils op: 0.10188841819763184 seconds + 0: Time to load utils op: 0.10170912742614746 seconds +11: Time to load utils op: 0.0004923343658447266 seconds +11: Time to load utils op: 0.0004918575286865234 seconds +11: Time to load utils op: 0.0005338191986083984 seconds +11: Time to load utils op: 0.0005230903625488281 seconds + 1: Time to load utils op: 0.10265016555786133 seconds + 1: Time to load utils op: 0.10273265838623047 seconds + 1: Time to load utils op: 0.10289788246154785 secondsTime to load utils op: 0.10277414321899414 seconds + 1: + 3: Time to load utils op: 0.10244202613830566 seconds + 3: Time to load utils op: 0.10228109359741211 seconds + 3: Time to load utils op: 0.10227131843566895 seconds + 3: Time to load utils op: 0.10290050506591797 seconds + 2: Time to load utils op: 0.10372352600097656 seconds + 4: Time to load utils op: 0.1029510498046875 seconds + 4: Time to load utils op: 0.10266900062561035 seconds + 4: Time to load utils op: 0.10306739807128906 seconds + 2: Time to load utils op: 0.10375404357910156 seconds + 4: Time to load utils op: 0.10297966003417969 seconds + 2: Time to load utils op: 0.1038815975189209 seconds + 2: Time to load utils op: 0.10403251647949219 seconds + 5: Time to load utils op: 0.10267305374145508 seconds + 5: Time to load utils op: 0.10241103172302246 secondsTime to load utils op: 0.1024160385131836 seconds + 5: +20: Time to load utils op: 0.0010023117065429688 seconds +20: Time to load utils op: 0.00095367431640625 secondsTime to load utils op: 0.0009381771087646484 seconds +20: + 5: Time to load utils op: 0.10241150856018066 seconds +20: Time to load utils op: 0.0010335445404052734 seconds + 7: Time to load utils op: 0.10290384292602539 secondsTime to load utils op: 0.10236811637878418 seconds + 7: + 7: Time to load utils op: 0.1031641960144043 seconds + 7: Time to load utils op: 0.10234785079956055 seconds +22: Time to load utils op: 0.0005154609680175781 seconds +22: Time to load utils op: 0.0005254745483398438 seconds +22: Time to load utils op: 0.0005564689636230469 secondsTime to load utils op: 0.0005369186401367188 seconds +22: + 6: Time to load utils op: 0.10286641120910645 seconds + 6: Time to load utils op: 0.10292601585388184 seconds + 6: Time to load utils op: 0.10307693481445312 seconds + 6: Time to load utils op: 0.1031036376953125 seconds + 3: Time to load utils op: 0.00048542022705078125 seconds + 3: Time to load utils op: 0.0004909038543701172 secondsTime to load utils op: 0.0004210472106933594 seconds + 3: + 9: Time to load utils op: 0.10228848457336426 seconds + 9: Time to load utils op: 0.10286808013916016 seconds + 9: Time to load utils op: 0.10284829139709473 seconds + 3: Time to load utils op: 0.0005223751068115234 seconds + 9: Time to load utils op: 0.10297918319702148 seconds +10: Time to load utils op: 0.10267257690429688 seconds +10: Time to load utils op: 0.1024322509765625 seconds + 8: Time to load utils op: 0.10338044166564941 seconds +11: Time to load utils op: 0.1021885871887207 seconds + 8: Time to load utils op: 0.10312080383300781 seconds +11: Time to load utils op: 0.10228252410888672 seconds +11: Time to load utils op: 0.1024467945098877 seconds +11: Time to load utils op: 0.10255122184753418 seconds +12: Time to load utils op: 0.0004730224609375 seconds +10: Time to load utils op: 0.10277080535888672 seconds + 8: Time to load utils op: 0.10356378555297852 seconds +12: Time to load utils op: 0.0003960132598876953 seconds +12: Time to load utils op: 0.0004951953887939453 seconds +10: Time to load utils op: 0.1033620834350586 seconds +12: Time to load utils op: 0.0005178451538085938 seconds + 8: Time to load utils op: 0.10379981994628906 seconds +13: Time to load utils op: 0.1026766300201416 seconds +13: Time to load utils op: 0.10276412963867188 seconds +13: Time to load utils op: 0.1028909683227539 seconds +13: Time to load utils op: 0.10307049751281738 seconds +15: Time to load utils op: 0.10304903984069824 seconds +16: Time to load utils op: 0.1027991771697998 seconds +16: Time to load utils op: 0.10263919830322266 seconds +14: Time to load utils op: 0.1024928092956543 seconds +15: Time to load utils op: 0.10325860977172852 seconds +15: Time to load utils op: 0.10317111015319824 seconds +16: Time to load utils op: 0.10288023948669434 seconds +15: Time to load utils op: 0.10330367088317871 seconds +16: Time to load utils op: 0.10308623313903809 seconds +14: Time to load utils op: 0.10285329818725586 seconds +14: Time to load utils op: 0.1030278205871582 seconds +14: Time to load utils op: 0.10318708419799805 seconds +18: Time to load utils op: 0.103057861328125 seconds +17: Time to load utils op: 0.10247969627380371 seconds +18: Time to load utils op: 0.10299873352050781 secondsTime to load utils op: 0.10332489013671875 secondsTime to load utils op: 0.10321211814880371 seconds +18: +18: +19: Time to load utils op: 0.1026463508605957 seconds +19: Time to load utils op: 0.10307717323303223 seconds +12: Time to load utils op: 0.10274791717529297 seconds +19: Time to load utils op: 0.10306000709533691 seconds +12: Time to load utils op: 0.10288333892822266 seconds +19: Time to load utils op: 0.10351848602294922 seconds +17: Time to load utils op: 0.10238838195800781 seconds +17: Time to load utils op: 0.10248780250549316 seconds +17: Time to load utils op: 0.10250520706176758 seconds +25: Time to load utils op: 0.10250329971313477 seconds +25: Time to load utils op: 0.10218548774719238 seconds +12: Time to load utils op: 0.10232710838317871 seconds +12: Time to load utils op: 0.1023094654083252 seconds +25: Time to load utils op: 0.10203981399536133 seconds +25: Time to load utils op: 0.10204601287841797 seconds +21: Time to load utils op: 0.10272884368896484 seconds +20: Time to load utils op: 0.1040797233581543 secondsTime to load utils op: 0.1040341854095459 seconds +20: +20: Time to load utils op: 0.10393428802490234 seconds +20: Time to load utils op: 0.1039280891418457 seconds +24: Time to load utils op: 0.1029660701751709 seconds +24: Time to load utils op: 0.10260462760925293 seconds +21: Time to load utils op: 0.1023714542388916 seconds +21: Time to load utils op: 0.10250663757324219 seconds +24: Time to load utils op: 0.10289835929870605 seconds +24: Time to load utils op: 0.10294461250305176 seconds +21: Time to load utils op: 0.10263752937316895 seconds +23: Time to load utils op: 0.10391497611999512 seconds +26: Time to load utils op: 0.10233545303344727 seconds +23: Time to load utils op: 0.10384535789489746 seconds +26: Time to load utils op: 0.10236787796020508 seconds +22: Time to load utils op: 0.1042795181274414 seconds +22: Time to load utils op: 0.1045534610748291 secondsTime to load utils op: 0.10452866554260254 seconds +22: +23: Time to load utils op: 0.10441970825195312 seconds +22: Time to load utils op: 0.10447573661804199 seconds +26: Time to load utils op: 0.10264444351196289 seconds +23: Time to load utils op: 0.10410690307617188 seconds +26: Time to load utils op: 0.1026926040649414 seconds +27: Time to load utils op: 0.10259604454040527 seconds +27: Time to load utils op: 0.1027822494506836 seconds +27: Time to load utils op: 0.10287141799926758 seconds +28: Time to load utils op: 0.10283255577087402 seconds +28: Time to load utils op: 0.10292267799377441 secondsTime to load utils op: 0.10264801979064941 seconds +28: +28: Time to load utils op: 0.1027066707611084 seconds +27: Time to load utils op: 0.10293412208557129 seconds +25: Time to load utils op: 0.0005228519439697266 seconds +25: Time to load utils op: 0.0005216598510742188 seconds +25: Time to load utils op: 0.0005650520324707031 secondsTime to load utils op: 0.0006313323974609375 seconds +25: +29: Time to load utils op: 0.10257244110107422 seconds +31: Time to load utils op: 0.10227227210998535 secondsTime to load utils op: 0.10239195823669434 seconds +31: +29: Time to load utils op: 0.10273909568786621 seconds +30: Time to load utils op: 0.10202527046203613 secondsTime to load utils op: 0.10234284400939941 seconds +30: +31: Time to load utils op: 0.1023101806640625 seconds +31: Time to load utils op: 0.10244965553283691 seconds +30: Time to load utils op: 0.10212373733520508 seconds +29: Time to load utils op: 0.10312557220458984 seconds +29: Time to load utils op: 0.10354804992675781 seconds +30: Time to load utils op: 0.1024928092956543 seconds + 0: Time to load utils op: 0.0003991127014160156 seconds + 0: Time to load utils op: 0.0003917217254638672 seconds +24: Time to load utils op: 0.0005314350128173828 secondsTime to load utils op: 0.0005373954772949219 seconds +24: +24: Time to load utils op: 0.0004553794860839844 seconds +24: Time to load utils op: 0.0005037784576416016 seconds + 0: Time to load utils op: 0.0004184246063232422 seconds +18: Time to load utils op: 0.0009098052978515625 seconds +18: Time to load utils op: 0.0009543895721435547 seconds +18: Time to load utils op: 0.0008866786956787109 seconds +18: Time to load utils op: 0.0009455680847167969 seconds +14: Time to load utils op: 0.0005068778991699219 seconds +14: Time to load utils op: 0.0005321502685546875 seconds +14: Time to load utils op: 0.0004792213439941406 seconds +21: Time to load utils op: 0.0004887580871582031 seconds +14: Time to load utils op: 0.0005347728729248047 seconds +26: Time to load utils op: 0.0004966259002685547 seconds +21: Time to load utils op: 0.0003867149353027344 secondsTime to load utils op: 0.00038886070251464844 secondsTime to load utils op: 0.00040912628173828125 seconds +21: +21: +26: Time to load utils op: 0.0005049705505371094 seconds +26: Time to load utils op: 0.0004992485046386719 seconds +26: Time to load utils op: 0.0005528926849365234 seconds + 1: Time to load utils op: 0.0004818439483642578 seconds + 9: Time to load utils op: 0.0004875659942626953 seconds + 1: Time to load utils op: 0.0004990100860595703 secondsTime to load utils op: 0.0004296302795410156 seconds + 1: + 3: Time to load utils op: 0.0004115104675292969 seconds + 3: Time to load utils op: 0.00039076805114746094 secondsTime to load utils op: 0.00041675567626953125 seconds + 3: + 9: Time to load utils op: 0.0005629062652587891 seconds + 9: Time to load utils op: 0.0006148815155029297 seconds + 1: Time to load utils op: 0.0005135536193847656 secondsTime to load utils op: 0.0004215240478515625 seconds + 1: + 9: Time to load utils op: 0.0006420612335205078 seconds + 1: Time to load utils op: 0.0005204677581787109 seconds + 1: Time to load utils op: 0.0005457401275634766 seconds + 1: Time to load utils op: 0.0005505084991455078 seconds +28: Time to load utils op: 0.0008678436279296875 seconds +23: Time to load utils op: 0.0004935264587402344 seconds +28: Time to load utils op: 0.0009233951568603516 secondsTime to load utils op: 0.0009658336639404297 seconds +28: +23: Time to load utils op: 0.0005548000335693359 secondsTime to load utils op: 0.0005314350128173828 seconds +23: Time to load utils op: 0.000530242919921875 seconds +23: +28: Time to load utils op: 0.0009770393371582031 seconds + 3: Time to load utils op: 0.00037169456481933594 seconds + 6: Time to load utils op: 0.0003514289855957031 seconds +10: Time to load utils op: 0.0005135536193847656 seconds +10: Time to load utils op: 0.0005297660827636719 seconds +10: Time to load utils op: 0.0004253387451171875 seconds +10: Time to load utils op: 0.0005128383636474609 seconds + 6: Time to load utils op: 0.00045013427734375 seconds + 6: Time to load utils op: 0.0004048347473144531 seconds + 6: Time to load utils op: 0.00043201446533203125 seconds + 7: Time to load utils op: 0.00039696693420410156 seconds + 7: Time to load utils op: 0.0003941059112548828 seconds +11: Time to load utils op: 0.0004367828369140625 seconds + 9: Time to load utils op: 0.00038433074951171875 seconds +11: Time to load utils op: 0.0004405975341796875 seconds + 9: Time to load utils op: 0.0003883838653564453 seconds + 9: Time to load utils op: 0.0004088878631591797 seconds +10: Time to load utils op: 0.000331878662109375 seconds +11: Time to load utils op: 0.00037860870361328125 seconds + 7: Time to load utils op: 0.00039839744567871094 seconds +10: Time to load utils op: 0.0003573894500732422 seconds +11: Time to load utils op: 0.00037026405334472656 seconds +17: Time to load utils op: 0.0005486011505126953 seconds +17: Time to load utils op: 0.0005288124084472656 seconds + 9: Time to load utils op: 0.0003998279571533203 seconds +17: Time to load utils op: 0.0005352497100830078 seconds +17: Time to load utils op: 0.0006239414215087891 seconds +10: Time to load utils op: 0.0003714561462402344 seconds +10: Time to load utils op: 0.0003516674041748047 seconds + 7: Time to load utils op: 0.0004203319549560547 seconds +31: Time to load utils op: 0.0005159378051757812 secondsTime to load utils op: 0.00040912628173828125 seconds +31: +31: Time to load utils op: 0.0003910064697265625 seconds +31: Time to load utils op: 0.0004329681396484375 seconds +19: Time to load utils op: 0.0009238719940185547 seconds +19: Time to load utils op: 0.0010101795196533203 seconds +19: Time to load utils op: 0.000972747802734375 seconds +19: Time to load utils op: 0.0010440349578857422 seconds + 8: Time to load utils op: 0.0007891654968261719 seconds + 8: Time to load utils op: 0.0010504722595214844 seconds + 8: Time to load utils op: 0.001298666000366211 seconds + 8: Time to load utils op: 0.0013916492462158203 seconds + 8: Time to load utils op: 0.0013730525970458984 seconds + 8: Time to load utils op: 0.0014286041259765625 seconds + 8: Time to load utils op: 0.001394510269165039 seconds +27: Time to load utils op: 0.0004911422729492188 seconds + 8: Time to load utils op: 0.0014562606811523438 seconds +27: Time to load utils op: 0.0005578994750976562 seconds +27: Time to load utils op: 0.0005714893341064453 secondsTime to load utils op: 0.0005159378051757812 seconds +27: + 5: Time to load utils op: 0.0005040168762207031 seconds + 5: Time to load utils op: 0.0004265308380126953 secondsTime to load utils op: 0.0004367828369140625 seconds + 5: + 5: Time to load utils op: 0.0004696846008300781 seconds + 5: Time to load utils op: 0.00041365623474121094 seconds + 5: Time to load utils op: 0.0004949569702148438 seconds + 5: Time to load utils op: 0.00044465065002441406 secondsTime to load utils op: 0.0004436969757080078 seconds + 5: +16: Time to load utils op: 0.0008363723754882812 secondsTime to load utils op: 0.0007634162902832031 seconds +16: +16: Time to load utils op: 0.0007596015930175781 seconds +29: Time to load utils op: 0.0006496906280517578 seconds +16: Time to load utils op: 0.0008180141448974609 seconds +16: Time to load utils op: 0.00037169456481933594 seconds +16: Time to load utils op: 0.0003387928009033203 seconds + 4: Time to load utils op: 0.0008242130279541016 seconds +29: Time to load utils op: 0.0009071826934814453 seconds +29: Time to load utils op: 0.0008759498596191406 seconds + 2: Time to load utils op: 0.0005323886871337891 seconds + 2: Time to load utils op: 0.0005147457122802734 seconds + 4: Time to load utils op: 0.0011374950408935547 seconds +29: Time to load utils op: 0.0009610652923583984 seconds +16: Time to load utils op: 0.0003712177276611328 seconds + 2: Time to load utils op: 0.0005741119384765625 seconds +15: Time to load utils op: 0.0005371570587158203 seconds +15: Time to load utils op: 0.0005068778991699219 seconds + 4: Time to load utils op: 0.0013039112091064453 secondsTime to load utils op: 0.0012328624725341797 seconds + 4: +16: Time to load utils op: 0.00033211708068847656 seconds +13: Time to load utils op: 0.0004878044128417969 seconds +15: Time to load utils op: 0.0004425048828125 seconds +15: Time to load utils op: 0.00044536590576171875 seconds + 2: Time to load utils op: 0.0005700588226318359 seconds + 4: Time to load utils op: 0.0012331008911132812 seconds + 2: Time to load utils op: 0.0005407333374023438 seconds + 2: Time to load utils op: 0.0006206035614013672 seconds + 4: Time to load utils op: 0.0012445449829101562 secondsTime to load utils op: 0.001262664794921875 seconds + 4: +13: Time to load utils op: 0.00043082237243652344 secondsTime to load utils op: 0.0004215240478515625 secondsTime to load utils op: 0.0005202293395996094 secondsTime to load utils op: 0.0005297660827636719 seconds +13: +13: + 2: Time to load utils op: 0.0005645751953125 seconds +15: Time to load utils op: 0.0005886554718017578 seconds +13: + 4: Time to load utils op: 0.0012922286987304688 seconds +15: Time to load utils op: 0.00057220458984375 seconds +15: Time to load utils op: 0.0006198883056640625 seconds +13: Time to load utils op: 0.0005936622619628906 secondsTime to load utils op: 0.0005965232849121094 seconds +13: +13: Time to load utils op: 0.0005898475646972656 seconds + 2: Time to load utils op: 0.0006361007690429688 seconds +18: Time to load utils op: 0.00036716461181640625 seconds +15: Time to load utils op: 0.0003829002380371094 seconds +14: Time to load utils op: 0.0003986358642578125 seconds +14: Time to load utils op: 0.00037026405334472656 seconds +17: Time to load utils op: 0.00034046173095703125 seconds +19: Time to load utils op: 0.0003376007080078125 seconds +14: Time to load utils op: 0.00039696693420410156 seconds +14: Time to load utils op: 0.0004143714904785156 seconds +19: Time to load utils op: 0.0003693103790283203 seconds +19: Time to load utils op: 0.000370025634765625 seconds +17: Time to load utils op: 0.00035452842712402344 seconds +19: Time to load utils op: 0.0003783702850341797 seconds +25: Time to load utils op: 0.00033855438232421875 seconds +18: Time to load utils op: 0.00038814544677734375 seconds +25: Time to load utils op: 0.0003795623779296875 seconds +18: Time to load utils op: 0.00037097930908203125 seconds +18: Time to load utils op: 0.0003631114959716797 seconds +25: Time to load utils op: 0.000354766845703125 seconds +12: Time to load utils op: 0.0003943443298339844 seconds +17: Time to load utils op: 0.0003757476806640625 seconds +21: Time to load utils op: 0.0003745555877685547 seconds +20: Time to load utils op: 0.00037598609924316406 seconds +21: Time to load utils op: 0.00037670135498046875 seconds +12: Time to load utils op: 0.00040650367736816406 seconds +20: Time to load utils op: 0.0003979206085205078 seconds +24: Time to load utils op: 0.0003666877746582031 seconds +12: Time to load utils op: 0.00040221214294433594 seconds +17: Time to load utils op: 0.0003657341003417969 seconds +20: Time to load utils op: 0.0003757476806640625 seconds +12: Time to load utils op: 0.00037932395935058594 seconds +21: Time to load utils op: 0.0003495216369628906 seconds +26: Time to load utils op: 0.0003440380096435547 seconds +23: Time to load utils op: 0.0003445148468017578 seconds +24: Time to load utils op: 0.0004000663757324219 seconds +25: Time to load utils op: 0.00035262107849121094 seconds +20: Time to load utils op: 0.00034308433532714844 seconds +24: Time to load utils op: 0.0003752708435058594 seconds +23: Time to load utils op: 0.0003871917724609375 secondsTime to load utils op: 0.0003771781921386719 seconds +23: +24: Time to load utils op: 0.00038313865661621094 seconds +23: Time to load utils op: 0.0003769397735595703 seconds +26: Time to load utils op: 0.00037860870361328125 seconds +26: Time to load utils op: 0.00039958953857421875 secondsTime to load utils op: 0.0004029273986816406 seconds +26: +21: Time to load utils op: 0.0003733634948730469 seconds +28: Time to load utils op: 0.0003705024719238281 seconds +28: Time to load utils op: 0.0004169940948486328 seconds +28: Time to load utils op: 0.0003783702850341797 seconds +27: Time to load utils op: 0.000370025634765625 seconds +28: Time to load utils op: 0.0003676414489746094 seconds +22: Time to load utils op: 0.0003902912139892578 seconds +27: Time to load utils op: 0.0003936290740966797 seconds +22: Time to load utils op: 0.0003676414489746094 seconds +27: Time to load utils op: 0.0003829002380371094 seconds +27: Time to load utils op: 0.00035953521728515625 seconds +22: Time to load utils op: 0.00042366981506347656 seconds +22: Time to load utils op: 0.00037860870361328125 seconds +31: Time to load utils op: 0.00037932395935058594 seconds +29: Time to load utils op: 0.0003769397735595703 seconds +31: Time to load utils op: 0.0003952980041503906 seconds +31: Time to load utils op: 0.000392913818359375 seconds +31: Time to load utils op: 0.00040531158447265625 seconds +29: Time to load utils op: 0.0003273487091064453 seconds +29: Time to load utils op: 0.0003571510314941406 seconds +29: Time to load utils op: 0.00037670135498046875 seconds +32: Time to load utils op: 0.20225238800048828 secondsTime to load utils op: 0.2027273178100586 seconds +32: +32: Time to load utils op: 0.20308732986450195 seconds +32: Time to load utils op: 0.0005857944488525391 seconds +30: Time to load utils op: 0.0005218982696533203 seconds +30: Time to load utils op: 0.0005633831024169922 seconds +30: Time to load utils op: 0.0005199909210205078 seconds +30: Time to load utils op: 0.0005459785461425781 seconds +30: Time to load utils op: 0.0005781650543212891 secondsTime to load utils op: 0.0005476474761962891 seconds +30: +30: Time to load utils op: 0.0006372928619384766 seconds +30: Time to load utils op: 0.0006420612335205078 seconds +35: Time to load utils op: 0.21075654029846191 seconds +35: Time to load utils op: 0.21085262298583984 secondsTime to load utils op: 0.20985889434814453 seconds +35: +35: Time to load utils op: 0.2101433277130127 seconds +33: Time to load utils op: 0.21150684356689453 secondsTime to load utils op: 0.21107697486877441 seconds +33: Time to load utils op: 0.21125411987304688 seconds +33: +33: Time to load utils op: 0.21186590194702148 seconds +34: Time to load utils op: 0.21120858192443848 secondsTime to load utils op: 0.21135497093200684 seconds +34: +34: Time to load utils op: 0.2103111743927002 secondsTime to load utils op: 0.2115323543548584 seconds +34: +36: Time to load utils op: 0.21038818359375 seconds +36: Time to load utils op: 0.210282564163208 seconds +36: Time to load utils op: 0.21051597595214844 seconds +36: Time to load utils op: 0.21051597595214844 seconds +41: Time to load utils op: 0.2098236083984375 secondsTime to load utils op: 0.2098231315612793 secondsTime to load utils op: 0.20914483070373535 seconds +41: +41: +41: Time to load utils op: 0.20886778831481934 seconds +40: Time to load utils op: 0.20974445343017578 secondsTime to load utils op: 0.20981717109680176 seconds +40: Time to load utils op: 0.20969724655151367 secondsTime to load utils op: 0.20968842506408691 seconds +40: +40: +37: Time to load utils op: 0.21050333976745605 secondsTime to load utils op: 0.2105114459991455 secondsTime to load utils op: 0.21050763130187988 seconds +37: Time to load utils op: 0.21051597595214844 seconds +37: +37: +46: Time to load utils op: 0.21002745628356934 secondsTime to load utils op: 0.2105121612548828 secondsTime to load utils op: 0.210615873336792 seconds +46: +46: +46: Time to load utils op: 0.21004343032836914 seconds +42: Time to load utils op: 0.2097330093383789 secondsTime to load utils op: 0.2097330093383789 seconds +42: +42: Time to load utils op: 0.20973706245422363 seconds +42: Time to load utils op: 0.20975184440612793 seconds +38: Time to load utils op: 0.2123119831085205 secondsTime to load utils op: 0.2123115062713623 secondsTime to load utils op: 0.2123091220855713 seconds +38: +38: +38: Time to load utils op: 0.2123243808746338 seconds +39: Time to load utils op: 0.21968770027160645 secondsTime to load utils op: 0.2196955680847168 seconds +39: +39: Time to load utils op: 0.219696044921875 seconds +39: Time to load utils op: 0.21970415115356445 seconds + 0: Time to load utils op: 0.20251083374023438 seconds +45: Time to load utils op: 0.21843552589416504 seconds +45: Time to load utils op: 0.21843791007995605 seconds +45: Time to load utils op: 0.2184462547302246 seconds +45: Time to load utils op: 0.21845555305480957 seconds +49: Time to load utils op: 0.22107601165771484 secondsTime to load utils op: 0.2207956314086914 secondsTime to load utils op: 0.22094345092773438 secondsTime to load utils op: 0.22010540962219238 seconds +49: +49: +49: +32: Time to load utils op: 0.0003669261932373047 seconds +54: Time to load utils op: 0.21873855590820312 secondsTime to load utils op: 0.21887898445129395 secondsTime to load utils op: 0.21951556205749512 seconds +54: +54: Time to load utils op: 0.21906113624572754 seconds +54: +48: Time to load utils op: 0.2185688018798828 secondsTime to load utils op: 0.21857690811157227 secondsTime to load utils op: 0.21857762336730957 secondsTime to load utils op: 0.2185816764831543 seconds +48: +48: +48: +47: Time to load utils op: 0.2223374843597412 secondsTime to load utils op: 0.2225499153137207 secondsTime to load utils op: 0.2225661277770996 secondsTime to load utils op: 0.22253203392028809 seconds +47: +47: +47: +56: Time to load utils op: 0.21811389923095703 secondsTime to load utils op: 0.21810650825500488 secondsTime to load utils op: 0.21748614311218262 secondsTime to load utils op: 0.21811270713806152 seconds +56: +56: +56: +51: Time to load utils op: 0.2172079086303711 secondsTime to load utils op: 0.2172071933746338 secondsTime to load utils op: 0.21719932556152344 seconds +51: +51: +51: Time to load utils op: 0.21720290184020996 seconds +57: Time to load utils op: 0.21362018585205078 secondsTime to load utils op: 0.2136213779449463 secondsTime to load utils op: 0.21359920501708984 seconds +57: +57: +57: Time to load utils op: 0.21362709999084473 seconds +55: Time to load utils op: 0.21879363059997559 secondsTime to load utils op: 0.2185840606689453 seconds +55: +55: Time to load utils op: 0.21892380714416504 secondsTime to load utils op: 0.21858882904052734 seconds +55: +58: Time to load utils op: 0.2133932113647461 secondsTime to load utils op: 0.21339821815490723 secondsTime to load utils op: 0.2133939266204834 secondsTime to load utils op: 0.21339678764343262 seconds +58: +58: +58: +52: Time to load utils op: 0.21706819534301758 secondsTime to load utils op: 0.21707510948181152 secondsTime to load utils op: 0.21707868576049805 seconds +52: Time to load utils op: 0.21708059310913086 seconds +52: +52: +43: Time to load utils op: 0.2137460708618164 secondsTime to load utils op: 0.2137584686279297 secondsTime to load utils op: 0.21374964714050293 secondsTime to load utils op: 0.21373987197875977 seconds +43: +43: +43: +53: Time to load utils op: 0.21668171882629395 secondsTime to load utils op: 0.21667695045471191 secondsTime to load utils op: 0.21667861938476562 seconds +53: +53: +50: Time to load utils op: 0.2192399501800537 secondsTime to load utils op: 0.22037982940673828 secondsTime to load utils op: 0.22008657455444336 seconds +50: +50: Time to load utils op: 0.21735095977783203 seconds +50: +59: Time to load utils op: 0.21448373794555664 secondsTime to load utils op: 0.2144920825958252 seconds +59: +59: Time to load utils op: 0.21448898315429688 seconds +59: Time to load utils op: 0.21450209617614746 seconds +61: Time to load utils op: 0.21389460563659668 secondsTime to load utils op: 0.2138996124267578 seconds +61: +61: Time to load utils op: 0.21391057968139648 secondsTime to load utils op: 0.21390223503112793 seconds +61: +63: Time to load utils op: 0.2130587100982666 secondsTime to load utils op: 0.21306419372558594 secondsTime to load utils op: 0.21306109428405762 seconds +63: +63: Time to load utils op: 0.21306681632995605 seconds +63: +60: Time to load utils op: 0.2092897891998291 secondsTime to load utils op: 0.2106788158416748 seconds +60: +60: Time to load utils op: 0.20879912376403809 seconds +60: Time to load utils op: 0.2047100067138672 seconds +44: Time to load utils op: 0.21340417861938477 secondsTime to load utils op: 0.2134096622467041 seconds +44: +44: Time to load utils op: 0.21255850791931152 secondsTime to load utils op: 0.21262240409851074 seconds +44: +53: Time to load utils op: 0.21672296524047852 seconds +32: Time to load utils op: 0.0004286766052246094 seconds +32: Time to load utils op: 0.0004436969757080078 seconds + 0: Time to load utils op: 0.4026970863342285 seconds +62: Time to load utils op: 0.21059942245483398 seconds +62: Time to load utils op: 0.20965790748596191 secondsTime to load utils op: 0.21060943603515625 seconds +62: +62: Time to load utils op: 0.2095954418182373 seconds +41: Time to load utils op: 0.0009784698486328125 seconds +41: Time to load utils op: 0.0009891986846923828 seconds +41: Time to load utils op: 0.0009515285491943359 seconds +41: Time to load utils op: 0.0010895729064941406 seconds +47: Time to load utils op: 0.0007996559143066406 secondsTime to load utils op: 0.0007119178771972656 secondsTime to load utils op: 0.0006875991821289062 seconds +47: +47: +47: Time to load utils op: 0.000827789306640625 seconds +46: Time to load utils op: 0.0009765625 seconds +46: Time to load utils op: 0.000988006591796875 seconds +46: Time to load utils op: 0.0009853839874267578 seconds +46: Time to load utils op: 0.0009555816650390625 seconds +33: Time to load utils op: 0.0009024143218994141 seconds +33: Time to load utils op: 0.0008392333984375 secondsTime to load utils op: 0.0007605552673339844 seconds +33: +33: Time to load utils op: 0.0009238719940185547 seconds +49: Time to load utils op: 0.0007467269897460938 seconds +54: Time to load utils op: 0.0007598400115966797 seconds +49: Time to load utils op: 0.0008492469787597656 secondsTime to load utils op: 0.0008745193481445312 seconds +49: +36: Time to load utils op: 0.0009739398956298828 secondsTime to load utils op: 0.0009748935699462891 seconds +36: Time to load utils op: 0.0009748935699462891 seconds +36: +54: Time to load utils op: 0.000896453857421875 secondsTime to load utils op: 0.0008766651153564453 seconds +54: +49: Time to load utils op: 0.000982046127319336 seconds +56: Time to load utils op: 0.0007929801940917969 seconds +54: Time to load utils op: 0.0009188652038574219 seconds +36: Time to load utils op: 0.0011115074157714844 seconds +56: Time to load utils op: 0.0008332729339599609 seconds +56: Time to load utils op: 0.0008168220520019531 seconds +56: Time to load utils op: 0.0008742809295654297 seconds +37: Time to load utils op: 0.0008547306060791016 secondsTime to load utils op: 0.0008716583251953125 seconds +37: +37: Time to load utils op: 0.0008471012115478516 seconds +34: Time to load utils op: 0.0008947849273681641 secondsTime to load utils op: 0.000896453857421875 seconds +34: +37: Time to load utils op: 0.0009312629699707031 seconds +34: Time to load utils op: 0.0008881092071533203 seconds +34: Time to load utils op: 0.0009832382202148438 seconds +40: Time to load utils op: 0.001039743423461914 seconds +40: Time to load utils op: 0.0010709762573242188 seconds +40: Time to load utils op: 0.001001596450805664 seconds +40: Time to load utils op: 0.0010805130004882812 seconds +39: Time to load utils op: 0.0008740425109863281 secondsTime to load utils op: 0.0008420944213867188 seconds +39: +39: Time to load utils op: 0.0008273124694824219 seconds +39: Time to load utils op: 0.0009050369262695312 seconds +55: Time to load utils op: 0.0008618831634521484 seconds +55: Time to load utils op: 0.0010051727294921875 seconds +55: Time to load utils op: 0.001056671142578125 seconds +55: Time to load utils op: 0.001180887222290039 seconds +45: Time to load utils op: 0.0006844997406005859 seconds +45: Time to load utils op: 0.0009095668792724609 secondsTime to load utils op: 0.0008990764617919922 seconds +45: +45: Time to load utils op: 0.0009295940399169922 seconds +35: Time to load utils op: 0.0007050037384033203 seconds +51: Time to load utils op: 0.0008594989776611328 seconds +35: Time to load utils op: 0.0009794235229492188 secondsTime to load utils op: 0.0009279251098632812 seconds +35: +51: Time to load utils op: 0.0009105205535888672 seconds +51: Time to load utils op: 0.0009169578552246094 seconds +35: Time to load utils op: 0.0009353160858154297 seconds +51: Time to load utils op: 0.0009484291076660156 seconds +59: Time to load utils op: 0.0009009838104248047 seconds +59: Time to load utils op: 0.0010743141174316406 seconds +59: Time to load utils op: 0.0010476112365722656 seconds +59: Time to load utils op: 0.0011937618255615234 seconds +38: Time to load utils op: 0.0007295608520507812 seconds +38: Time to load utils op: 0.0008249282836914062 seconds +38: Time to load utils op: 0.0005817413330078125 seconds +38: Time to load utils op: 0.0009191036224365234 seconds +50: Time to load utils op: 0.000568389892578125 seconds +50: Time to load utils op: 0.0005145072937011719 seconds +50: Time to load utils op: 0.0005028247833251953 seconds +50: Time to load utils op: 0.0005202293395996094 seconds +63: Time to load utils op: 0.0006875991821289062 seconds +63: Time to load utils op: 0.0009374618530273438 seconds +63: Time to load utils op: 0.0009016990661621094 seconds +63: Time to load utils op: 0.0009510517120361328 seconds +48: Time to load utils op: 0.0008540153503417969 seconds +48: Time to load utils op: 0.0009937286376953125 seconds +42: Time to load utils op: 0.0009238719940185547 seconds +42: Time to load utils op: 0.0009293556213378906 secondsTime to load utils op: 0.0009024143218994141 seconds +42: +48: Time to load utils op: 0.0009489059448242188 seconds +48: Time to load utils op: 0.0009396076202392578 seconds +42: Time to load utils op: 0.0009295940399169922 seconds +58: Time to load utils op: 0.0008144378662109375 seconds +58: Time to load utils op: 0.0009214878082275391 secondsTime to load utils op: 0.0009205341339111328 seconds +58: +58: Time to load utils op: 0.0009407997131347656 seconds +57: Time to load utils op: 0.0009074211120605469 seconds +57: Time to load utils op: 0.0009324550628662109 seconds +57: Time to load utils op: 0.0009624958038330078 seconds +52: Time to load utils op: 0.0009472370147705078 seconds +52: Time to load utils op: 0.0009086132049560547 secondsTime to load utils op: 0.0009634494781494141 seconds +52: +57: Time to load utils op: 0.0009849071502685547 seconds +52: Time to load utils op: 0.0009872913360595703 seconds +43: Time to load utils op: 0.0008940696716308594 secondsTime to load utils op: 0.0008883476257324219 seconds +43: +43: Time to load utils op: 0.0009713172912597656 seconds +43: Time to load utils op: 0.001043558120727539 seconds +60: Time to load utils op: 0.0005540847778320312 seconds +60: Time to load utils op: 0.0006186962127685547 seconds +60: Time to load utils op: 0.0005879402160644531 seconds +44: Time to load utils op: 0.0008633136749267578 seconds +44: Time to load utils op: 0.0008945465087890625 seconds +44: Time to load utils op: 0.0009768009185791016 seconds +44: Time to load utils op: 0.0007684230804443359 seconds +60: Time to load utils op: 0.0005364418029785156 seconds +53: Time to load utils op: 0.0009250640869140625 seconds +53: Time to load utils op: 0.0009024143218994141 seconds +53: Time to load utils op: 0.0009000301361083984 seconds +53: Time to load utils op: 0.0009572505950927734 seconds +62: Time to load utils op: 0.0007901191711425781 seconds +62: Time to load utils op: 0.000812530517578125 secondsTime to load utils op: 0.0005180835723876953 seconds +62: +62: Time to load utils op: 0.0007100105285644531 seconds +61: Time to load utils op: 0.0009481906890869141 seconds +61: Time to load utils op: 0.0009355545043945312 seconds +61: Time to load utils op: 0.0009453296661376953 seconds +61: Time to load utils op: 0.000978708267211914 seconds + 0: [2023-04-29 11:37:20,155] [INFO] [utils.py:827:see_memory_usage] before initializing group 0 + 0: [2023-04-29 11:37:20,155] [INFO] [utils.py:828:see_memory_usage] MA 4.15 GB Max_MA 4.15 GB CA 4.18 GB Max_CA 4 GB + 0: [2023-04-29 11:37:20,155] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 40.18 GB, percent = 8.0% + 0: [2023-04-29 11:37:20,459] [INFO] [utils.py:827:see_memory_usage] after initializing group 0 + 0: [2023-04-29 11:37:20,459] [INFO] [utils.py:828:see_memory_usage] MA 8.44 GB Max_MA 8.44 GB CA 10.57 GB Max_CA 11 GB + 0: [2023-04-29 11:37:20,460] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 40.4 GB, percent = 8.0% + 0: Time to load utils op: 0.00048828125 seconds + 0: [2023-04-29 11:37:20,578] [INFO] [utils.py:827:see_memory_usage] before initializing group 1 + 0: [2023-04-29 11:37:20,579] [INFO] [utils.py:828:see_memory_usage] MA 8.44 GB Max_MA 8.44 GB CA 10.57 GB Max_CA 11 GB + 0: [2023-04-29 11:37:20,579] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 40.49 GB, percent = 8.0% + 0: [2023-04-29 11:37:20,699] [INFO] [utils.py:827:see_memory_usage] after initializing group 1 + 0: [2023-04-29 11:37:20,700] [INFO] [utils.py:828:see_memory_usage] MA 12.5 GB Max_MA 12.5 GB CA 16.62 GB Max_CA 17 GB + 0: [2023-04-29 11:37:20,700] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 40.6 GB, percent = 8.1% + 0: [2023-04-29 11:37:20,815] [INFO] [utils.py:827:see_memory_usage] before initializing group 2 + 0: [2023-04-29 11:37:20,816] [INFO] [utils.py:828:see_memory_usage] MA 12.5 GB Max_MA 12.5 GB CA 16.62 GB Max_CA 17 GB + 0: [2023-04-29 11:37:20,816] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 40.7 GB, percent = 8.1% + 0: [2023-04-29 11:37:20,935] [INFO] [utils.py:827:see_memory_usage] after initializing group 2 + 0: [2023-04-29 11:37:20,936] [INFO] [utils.py:828:see_memory_usage] MA 12.51 GB Max_MA 12.51 GB CA 16.62 GB Max_CA 17 GB + 0: [2023-04-29 11:37:20,936] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 40.81 GB, percent = 8.1% + 0: [2023-04-29 11:37:21,052] [INFO] [utils.py:827:see_memory_usage] before initialize_optimizer + 0: [2023-04-29 11:37:21,053] [INFO] [utils.py:828:see_memory_usage] MA 12.51 GB Max_MA 12.51 GB CA 16.62 GB Max_CA 17 GB + 0: [2023-04-29 11:37:21,053] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 40.92 GB, percent = 8.1% +32: ninja: no work to do. +32: Time to load utils op: 0.26171875 seconds +59: Time to load utils op: 0.15230274200439453 seconds +42: Time to load utils op: 0.1642742156982422 seconds +59: Time to load utils op: 0.1585383415222168 seconds +53: Time to load utils op: 0.16451764106750488 seconds +57: Time to load utils op: 0.1524946689605713 seconds +42: Time to load utils op: 0.17030811309814453 seconds +53: Time to load utils op: 0.17675518989562988 seconds +59: Time to load utils op: 0.16707777976989746 seconds +57: Time to load utils op: 0.1586768627166748 seconds +42: Time to load utils op: 0.17052698135375977 seconds +53: Time to load utils op: 0.1827700138092041 seconds +57: Time to load utils op: 0.1645495891571045 seconds +59: Time to load utils op: 0.17405915260314941 seconds +42: Time to load utils op: 0.18278169631958008 seconds +53: Time to load utils op: 0.18886899948120117 seconds +57: Time to load utils op: 0.1705002784729004 seconds +41: Time to load utils op: 0.2756028175354004 seconds +56: Time to load utils op: 0.2667572498321533 seconds +56: Time to load utils op: 0.26771998405456543 secondsTime to load utils op: 0.2679004669189453 seconds +56: +56: Time to load utils op: 0.2671983242034912 seconds +60: Time to load utils op: 0.26645588874816895 seconds +58: Time to load utils op: 0.2629094123840332 seconds +37: Time to load utils op: 0.2496802806854248 seconds +45: Time to load utils op: 0.27146005630493164 seconds +45: Time to load utils op: 0.27162671089172363 secondsTime to load utils op: 0.27171874046325684 seconds +45: +45: Time to load utils op: 0.27175188064575195 seconds +55: Time to load utils op: 0.271451473236084 seconds +55: Time to load utils op: 0.27252888679504395 seconds +37: Time to load utils op: 0.25182032585144043 seconds +37: Time to load utils op: 0.251537561416626 seconds +55: Time to load utils op: 0.27266907691955566 seconds +43: Time to load utils op: 0.27461671829223633 seconds +55: Time to load utils op: 0.27219700813293457 seconds +43: Time to load utils op: 0.27474451065063477 seconds +43: Time to load utils op: 0.2745819091796875 secondsTime to load utils op: 0.2745802402496338 seconds +43: +37: Time to load utils op: 0.2521939277648926 seconds +58: Time to load utils op: 0.2661316394805908 seconds +36: Time to load utils op: 0.2682812213897705 seconds +41: Time to load utils op: 0.28217625617980957 seconds +60: Time to load utils op: 0.2711353302001953 secondsTime to load utils op: 0.2711613178253174 seconds +60: +35: Time to load utils op: 0.2849569320678711 seconds +60: Time to load utils op: 0.27097105979919434 seconds +58: Time to load utils op: 0.26775312423706055 seconds +44: Time to load utils op: 0.2779567241668701 seconds +58: Time to load utils op: 0.2693443298339844 seconds +63: Time to load utils op: 0.2715127468109131 seconds +54: Time to load utils op: 0.27701735496520996 seconds +36: Time to load utils op: 0.27141761779785156 seconds +33: Time to load utils op: 0.2892022132873535 seconds +63: Time to load utils op: 0.2731292247772217 seconds +41: Time to load utils op: 0.2877814769744873 seconds +49: Time to load utils op: 0.2834136486053467 seconds +44: Time to load utils op: 0.28257274627685547 seconds +34: Time to load utils op: 0.2883000373840332 seconds +35: Time to load utils op: 0.29120612144470215 seconds +36: Time to load utils op: 0.27591896057128906 seconds +63: Time to load utils op: 0.27715277671813965 seconds +54: Time to load utils op: 0.282073974609375 seconds +46: Time to load utils op: 0.28723597526550293 seconds +41: Time to load utils op: 0.29087018966674805 seconds +50: Time to load utils op: 0.28346967697143555 seconds +33: Time to load utils op: 0.29576826095581055 seconds +44: Time to load utils op: 0.28664708137512207 seconds +49: Time to load utils op: 0.2875528335571289 seconds +48: Time to load utils op: 0.23936700820922852 seconds +63: Time to load utils op: 0.28032469749450684 seconds +34: Time to load utils op: 0.29377007484436035 seconds +35: Time to load utils op: 0.2972722053527832 seconds +54: Time to load utils op: 0.2874948978424072 seconds +46: Time to load utils op: 0.2936899662017822 seconds +36: Time to load utils op: 0.2969367504119873 seconds +44: Time to load utils op: 0.2907583713531494 seconds +50: Time to load utils op: 0.2895650863647461 seconds +33: Time to load utils op: 0.3020613193511963 seconds +49: Time to load utils op: 0.2928779125213623 seconds +40: Time to load utils op: 0.2780013084411621 seconds +40: Time to load utils op: 0.2779839038848877 seconds +40: Time to load utils op: 0.27843379974365234 secondsTime to load utils op: 0.27846455574035645 seconds +40: +54: Time to load utils op: 0.2923929691314697 seconds +34: Time to load utils op: 0.29975318908691406 seconds +35: Time to load utils op: 0.3043339252471924 seconds +49: Time to load utils op: 0.2966597080230713 seconds +46: Time to load utils op: 0.29920029640197754 seconds +50: Time to load utils op: 0.29624414443969727 seconds +33: Time to load utils op: 0.30746984481811523 seconds +43: Time to load utils op: 0.0070269107818603516 secondsTime to load utils op: 0.007135152816772461 seconds +43: +34: Time to load utils op: 0.30580949783325195 seconds +43: Time to load utils op: 0.00035452842712402344 seconds +32: Time to load utils op: 0.3126339912414551 seconds +48: Time to load utils op: 0.23120546340942383 seconds +46: Time to load utils op: 0.30530238151550293 seconds +61: Time to load utils op: 0.2946815490722656 seconds +32: Time to load utils op: 0.31352972984313965 seconds +50: Time to load utils op: 0.30162715911865234 seconds +47: Time to load utils op: 0.30628514289855957 seconds +32: Time to load utils op: 0.3134148120880127 seconds +43: Time to load utils op: 0.008936882019042969 seconds +47: Time to load utils op: 0.308565616607666 seconds +47: Time to load utils op: 0.3085815906524658 seconds +47: Time to load utils op: 0.30894041061401367 seconds +55: Time to load utils op: 0.0004925727844238281 seconds +55: Time to load utils op: 0.0004603862762451172 seconds +61: Time to load utils op: 0.3005068302154541 seconds +55: Time to load utils op: 0.0003228187561035156 seconds +48: Time to load utils op: 0.2362825870513916 seconds +55: Time to load utils op: 0.0004143714904785156 seconds +38: Time to load utils op: 0.28543663024902344 seconds +48: Time to load utils op: 0.23947882652282715 seconds +61: Time to load utils op: 0.3038938045501709 seconds +61: Time to load utils op: 0.3077819347381592 seconds +38: Time to load utils op: 0.2912635803222656 seconds +52: Time to load utils op: 0.24993014335632324 seconds +32: Time to load utils op: 0.0005791187286376953 seconds +63: Time to load utils op: 0.0004487037658691406 seconds +63: Time to load utils op: 0.000408172607421875 seconds +63: Time to load utils op: 0.0003631114959716797 seconds +63: Time to load utils op: 0.0003554821014404297 seconds +39: Time to load utils op: 0.2842833995819092 seconds +39: Time to load utils op: 0.2843770980834961 seconds + 0: [2023-04-29 11:37:21,371] [INFO] [utils.py:827:see_memory_usage] end initialize_optimizer +39: Time to load utils op: 0.28466296195983887 seconds + 0: [2023-04-29 11:37:21,372] [INFO] [utils.py:828:see_memory_usage] MA 12.64 GB Max_MA 12.64 GB CA 16.62 GB Max_CA 17 GB +39: Time to load utils op: 0.2849740982055664 seconds + 0: [2023-04-29 11:37:21,372] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 41.19 GB, percent = 8.2% +38: Time to load utils op: 0.2971968650817871 seconds +52: Time to load utils op: 0.2624173164367676 seconds +38: Time to load utils op: 0.30047178268432617 seconds +51: Time to load utils op: 0.2910130023956299 seconds +62: Time to load utils op: 0.31417274475097656 seconds +36: Time to load utils op: 0.0004546642303466797 seconds +36: Time to load utils op: 0.00048041343688964844 seconds +36: Time to load utils op: 0.00035500526428222656 seconds +36: Time to load utils op: 0.00034618377685546875 seconds +52: Time to load utils op: 0.2620992660522461 seconds +56: Time to load utils op: 0.004448413848876953 secondsTime to load utils op: 0.0046863555908203125 seconds +56: Time to load utils op: 0.004559755325317383 seconds +56: +56: Time to load utils op: 0.0043718814849853516 seconds +52: Time to load utils op: 0.2656276226043701 seconds +51: Time to load utils op: 0.29784250259399414 seconds +62: Time to load utils op: 0.32012438774108887 seconds +58: Time to load utils op: 0.006102085113525391 seconds +58: Time to load utils op: 0.005606174468994141 seconds +58: Time to load utils op: 0.0055272579193115234 seconds +58: Time to load utils op: 0.006138324737548828 seconds +62: Time to load utils op: 0.32329845428466797 seconds +51: Time to load utils op: 0.30324482917785645 seconds +62: Time to load utils op: 0.3247663974761963 seconds +51: Time to load utils op: 0.3049178123474121 seconds +37: Time to load utils op: 0.0025289058685302734 secondsTime to load utils op: 0.0025980472564697266 seconds +37: +37: Time to load utils op: 0.002724885940551758 seconds +37: Time to load utils op: 0.0026607513427734375 seconds +32: Time to load utils op: 0.000354766845703125 secondsTime to load utils op: 0.00037932395935058594 seconds +32: +32: Time to load utils op: 0.0004737377166748047 seconds +40: Time to load utils op: 0.005515098571777344 secondsTime to load utils op: 0.005443096160888672 seconds +40: +40: Time to load utils op: 0.005972623825073242 secondsTime to load utils op: 0.005779743194580078 seconds +40: +38: Time to load utils op: 0.0015413761138916016 seconds +39: Time to load utils op: 0.001592397689819336 seconds +39: Time to load utils op: 0.0015385150909423828 seconds +39: Time to load utils op: 0.0020127296447753906 seconds +39: Time to load utils op: 0.0021152496337890625 seconds +38: Time to load utils op: 0.00033092498779296875 seconds +38: Time to load utils op: 0.00037407875061035156 seconds +60: Time to load utils op: 0.002629518508911133 seconds +60: Time to load utils op: 0.0031871795654296875 seconds +60: Time to load utils op: 0.0025191307067871094 seconds +60: Time to load utils op: 0.0028085708618164062 seconds +45: Time to load utils op: 0.0004496574401855469 seconds +45: Time to load utils op: 0.00045990943908691406 secondsTime to load utils op: 0.00048160552978515625 seconds +45: +45: Time to load utils op: 0.010923385620117188 seconds +38: Time to load utils op: 0.0003495216369628906 seconds + 0: [2023-04-29 11:37:21,509] [INFO] [utils.py:827:see_memory_usage] end bf16_optimizer + 0: [2023-04-29 11:37:21,510] [INFO] [utils.py:828:see_memory_usage] MA 12.64 GB Max_MA 12.64 GB CA 16.62 GB Max_CA 17 GB + 0: [2023-04-29 11:37:21,510] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 41.47 GB, percent = 8.2% + 0: [2023-04-29 11:37:21,510] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Final Optimizer = FusedAdam + 0: [2023-04-29 11:37:21,510] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed using client LR scheduler + 0: [2023-04-29 11:37:21,510] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed LR Scheduler = + 0: [2023-04-29 11:37:21,510] [INFO] [logging.py:68:log_dist] [Rank 0] step=0, skipped=0, lr=[0.0002, 0.0002, 0.0002], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] + 0: [2023-04-29 11:37:21,511] [INFO] [config.py:1007:print] DeepSpeedEngine configuration: + 0: [2023-04-29 11:37:21,511] [INFO] [config.py:1011:print] activation_checkpointing_config { + 0: "partition_activations": false, + 0: "contiguous_memory_optimization": false, + 0: "cpu_checkpointing": false, + 0: "number_checkpoints": null, + 0: "synchronize_checkpoint_boundary": false, + 0: "profile": false + 0: } + 0: [2023-04-29 11:37:21,511] [INFO] [config.py:1011:print] aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True} + 0: [2023-04-29 11:37:21,511] [INFO] [config.py:1011:print] amp_enabled .................. False + 0: [2023-04-29 11:37:21,511] [INFO] [config.py:1011:print] amp_params ................... False + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] autotuning_config ............ { + 0: "enabled": false, + 0: "start_step": null, + 0: "end_step": null, + 0: "metric_path": null, + 0: "arg_mappings": null, + 0: "metric": "throughput", + 0: "model_info": null, + 0: "results_dir": "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/autotuning_results", + 0: "exps_dir": "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/autotuning_exps", + 0: "overwrite": true, + 0: "fast": true, + 0: "start_profile_step": 3, + 0: "end_profile_step": 5, + 0: "tuner_type": "gridsearch", + 0: "tuner_early_stopping": 5, + 0: "tuner_num_trials": 50, + 0: "model_info_path": null, + 0: "mp_size": 1, + 0: "max_train_batch_size": null, + 0: "min_train_batch_size": 1, + 0: "max_train_micro_batch_size_per_gpu": 1.024000e+03, + 0: "min_train_micro_batch_size_per_gpu": 1, + 0: "num_tuning_micro_batch_sizes": 3 + 0: } + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] bfloat16_enabled ............. True + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] checkpoint_parallel_write_pipeline False + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] checkpoint_tag_validation_enabled True + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] checkpoint_tag_validation_fail False + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] comms_config ................. + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] communication_data_type ...... None + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] compression_config ........... {'weight_quantization': {'shared_parameters': {'enabled': False, 'quantizer_kernel': False, 'schedule_offset': 0, 'quantize_groups': 1, 'quantize_verbose': False, 'quantization_type': 'symmetric', 'quantize_weight_in_forward': False, 'rounding': 'nearest', 'fp16_mixed_quantize': False, 'quantize_change_ratio': 0.001}, 'different_groups': {}}, 'activation_quantization': {'shared_parameters': {'enabled': False, 'quantization_type': 'symmetric', 'range_calibration': 'dynamic', 'schedule_offset': 1000}, 'different_groups': {}}, 'sparse_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'row_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'head_pruning': {'shared_parameters': {'enabled': False, 'method': 'topk', 'schedule_offset': 1000}, 'different_groups': {}}, 'channel_pruning': {'shared_pa + 0: rameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'layer_reduction': {'enabled': False}} + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] curriculum_enabled ........... False + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] curriculum_params ............ False + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] dataloader_drop_last ......... False + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] disable_allgather ............ False + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] dump_state ................... False + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] dynamic_loss_scale_args ...... None + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] eigenvalue_enabled ........... False + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] eigenvalue_gas_boundary_resolution 1 + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] eigenvalue_layer_name ........ bert.encoder.layer + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] eigenvalue_layer_num ......... 0 + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] eigenvalue_max_iter .......... 100 + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] eigenvalue_stability ......... 1e-06 + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] eigenvalue_tol ............... 0.01 + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] eigenvalue_verbose ........... False + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] elasticity_enabled ........... False + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] flops_profiler_config ........ { + 0: "enabled": false, + 0: "profile_step": 1, + 0: "module_depth": -1, + 0: "top_modules": 1, + 0: "detailed": true, + 0: "output_file": null + 0: } + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] fp16_auto_cast ............... None + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] fp16_enabled ................. False + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] fp16_master_weights_and_gradients False + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] global_rank .................. 0 + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] gradient_accumulation_steps .. 4 + 0: [2023-04-29 11:37:21,512] [INFO] [config.py:1011:print] gradient_clipping ............ 1.0 + 0: [2023-04-29 11:37:21,513] [INFO] [config.py:1011:print] gradient_predivide_factor .... 1.0 + 0: [2023-04-29 11:37:21,513] [INFO] [config.py:1011:print] initial_dynamic_scale ........ 1 + 0: [2023-04-29 11:37:21,513] [INFO] [config.py:1011:print] load_universal_checkpoint .... False + 0: [2023-04-29 11:37:21,513] [INFO] [config.py:1011:print] loss_scale ................... 1.0 + 0: [2023-04-29 11:37:21,513] [INFO] [config.py:1011:print] memory_breakdown ............. False + 0: [2023-04-29 11:37:21,513] [INFO] [config.py:1011:print] monitor_config ............... + 0: [2023-04-29 11:37:21,513] [INFO] [config.py:1011:print] nebula_config ................ { + 0: "enabled": false, + 0: "persistent_storage_path": null, + 0: "persistent_time_interval": 100, + 0: "num_of_version_in_retention": 2, + 0: "enable_nebula_load": true, + 0: "load_path": null + 0: } + 0: [2023-04-29 11:37:21,513] [INFO] [config.py:1011:print] optimizer_legacy_fusion ...... False + 0: [2023-04-29 11:37:21,513] [INFO] [config.py:1011:print] optimizer_name ............... None + 0: [2023-04-29 11:37:21,513] [INFO] [config.py:1011:print] optimizer_params ............. None + 0: [2023-04-29 11:37:21,513] [INFO] [config.py:1011:print] pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0} + 0: [2023-04-29 11:37:21,513] [INFO] [config.py:1011:print] pld_enabled .................. False + 0: [2023-04-29 11:37:21,513] [INFO] [config.py:1011:print] pld_params ................... False + 0: [2023-04-29 11:37:21,513] [INFO] [config.py:1011:print] prescale_gradients ........... False + 0: [2023-04-29 11:37:21,513] [INFO] [config.py:1011:print] scheduler_name ............... None + 0: [2023-04-29 11:37:21,513] [INFO] [config.py:1011:print] scheduler_params ............. None + 0: [2023-04-29 11:37:21,513] [INFO] [config.py:1011:print] sparse_attention ............. None + 0: [2023-04-29 11:37:21,513] [INFO] [config.py:1011:print] sparse_gradients_enabled ..... False + 0: [2023-04-29 11:37:21,513] [INFO] [config.py:1011:print] steps_per_print .............. 2000 + 0: [2023-04-29 11:37:21,513] [INFO] [config.py:1011:print] train_batch_size ............. 512 + 0: [2023-04-29 11:37:21,513] [INFO] [config.py:1011:print] train_micro_batch_size_per_gpu 1 + 0: [2023-04-29 11:37:21,513] [INFO] [config.py:1011:print] use_node_local_storage ....... False + 0: [2023-04-29 11:37:21,513] [INFO] [config.py:1011:print] wall_clock_breakdown ......... False + 0: [2023-04-29 11:37:21,513] [INFO] [config.py:1011:print] world_size ................... 128 + 0: [2023-04-29 11:37:21,513] [INFO] [config.py:1011:print] zero_allow_untested_optimizer False + 0: [2023-04-29 11:37:21,513] [INFO] [config.py:1011:print] zero_config .................. stage=0 contiguous_gradients=True reduce_scatter=True reduce_bucket_size=500000000 allgather_partitions=True allgather_bucket_size=500000000 overlap_comm=False load_from_fp32_weights=True elastic_checkpoint=False offload_param=None offload_optimizer=None sub_group_size=1000000000 cpu_offload_param=None cpu_offload_use_pin_memory=None cpu_offload=None prefetch_bucket_size=50000000 param_persistence_threshold=100000 model_persistence_threshold=9223372036854775807 max_live_parameters=1000000000 max_reuse_distance=1000000000 gather_16bit_weights_on_model_save=False stage3_gather_fp16_weights_on_model_save=False ignore_unused_parameters=True legacy_stage1=False round_robin_gradients=False + 0: [2023-04-29 11:37:21,513] [INFO] [config.py:1011:print] zero_enabled ................. False + 0: [2023-04-29 11:37:21,513] [INFO] [config.py:1011:print] zero_optimization_stage ...... 0 + 0: [2023-04-29 11:37:21,513] [INFO] [config.py:996:print_user_config] json = { + 0: "train_micro_batch_size_per_gpu": 1, + 0: "train_batch_size": 512, + 0: "gradient_clipping": 1.0, + 0: "zero_optimization": { + 0: "stage": 0 + 0: }, + 0: "bf16": { + 0: "enabled": true + 0: }, + 0: "steps_per_print": 2.000000e+03, + 0: "wall_clock_breakdown": false + 0: } + 0: Time to load utils op: 0.00410151481628418 seconds + 0: [2023-04-29 11:37:21,518] [INFO] [engine.py:87:__init__] CONFIG: micro_batches=4 micro_batch_size=1 +42: Time to load utils op: 0.0009410381317138672 seconds +42: Time to load utils op: 0.0003974437713623047 seconds +42: Time to load utils op: 0.00036072731018066406 secondsTime to load utils op: 0.00036525726318359375 seconds +42: +47: Time to load utils op: 0.0072286128997802734 seconds +44: Time to load utils op: 0.006841421127319336 seconds +44: Time to load utils op: 0.006857156753540039 secondsTime to load utils op: 0.0067174434661865234 secondsTime to load utils op: 0.006784677505493164 seconds +44: +44: +61: Time to load utils op: 0.000568389892578125 secondsTime to load utils op: 0.0005931854248046875 seconds +61: +61: Time to load utils op: 0.0005028247833251953 seconds +61: Time to load utils op: 0.0004413127899169922 seconds +54: Time to load utils op: 0.0026040077209472656 secondsTime to load utils op: 0.002601146697998047 seconds +54: +54: Time to load utils op: 0.002834796905517578 seconds +54: Time to load utils op: 0.0020134449005126953 seconds +47: Time to load utils op: 0.00036144256591796875 seconds +49: Time to load utils op: 0.00456690788269043 seconds +49: Time to load utils op: 0.0003695487976074219 seconds +49: Time to load utils op: 0.0003504753112792969 seconds +49: Time to load utils op: 0.0004756450653076172 seconds +47: Time to load utils op: 0.0003612041473388672 seconds +41: Time to load utils op: 0.006154298782348633 secondsTime to load utils op: 0.00617671012878418 seconds +41: Time to load utils op: 0.006079912185668945 seconds +41: Time to load utils op: 0.006045341491699219 seconds +41: +47: Time to load utils op: 0.00047969818115234375 seconds +62: Time to load utils op: 0.0051746368408203125 secondsTime to load utils op: 0.0052335262298583984 secondsTime to load utils op: 0.005258321762084961 seconds +62: +62: +62: Time to load utils op: 0.00538945198059082 seconds +59: Time to load utils op: 0.008336067199707031 seconds +53: Time to load utils op: 0.004183292388916016 secondsTime to load utils op: 0.004213094711303711 seconds +53: +53: Time to load utils op: 0.0004718303680419922 seconds +59: Time to load utils op: 0.008346319198608398 seconds +51: Time to load utils op: 0.0048809051513671875 secondsTime to load utils op: 0.004990577697753906 seconds +51: +51: Time to load utils op: 0.004678010940551758 seconds +51: Time to load utils op: 0.004630327224731445 seconds +53: Time to load utils op: 0.0004267692565917969 seconds +57: Time to load utils op: 0.00395512580871582 secondsTime to load utils op: 0.0039539337158203125 seconds +57: +48: Time to load utils op: 0.00330352783203125 secondsTime to load utils op: 0.0035161972045898438 secondsTime to load utils op: 0.0034568309783935547 seconds +48: +48: +48: Time to load utils op: 0.003018617630004883 seconds +57: Time to load utils op: 0.0041086673736572266 seconds +59: Time to load utils op: 0.0004947185516357422 seconds +32: [2023-04-29 11:37:21,715] [INFO] [engine.py:145:__init__] RANK=256 STAGE=1 LAYERS=25 [24, 49) STAGE_PARAMS=2226427904 (2226.428M) TOTAL_PARAMS=8905695232 (8905.695M) UNIQUE_PARAMS=8682348544 (8682.349M) + 0: [2023-04-29 11:37:21,715] [INFO] [engine.py:145:__init__] RANK=0 STAGE=0 LAYERS=24 [0, 24) STAGE_PARAMS=2226419712 (2226.420M) TOTAL_PARAMS=8905695232 (8905.695M) UNIQUE_PARAMS=8682348544 (8682.349M) +32: [2023-04-29 11:37:21,715] [INFO] [engine.py:145:__init__] RANK=257 STAGE=1 LAYERS=25 [24, 49) STAGE_PARAMS=2226427904 (2226.428M) TOTAL_PARAMS=8905695232 (8905.695M) UNIQUE_PARAMS=8682348544 (8682.349M) + 0: [2023-04-29 11:37:21,715] [INFO] [engine.py:145:__init__] RANK=1 STAGE=0 LAYERS=24 [0, 24) STAGE_PARAMS=2226419712 (2226.420M) TOTAL_PARAMS=8905695232 (8905.695M) UNIQUE_PARAMS=8682348544 (8682.349M) +59: Time to load utils op: 0.0005049705505371094 seconds +57: Time to load utils op: 0.00040459632873535156 seconds +46: Time to load utils op: 0.004313230514526367 seconds +46: Time to load utils op: 0.0004456043243408203 secondsTime to load utils op: 0.0004680156707763672 seconds +46: +52: Time to load utils op: 0.0039038658142089844 seconds +34: Time to load utils op: 0.004075288772583008 seconds +50: Time to load utils op: 0.0069103240966796875 seconds +34: Time to load utils op: 0.004150390625 seconds +50: Time to load utils op: 0.00033736228942871094 seconds +34: Time to load utils op: 0.0004467964172363281 seconds +52: Time to load utils op: 0.004555702209472656 seconds +35: Time to load utils op: 0.004128456115722656 secondsTime to load utils op: 0.004163980484008789 seconds +35: +35: Time to load utils op: 0.004258871078491211 seconds +33: Time to load utils op: 0.0043752193450927734 secondsTime to load utils op: 0.0045168399810791016 seconds +33: +52: Time to load utils op: 0.00035452842712402344 seconds +35: Time to load utils op: 0.0003304481506347656 seconds +50: Time to load utils op: 0.0003437995910644531 seconds +52: Time to load utils op: 0.0003962516784667969 seconds +33: Time to load utils op: 0.0003666877746582031 seconds +46: Time to load utils op: 0.0004734992980957031 seconds +34: Time to load utils op: 0.00035834312438964844 seconds +50: Time to load utils op: 0.0003981590270996094 seconds +33: Time to load utils op: 0.0004715919494628906 seconds +32: [2023-04-29 11:37:23,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +32: [2023-04-29 11:37:23,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +32: [2023-04-29 11:37:23,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +32: [2023-04-29 11:37:23,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +32: [2023-04-29 11:37:23,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +32: [2023-04-29 11:37:23,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +32: [2023-04-29 11:37:23,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +32: [2023-04-29 11:37:23,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +56: [2023-04-29 11:37:23,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +56: [2023-04-29 11:37:23,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +56: [2023-04-29 11:37:23,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +56: [2023-04-29 11:37:23,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +56: [2023-04-29 11:37:23,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +56: [2023-04-29 11:37:23,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +56: [2023-04-29 11:37:23,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +56: [2023-04-29 11:37:23,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 0: [2023-04-29 11:37:23,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 0: [2023-04-29 11:37:23,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 0: [2023-04-29 11:37:23,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 0: [2023-04-29 11:37:23,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 0: [2023-04-29 11:37:23,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +26: [2023-04-29 11:37:23,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +26: [2023-04-29 11:37:23,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +26: [2023-04-29 11:37:23,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +26: [2023-04-29 11:37:23,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +26: [2023-04-29 11:37:23,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 0: [2023-04-29 11:37:23,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 0: [2023-04-29 11:37:23,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +26: [2023-04-29 11:37:23,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +26: [2023-04-29 11:37:23,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +59: [2023-04-29 11:37:23,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +59: [2023-04-29 11:37:23,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +59: [2023-04-29 11:37:23,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +59: [2023-04-29 11:37:23,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +59: [2023-04-29 11:37:23,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +59: [2023-04-29 11:37:23,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +59: [2023-04-29 11:37:23,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +60: [2023-04-29 11:37:23,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +60: [2023-04-29 11:37:23,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +60: [2023-04-29 11:37:23,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +60: [2023-04-29 11:37:23,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +60: [2023-04-29 11:37:23,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +60: [2023-04-29 11:37:23,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +60: [2023-04-29 11:37:23,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +62: [2023-04-29 11:37:23,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +62: [2023-04-29 11:37:23,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +62: [2023-04-29 11:37:23,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +62: [2023-04-29 11:37:23,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +62: [2023-04-29 11:37:23,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +62: [2023-04-29 11:37:23,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +62: [2023-04-29 11:37:23,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +26: [2023-04-29 11:37:23,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +48: [2023-04-29 11:37:23,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +10: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +48: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +48: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +48: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +48: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +48: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +33: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +48: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 0: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 3: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +34: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +59: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +41: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +35: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +60: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +10: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +10: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +10: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +62: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +10: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +34: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +34: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +10: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +10: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +41: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +41: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +41: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +41: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +41: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +34: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +33: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +33: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +33: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +33: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 3: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 3: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 3: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 3: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 3: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +41: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +35: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +35: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +35: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +35: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +35: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +33: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 3: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +34: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +34: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +33: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +35: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +34: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +31: [2023-04-29 11:37:23,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +48: [2023-04-29 11:37:23,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +31: [2023-04-29 11:37:23,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +31: [2023-04-29 11:37:23,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +10: [2023-04-29 11:37:23,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +31: [2023-04-29 11:37:23,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +31: [2023-04-29 11:37:23,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +31: [2023-04-29 11:37:23,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +31: [2023-04-29 11:37:23,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +33: [2023-04-29 11:37:23,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +63: [2023-04-29 11:37:23,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +63: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +34: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +41: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +50: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 3: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +53: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 9: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +39: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +35: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +53: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +53: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +39: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +39: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +39: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 9: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 9: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 9: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 9: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +39: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +39: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +53: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 9: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 9: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +63: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +63: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +39: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +53: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +63: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +63: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +63: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +53: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +53: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +28: [2023-04-29 11:37:23,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +55: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +45: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +54: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 8: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +47: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +31: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +28: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +28: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +54: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +54: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +54: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +54: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +28: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +28: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +28: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +45: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +45: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +45: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +54: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +47: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +28: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 9: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +24: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +47: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 4: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +44: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +50: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +61: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +53: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +55: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +55: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +55: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +55: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +55: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +63: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +58: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 8: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +54: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +47: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +28: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +40: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +50: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +39: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +51: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +55: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 8: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 8: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +47: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +47: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +37: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +42: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 7: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 8: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +47: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +50: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +23: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 8: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 8: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +50: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +50: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +45: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +45: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +45: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +58: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +50: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +51: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +24: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +37: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +42: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +40: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +40: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +40: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +40: [2023-04-29 11:37:23,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +40: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 7: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +61: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +61: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +24: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +40: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +44: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +44: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +44: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +51: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +58: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +58: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 4: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +44: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +11: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +24: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +24: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +37: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 4: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +61: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +61: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +61: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +61: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +51: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +58: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +58: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +24: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +25: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +47: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 4: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 4: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 4: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +52: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +45: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +51: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +55: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +58: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 8: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +24: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +54: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +37: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +43: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +49: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +42: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +40: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 7: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 7: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 7: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +36: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +51: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +51: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +58: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +37: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +37: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +23: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 4: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +57: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +37: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 7: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 7: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +23: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +23: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +23: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 4: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +23: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +23: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +46: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +44: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +44: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +61: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +50: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +49: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +24: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +37: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +42: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +42: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +42: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +42: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +44: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +49: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +49: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +49: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 7: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +52: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +52: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +52: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +43: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +43: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +11: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +11: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +11: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +11: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +51: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +25: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +25: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +25: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +25: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +25: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +49: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +49: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +52: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +36: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +36: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +36: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +36: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +25: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +43: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +43: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +43: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +43: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +36: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +11: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +42: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +52: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +52: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +36: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +11: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +23: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +38: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +57: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +57: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +57: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +57: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +57: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +52: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +11: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +57: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +46: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +25: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +43: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +49: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +38: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +38: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +36: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +38: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +38: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +57: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 6: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 6: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 6: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 6: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 6: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +46: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +46: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +46: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 6: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 6: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 6: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +46: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +46: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +38: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +38: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +38: [2023-04-29 11:37:23,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +46: [2023-04-29 11:37:23,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 2: [2023-04-29 11:37:23,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 2: [2023-04-29 11:37:23,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 2: [2023-04-29 11:37:23,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 2: [2023-04-29 11:37:23,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 2: [2023-04-29 11:37:23,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 2: [2023-04-29 11:37:23,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 2: [2023-04-29 11:37:23,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +12: [2023-04-29 11:37:23,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +12: [2023-04-29 11:37:23,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +12: [2023-04-29 11:37:23,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +12: [2023-04-29 11:37:23,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +12: [2023-04-29 11:37:23,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +12: [2023-04-29 11:37:23,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +12: [2023-04-29 11:37:23,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 2: [2023-04-29 11:37:23,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +22: [2023-04-29 11:37:23,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +22: [2023-04-29 11:37:23,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +22: [2023-04-29 11:37:23,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +22: [2023-04-29 11:37:23,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +22: [2023-04-29 11:37:23,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +22: [2023-04-29 11:37:23,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +22: [2023-04-29 11:37:23,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +32: [2023-04-29 11:37:23,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +32: [2023-04-29 11:37:23,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +32: [2023-04-29 11:37:23,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +32: [2023-04-29 11:37:23,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +32: [2023-04-29 11:37:23,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +32: [2023-04-29 11:37:23,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +32: [2023-04-29 11:37:23,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +32: [2023-04-29 11:37:23,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +32: [2023-04-29 11:37:23,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +32: [2023-04-29 11:37:23,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +32: [2023-04-29 11:37:23,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +32: [2023-04-29 11:37:23,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +32: [2023-04-29 11:37:23,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +32: [2023-04-29 11:37:23,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +32: [2023-04-29 11:37:23,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +32: [2023-04-29 11:37:23,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +12: [2023-04-29 11:37:23,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +14: [2023-04-29 11:37:23,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +14: [2023-04-29 11:37:23,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +14: [2023-04-29 11:37:23,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +14: [2023-04-29 11:37:23,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +14: [2023-04-29 11:37:23,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +14: [2023-04-29 11:37:23,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +56: [2023-04-29 11:37:23,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +56: [2023-04-29 11:37:23,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +56: [2023-04-29 11:37:23,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +56: [2023-04-29 11:37:23,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +14: [2023-04-29 11:37:23,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +56: [2023-04-29 11:37:23,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +56: [2023-04-29 11:37:23,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +56: [2023-04-29 11:37:23,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +22: [2023-04-29 11:37:23,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +14: [2023-04-29 11:37:23,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +56: [2023-04-29 11:37:23,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +56: [2023-04-29 11:37:23,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +56: [2023-04-29 11:37:23,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +56: [2023-04-29 11:37:23,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +56: [2023-04-29 11:37:23,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +56: [2023-04-29 11:37:23,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +56: [2023-04-29 11:37:23,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +56: [2023-04-29 11:37:23,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +56: [2023-04-29 11:37:23,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +60: [2023-04-29 11:37:23,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +60: [2023-04-29 11:37:23,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +60: [2023-04-29 11:37:23,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +60: [2023-04-29 11:37:23,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +60: [2023-04-29 11:37:23,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +60: [2023-04-29 11:37:23,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +60: [2023-04-29 11:37:23,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +60: [2023-04-29 11:37:23,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +60: [2023-04-29 11:37:23,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +60: [2023-04-29 11:37:23,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +60: [2023-04-29 11:37:23,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +60: [2023-04-29 11:37:23,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +60: [2023-04-29 11:37:23,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +60: [2023-04-29 11:37:23,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +60: [2023-04-29 11:37:23,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +60: [2023-04-29 11:37:23,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +59: [2023-04-29 11:37:23,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +59: [2023-04-29 11:37:23,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +59: [2023-04-29 11:37:23,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +59: [2023-04-29 11:37:23,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +59: [2023-04-29 11:37:23,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +59: [2023-04-29 11:37:23,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +59: [2023-04-29 11:37:23,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +59: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +59: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +59: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +59: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +59: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +59: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +59: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +59: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +59: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +33: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +33: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +33: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +33: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +33: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +20: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 0: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 0: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 0: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 0: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 0: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +33: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +33: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 0: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 0: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +20: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +20: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 0: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 0: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 0: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 0: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +33: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +20: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 0: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +20: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +20: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +35: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +35: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +35: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +26: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +26: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +26: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +26: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +26: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +35: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +35: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +35: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +35: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +20: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +26: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +26: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +26: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +26: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +26: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +26: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +35: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +26: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 1: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 1: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 1: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 1: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 1: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 0: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 0: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 0: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 0: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +33: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +33: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +33: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +33: [2023-04-29 11:37:23,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +33: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +33: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +33: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +33: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... + 1: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 1: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +26: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +26: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +26: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +35: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +35: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +35: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +35: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +26: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 5: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 5: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +35: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +35: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +35: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... + 5: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +35: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +48: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +48: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +48: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +48: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +48: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +48: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +48: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +48: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 5: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 5: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 5: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 5: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 0: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +30: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +46: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +46: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +48: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +48: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +48: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +46: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +46: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +26: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +46: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +46: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +46: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +48: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +48: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... + 0: [2023-04-29 11:37:23,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +48: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +48: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +48: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +46: [2023-04-29 11:37:23,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 0: [2023-04-29 11:37:23,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +26: [2023-04-29 11:37:23,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 0: [2023-04-29 11:37:23,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +26: [2023-04-29 11:37:23,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +46: [2023-04-29 11:37:23,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +46: [2023-04-29 11:37:23,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +46: [2023-04-29 11:37:23,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +46: [2023-04-29 11:37:23,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +46: [2023-04-29 11:37:23,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +46: [2023-04-29 11:37:23,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +46: [2023-04-29 11:37:23,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +46: [2023-04-29 11:37:23,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +26: [2023-04-29 11:37:23,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 0: [2023-04-29 11:37:23,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +26: [2023-04-29 11:37:23,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 0: [2023-04-29 11:37:23,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 0: [2023-04-29 11:37:23,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +26: [2023-04-29 11:37:23,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 0: [2023-04-29 11:37:23,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +26: [2023-04-29 11:37:23,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +26: [2023-04-29 11:37:23,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +30: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +30: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +30: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +30: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +30: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +30: [2023-04-29 11:37:23,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +50: [2023-04-29 11:37:23,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +50: [2023-04-29 11:37:23,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +50: [2023-04-29 11:37:23,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +50: [2023-04-29 11:37:23,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +50: [2023-04-29 11:37:23,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +50: [2023-04-29 11:37:23,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +50: [2023-04-29 11:37:23,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +50: [2023-04-29 11:37:23,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 8: [2023-04-29 11:37:23,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 8: [2023-04-29 11:37:23,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +50: [2023-04-29 11:37:23,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +50: [2023-04-29 11:37:23,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +50: [2023-04-29 11:37:23,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +50: [2023-04-29 11:37:23,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... + 8: [2023-04-29 11:37:23,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 8: [2023-04-29 11:37:23,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 8: [2023-04-29 11:37:23,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +50: [2023-04-29 11:37:23,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... + 8: [2023-04-29 11:37:23,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 8: [2023-04-29 11:37:23,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +50: [2023-04-29 11:37:23,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +50: [2023-04-29 11:37:23,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +50: [2023-04-29 11:37:23,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... + 8: [2023-04-29 11:37:23,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 8: [2023-04-29 11:37:23,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 8: [2023-04-29 11:37:23,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 8: [2023-04-29 11:37:23,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 8: [2023-04-29 11:37:23,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +54: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +54: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +54: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +54: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +54: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +54: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +54: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 8: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 8: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 8: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +54: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 8: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +34: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +34: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +34: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +34: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +34: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +63: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +63: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +63: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +63: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +63: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +34: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +34: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +63: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +63: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +34: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +63: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +20: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +54: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +54: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +54: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +54: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +54: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +54: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +54: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +54: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... + 3: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +41: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +41: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +41: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +41: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +41: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 3: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 3: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +34: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +34: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +34: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +34: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... + 3: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 3: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 3: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +41: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +63: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +63: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +25: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +25: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +25: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +25: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +25: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +41: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 8: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +34: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +34: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +25: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +47: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +47: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +47: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +47: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +47: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 3: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +63: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +63: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +34: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +34: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +25: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 3: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 7: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 7: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 7: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 7: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +63: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +63: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +25: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +25: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +25: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 3: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 3: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +41: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +63: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +25: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +47: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +47: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 7: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 7: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +32: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +25: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 3: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 7: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +63: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +47: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 3: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +32: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. + 5: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 7: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 7: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 8: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 7: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +32: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. + 7: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +59: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +59: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +48: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +41: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +41: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... + 1: [2023-04-29 11:37:23,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 7: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +59: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +48: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +41: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +41: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +24: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +24: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +24: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +24: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +24: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +48: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +41: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +41: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +41: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +41: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +24: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +24: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +25: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +25: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +25: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +25: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +32: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +47: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +47: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... + 3: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 3: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +35: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +35: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. + 8: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +56: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +24: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +24: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +48: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +60: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +60: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +60: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +24: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +24: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +47: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +47: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... + 3: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 3: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +10: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +10: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +10: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +10: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +10: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 7: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 7: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 7: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 7: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 8: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +24: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +47: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +35: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +56: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +47: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +10: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +47: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +10: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +47: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +10: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +56: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +33: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +33: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +10: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +28: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +28: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +59: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +10: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +33: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +10: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +30: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +28: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +28: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +28: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +28: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +60: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +28: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +35: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +56: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +28: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +46: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +33: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +28: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +28: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +24: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +24: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +24: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +10: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +24: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +46: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. + 8: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +28: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 3: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +46: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +28: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 8: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +10: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +10: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +10: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +10: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +46: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +32: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +25: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +28: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +28: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +28: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +48: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... + 3: [2023-04-29 11:37:23,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 7: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 8: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +28: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +32: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +59: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... + 8: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 3: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +32: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +11: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +11: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +11: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +11: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +11: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +31: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +48: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +32: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +11: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +11: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +31: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +31: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +48: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +35: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +11: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +31: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +31: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +25: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +11: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +31: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +59: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +56: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +35: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... + 7: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +31: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +55: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +55: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +55: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +55: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +55: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +60: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +11: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +33: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +49: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +11: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +31: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +55: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +55: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +59: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +59: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +60: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +62: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +62: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +62: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +56: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +56: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +48: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +11: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +31: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +24: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +25: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +49: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +49: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +35: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +35: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +39: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +39: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +39: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +39: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +39: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +31: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +55: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +62: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +62: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +62: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 3: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +49: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +49: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +36: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +36: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +36: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +36: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +36: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +31: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +62: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +33: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +33: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +49: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +36: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +11: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +11: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +60: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +49: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 7: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +36: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +39: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +31: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +62: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +56: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +39: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +11: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +11: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +60: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +24: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +49: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 7: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +31: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +33: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +39: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +25: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +31: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +31: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +31: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +46: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... + 3: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +10: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +28: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +36: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 3: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +10: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +55: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +55: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +24: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 9: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 9: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 9: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 9: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 9: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 4: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 4: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 4: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 4: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +55: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +55: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +46: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... + 3: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 9: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 9: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +55: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +62: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +62: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +62: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +25: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 4: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +55: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +55: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +10: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 4: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 4: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 9: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 9: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +55: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... + 7: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +62: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +24: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 4: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +28: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +39: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... + 9: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +62: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +62: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +49: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +49: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +49: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +49: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... + 4: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +62: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +62: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +42: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +42: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +42: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +42: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +42: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +44: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +44: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +44: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +44: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +44: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +36: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +36: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +36: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +36: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +39: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +45: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +45: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +45: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +45: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +45: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 9: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +46: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +25: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +49: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +49: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... + 4: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +28: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +28: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 7: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +36: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +36: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +39: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +45: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +49: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +42: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 4: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +44: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +44: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +36: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +36: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +39: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +39: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +39: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +45: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +46: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +49: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +42: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +10: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 4: [2023-04-29 11:37:23,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +39: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +39: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +51: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +51: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +51: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +53: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +53: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +53: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +53: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +53: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 9: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +50: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +50: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +44: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +45: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +51: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +51: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +51: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +25: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +42: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +51: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +53: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +53: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +50: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +53: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 3: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +11: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 9: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 9: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +24: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 7: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 9: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 9: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +31: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +51: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +24: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 7: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +45: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +45: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +45: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +25: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +45: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +42: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +42: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +42: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +50: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +54: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +54: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +54: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +42: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +42: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +31: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +42: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +11: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +24: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +42: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +42: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +44: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +53: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +53: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +31: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +45: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +45: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +45: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +54: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. + 4: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 4: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 4: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +28: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +31: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +45: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +53: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +53: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +44: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +44: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +53: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +53: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +24: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 4: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +53: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +44: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +53: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +28: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +51: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +51: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +51: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +51: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +51: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +44: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +44: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +44: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +52: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +52: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +52: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +52: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +51: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +44: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +11: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +51: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +51: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +28: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +52: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +61: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +61: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +61: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +43: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +10: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +28: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +52: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +52: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +11: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +61: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +61: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +61: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +61: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +43: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +43: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +34: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +43: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +43: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +43: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +43: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +63: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. + 6: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 6: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 6: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 6: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 6: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +10: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +52: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +58: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +34: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +61: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +38: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +38: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +38: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +38: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +38: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 4: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 6: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 6: [2023-04-29 11:37:23,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +57: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +57: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +57: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +57: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +57: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +58: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +34: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +43: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 6: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 6: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 9: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +58: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +58: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +58: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +58: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +37: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +38: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +38: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +63: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +63: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +57: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +57: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +58: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +10: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +23: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +23: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +23: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 6: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +37: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +40: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +40: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +40: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +40: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +40: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +52: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... + 6: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +58: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +37: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +37: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +37: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +37: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +41: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +41: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. + 6: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +37: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +23: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +23: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +38: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 4: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +40: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +40: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +52: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +50: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +11: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +57: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +41: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +10: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +23: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +52: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +52: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +31: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +47: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +37: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +23: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +40: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +52: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +61: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +61: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... + 4: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +43: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +43: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +43: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +43: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +41: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +23: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +23: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +23: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +52: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +52: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +31: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +31: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +61: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... + 9: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +23: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +52: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... + 6: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 6: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 6: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 6: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +11: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +61: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +54: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +43: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +43: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +61: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +34: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +43: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +23: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +50: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +61: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +43: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +61: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +58: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +58: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +58: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +47: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +47: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. + 9: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +54: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +54: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +37: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +11: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +61: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +57: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +58: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +23: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +38: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +38: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +50: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +58: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +58: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +37: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +37: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +11: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +58: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +58: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +37: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +40: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +40: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +40: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +57: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +23: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +38: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +38: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... + 4: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +50: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +57: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +47: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +37: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +37: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +23: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +38: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +40: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +57: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt... +54: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +37: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +38: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +57: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +57: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +37: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +23: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +38: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +38: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +57: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... + 9: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +57: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +40: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +40: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +31: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +34: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +40: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +40: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt... +63: [2023-04-29 11:37:23,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... + 4: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 4: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +34: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... + 6: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +41: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +63: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +34: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +41: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... + 4: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +34: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +63: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +41: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... + 6: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +47: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +47: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +47: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... + 9: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 9: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +41: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... + 4: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 6: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +47: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... + 6: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +23: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 9: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 9: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +49: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +55: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +49: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +49: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +63: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +55: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +55: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +49: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +23: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +39: [2023-04-29 11:37:23,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. + 6: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +39: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +55: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +23: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 6: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +39: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. + 6: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +36: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. + 6: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +23: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +39: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +36: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +36: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +42: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +42: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +42: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +62: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +62: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +36: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +62: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +23: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +45: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +49: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +63: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +53: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +53: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +53: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +55: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +44: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +49: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +42: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +55: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +49: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +29: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +23: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +45: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +45: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +49: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +23: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +39: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +44: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +55: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +55: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +53: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +62: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +44: [2023-04-29 11:37:23,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +39: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +44: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +23: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +39: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +39: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +36: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +36: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +45: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +51: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +51: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +36: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +36: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +51: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +52: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +52: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +52: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +61: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +42: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +61: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +61: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +29: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +29: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +29: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +29: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +62: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +29: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +29: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +42: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +51: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +43: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +38: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +38: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +38: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +45: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +52: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +45: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +45: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +53: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +62: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +44: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +43: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +42: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +38: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +61: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +43: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +42: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +44: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +53: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +37: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +58: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +58: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +62: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +57: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +44: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +53: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +53: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +43: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +40: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +58: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +57: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +57: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +40: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +44: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +62: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +45: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +37: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +37: [2023-04-29 11:37:23,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +40: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +57: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +58: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +51: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +37: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +61: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +51: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +52: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +51: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +40: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_03_model_states.pt. +52: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +51: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +61: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +43: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +38: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +38: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +52: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +52: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +61: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +61: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +38: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +43: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +58: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +37: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +57: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +37: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +38: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +58: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +40: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +37: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +43: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +43: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +40: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +40: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +58: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +37: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... + 0: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +58: [2023-04-29 11:37:23,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... + 0: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 0: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +57: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +57: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +57: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +40: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... + 8: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 3: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +28: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 8: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 8: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +28: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +26: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +26: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +28: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 0: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 3: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 3: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +25: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +25: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +25: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 8: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 7: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +24: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +24: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +24: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +26: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +31: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 7: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +25: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +10: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 7: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 6: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +28: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +11: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +11: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +11: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +31: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +31: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 3: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +23: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +26: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 7: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 0: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 0: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 0: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +10: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +10: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +23: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +11: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 6: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +31: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 9: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +23: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 4: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 4: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +24: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 4: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 9: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 9: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +10: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 6: [2023-04-29 11:37:23,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 3: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 8: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 6: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 4: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +28: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +23: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 8: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 8: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 0: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +26: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 9: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +28: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +28: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 8: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +26: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +25: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 3: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 3: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +24: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +24: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +25: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 7: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 7: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +24: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +26: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +25: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +31: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 7: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +25: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +10: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +11: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +28: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +31: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +31: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +26: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 3: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 6: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +11: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +11: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +23: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 7: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +10: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +10: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +11: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 9: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +23: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +24: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 9: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 4: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 4: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +31: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +10: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 4: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 9: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +23: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 6: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 4: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 6: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 9: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +23: [2023-04-29 11:37:23,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 6: [2023-04-29 11:37:23,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +32: [2023-04-29 11:37:23,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +32: [2023-04-29 11:37:23,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +32: [2023-04-29 11:37:23,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +32: [2023-04-29 11:37:23,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +59: [2023-04-29 11:37:23,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +59: [2023-04-29 11:37:23,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +59: [2023-04-29 11:37:23,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +59: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +33: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +33: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +48: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +48: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +33: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +60: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +60: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +60: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +56: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +35: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +34: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +34: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +34: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +48: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +56: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +35: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +56: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +60: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +55: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +48: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +33: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +47: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +54: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +54: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +54: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +32: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +55: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +39: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +39: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +63: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +63: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +47: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +35: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +55: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +47: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +36: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +36: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +36: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +41: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +41: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +41: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +52: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +39: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +56: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +61: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +52: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +51: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +51: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +51: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +32: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +32: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +54: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +55: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +52: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +34: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +47: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +43: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +43: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +63: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +46: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +41: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +49: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +40: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +40: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +35: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +32: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +39: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +61: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +62: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +62: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +46: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +42: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +49: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +49: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +59: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +59: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +59: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +37: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +50: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +36: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +45: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +45: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +45: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +62: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +46: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +43: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +40: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +53: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +53: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +53: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +63: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +29: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +37: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +49: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +52: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +50: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +42: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +42: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +50: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +59: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +37: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +57: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +57: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +46: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +33: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +33: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +33: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +44: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +44: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +44: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +45: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +61: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +53: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +58: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +62: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +34: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +34: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +48: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +48: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +43: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +38: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +40: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +35: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +51: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +58: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +60: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +60: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +56: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +34: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +48: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +58: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +42: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +38: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +38: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +35: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +60: [2023-04-29 11:37:23,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +44: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +50: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +57: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +58: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +60: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +56: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +38: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +55: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +56: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +48: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +33: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +61: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +47: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +47: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +37: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +35: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +55: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +54: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +54: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +54: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +55: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +63: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +63: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +57: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_02_model_states.pt. +41: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +41: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +39: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +39: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +39: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +56: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +47: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +52: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +52: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +36: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +36: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +36: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +41: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +61: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +51: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +51: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +51: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +34: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +55: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +54: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +63: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +47: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +43: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +41: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +49: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +35: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +52: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +43: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +39: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +40: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +40: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +61: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +49: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +42: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +62: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +62: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +36: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +45: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +45: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +45: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +43: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +49: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +52: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +53: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +53: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +63: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +49: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +42: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +42: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +40: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +37: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +53: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +46: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +62: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +37: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +43: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +50: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +61: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +46: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +58: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +37: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +38: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +38: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +38: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +40: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +44: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +44: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +44: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +50: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +45: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +51: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +53: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +57: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +46: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +58: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +42: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +58: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +62: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +50: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +57: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +44: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +38: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +58: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +46: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +61: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +37: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +57: [2023-04-29 11:37:23,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +57: [2023-04-29 11:37:23,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +50: [2023-04-29 11:37:23,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +16: [2023-04-29 11:37:23,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +16: [2023-04-29 11:37:23,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +16: [2023-04-29 11:37:23,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +16: [2023-04-29 11:37:23,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +16: [2023-04-29 11:37:23,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +16: [2023-04-29 11:37:23,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +13: [2023-04-29 11:37:23,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +16: [2023-04-29 11:37:23,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +13: [2023-04-29 11:37:23,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +13: [2023-04-29 11:37:23,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +13: [2023-04-29 11:37:23,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +13: [2023-04-29 11:37:23,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +13: [2023-04-29 11:37:23,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +13: [2023-04-29 11:37:23,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +13: [2023-04-29 11:37:23,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +16: [2023-04-29 11:37:23,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +12: [2023-04-29 11:37:23,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +12: [2023-04-29 11:37:23,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +12: [2023-04-29 11:37:23,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +12: [2023-04-29 11:37:23,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +12: [2023-04-29 11:37:23,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +12: [2023-04-29 11:37:23,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +12: [2023-04-29 11:37:23,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +12: [2023-04-29 11:37:23,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +12: [2023-04-29 11:37:23,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +12: [2023-04-29 11:37:23,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +19: [2023-04-29 11:37:23,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +21: [2023-04-29 11:37:23,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +21: [2023-04-29 11:37:23,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +21: [2023-04-29 11:37:23,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +21: [2023-04-29 11:37:23,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +21: [2023-04-29 11:37:23,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +19: [2023-04-29 11:37:23,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +19: [2023-04-29 11:37:23,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +19: [2023-04-29 11:37:23,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +19: [2023-04-29 11:37:23,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +19: [2023-04-29 11:37:23,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +21: [2023-04-29 11:37:23,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +19: [2023-04-29 11:37:23,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +21: [2023-04-29 11:37:23,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +27: [2023-04-29 11:37:23,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +27: [2023-04-29 11:37:23,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +27: [2023-04-29 11:37:23,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +27: [2023-04-29 11:37:23,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +27: [2023-04-29 11:37:23,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +27: [2023-04-29 11:37:23,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +27: [2023-04-29 11:37:23,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +12: [2023-04-29 11:37:23,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +12: [2023-04-29 11:37:23,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +12: [2023-04-29 11:37:23,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +17: [2023-04-29 11:37:23,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +17: [2023-04-29 11:37:23,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +17: [2023-04-29 11:37:23,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +17: [2023-04-29 11:37:23,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +17: [2023-04-29 11:37:23,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +17: [2023-04-29 11:37:23,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +17: [2023-04-29 11:37:23,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 2: [2023-04-29 11:37:23,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 2: [2023-04-29 11:37:23,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 2: [2023-04-29 11:37:23,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 2: [2023-04-29 11:37:23,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 2: [2023-04-29 11:37:23,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 2: [2023-04-29 11:37:23,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 2: [2023-04-29 11:37:23,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 2: [2023-04-29 11:37:23,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 2: [2023-04-29 11:37:23,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 2: [2023-04-29 11:37:23,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +15: [2023-04-29 11:37:23,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +15: [2023-04-29 11:37:23,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +15: [2023-04-29 11:37:23,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +15: [2023-04-29 11:37:23,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +15: [2023-04-29 11:37:23,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +15: [2023-04-29 11:37:23,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +12: [2023-04-29 11:37:23,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +12: [2023-04-29 11:37:23,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +12: [2023-04-29 11:37:23,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +12: [2023-04-29 11:37:23,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +12: [2023-04-29 11:37:23,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +15: [2023-04-29 11:37:23,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +21: [2023-04-29 11:37:23,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +19: [2023-04-29 11:37:23,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +12: [2023-04-29 11:37:23,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +12: [2023-04-29 11:37:23,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +27: [2023-04-29 11:37:23,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +18: [2023-04-29 11:37:23,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +18: [2023-04-29 11:37:23,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +18: [2023-04-29 11:37:23,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +18: [2023-04-29 11:37:23,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +18: [2023-04-29 11:37:23,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +18: [2023-04-29 11:37:23,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +18: [2023-04-29 11:37:23,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +29: [2023-04-29 11:37:23,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +29: [2023-04-29 11:37:23,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +29: [2023-04-29 11:37:23,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +29: [2023-04-29 11:37:23,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +29: [2023-04-29 11:37:23,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +29: [2023-04-29 11:37:23,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +29: [2023-04-29 11:37:23,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +29: [2023-04-29 11:37:23,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +29: [2023-04-29 11:37:23,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +29: [2023-04-29 11:37:23,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +29: [2023-04-29 11:37:23,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +29: [2023-04-29 11:37:23,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +17: [2023-04-29 11:37:23,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 2: [2023-04-29 11:37:23,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +15: [2023-04-29 11:37:23,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 2: [2023-04-29 11:37:23,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +29: [2023-04-29 11:37:23,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +29: [2023-04-29 11:37:23,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +29: [2023-04-29 11:37:23,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +29: [2023-04-29 11:37:23,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +12: [2023-04-29 11:37:23,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +12: [2023-04-29 11:37:23,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +12: [2023-04-29 11:37:23,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +12: [2023-04-29 11:37:23,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +18: [2023-04-29 11:37:23,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +12: [2023-04-29 11:37:23,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +12: [2023-04-29 11:37:23,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +12: [2023-04-29 11:37:23,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +12: [2023-04-29 11:37:23,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +22: [2023-04-29 11:37:23,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +22: [2023-04-29 11:37:23,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +22: [2023-04-29 11:37:23,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +22: [2023-04-29 11:37:23,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +22: [2023-04-29 11:37:23,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +22: [2023-04-29 11:37:23,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +22: [2023-04-29 11:37:23,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +22: [2023-04-29 11:37:23,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +22: [2023-04-29 11:37:23,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +22: [2023-04-29 11:37:23,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +22: [2023-04-29 11:37:23,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +22: [2023-04-29 11:37:23,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +22: [2023-04-29 11:37:23,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +22: [2023-04-29 11:37:23,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +22: [2023-04-29 11:37:23,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +22: [2023-04-29 11:37:23,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +29: [2023-04-29 11:37:23,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +12: [2023-04-29 11:37:23,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +12: [2023-04-29 11:37:23,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +29: [2023-04-29 11:37:23,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +29: [2023-04-29 11:37:23,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +12: [2023-04-29 11:37:23,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +12: [2023-04-29 11:37:23,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 2: [2023-04-29 11:37:23,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 2: [2023-04-29 11:37:23,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 2: [2023-04-29 11:37:23,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 2: [2023-04-29 11:37:23,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +29: [2023-04-29 11:37:23,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 2: [2023-04-29 11:37:23,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 2: [2023-04-29 11:37:23,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 2: [2023-04-29 11:37:23,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 2: [2023-04-29 11:37:23,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +14: [2023-04-29 11:37:23,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +14: [2023-04-29 11:37:23,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +14: [2023-04-29 11:37:23,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +14: [2023-04-29 11:37:23,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +14: [2023-04-29 11:37:23,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +14: [2023-04-29 11:37:23,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +14: [2023-04-29 11:37:23,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +14: [2023-04-29 11:37:23,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +14: [2023-04-29 11:37:23,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +14: [2023-04-29 11:37:23,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +14: [2023-04-29 11:37:23,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +14: [2023-04-29 11:37:23,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +14: [2023-04-29 11:37:23,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +14: [2023-04-29 11:37:23,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +14: [2023-04-29 11:37:23,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +14: [2023-04-29 11:37:23,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +14: [2023-04-29 11:37:23,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +14: [2023-04-29 11:37:23,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +22: [2023-04-29 11:37:23,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +22: [2023-04-29 11:37:23,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +22: [2023-04-29 11:37:23,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +14: [2023-04-29 11:37:23,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +14: [2023-04-29 11:37:23,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +22: [2023-04-29 11:37:23,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 2: [2023-04-29 11:37:23,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 2: [2023-04-29 11:37:23,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 2: [2023-04-29 11:37:23,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 2: [2023-04-29 11:37:23,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 2: [2023-04-29 11:37:23,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +29: [2023-04-29 11:37:23,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 2: [2023-04-29 11:37:23,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 2: [2023-04-29 11:37:23,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +22: [2023-04-29 11:37:23,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +22: [2023-04-29 11:37:23,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +29: [2023-04-29 11:37:23,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +29: [2023-04-29 11:37:23,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +22: [2023-04-29 11:37:23,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 2: [2023-04-29 11:37:23,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +29: [2023-04-29 11:37:23,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 2: [2023-04-29 11:37:23,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 2: [2023-04-29 11:37:23,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +29: [2023-04-29 11:37:23,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +29: [2023-04-29 11:37:23,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +29: [2023-04-29 11:37:23,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 2: [2023-04-29 11:37:23,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +29: [2023-04-29 11:37:23,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +29: [2023-04-29 11:37:23,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +29: [2023-04-29 11:37:23,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 2: [2023-04-29 11:37:23,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +14: [2023-04-29 11:37:23,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +14: [2023-04-29 11:37:23,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +14: [2023-04-29 11:37:23,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +22: [2023-04-29 11:37:23,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +29: [2023-04-29 11:37:23,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +29: [2023-04-29 11:37:23,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +14: [2023-04-29 11:37:23,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +22: [2023-04-29 11:37:23,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +22: [2023-04-29 11:37:23,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +22: [2023-04-29 11:37:23,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +22: [2023-04-29 11:37:23,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +22: [2023-04-29 11:37:23,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +22: [2023-04-29 11:37:23,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +22: [2023-04-29 11:37:23,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +22: [2023-04-29 11:37:23,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +14: [2023-04-29 11:37:23,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +14: [2023-04-29 11:37:23,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +14: [2023-04-29 11:37:23,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +14: [2023-04-29 11:37:23,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +14: [2023-04-29 11:37:23,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +14: [2023-04-29 11:37:23,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +14: [2023-04-29 11:37:23,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +14: [2023-04-29 11:37:23,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +13: [2023-04-29 11:37:23,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +13: [2023-04-29 11:37:23,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +13: [2023-04-29 11:37:23,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +13: [2023-04-29 11:37:23,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +13: [2023-04-29 11:37:23,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +13: [2023-04-29 11:37:23,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +13: [2023-04-29 11:37:23,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +13: [2023-04-29 11:37:23,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +13: [2023-04-29 11:37:23,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +13: [2023-04-29 11:37:23,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +13: [2023-04-29 11:37:23,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +13: [2023-04-29 11:37:23,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +13: [2023-04-29 11:37:23,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +13: [2023-04-29 11:37:23,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +13: [2023-04-29 11:37:23,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +13: [2023-04-29 11:37:23,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +13: [2023-04-29 11:37:23,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +13: [2023-04-29 11:37:23,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +13: [2023-04-29 11:37:23,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +13: [2023-04-29 11:37:23,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +15: [2023-04-29 11:37:23,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +15: [2023-04-29 11:37:23,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +15: [2023-04-29 11:37:23,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +15: [2023-04-29 11:37:23,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +15: [2023-04-29 11:37:23,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +15: [2023-04-29 11:37:23,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +15: [2023-04-29 11:37:23,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +15: [2023-04-29 11:37:23,462] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +15: [2023-04-29 11:37:23,462] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +15: [2023-04-29 11:37:23,462] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +15: [2023-04-29 11:37:23,462] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +15: [2023-04-29 11:37:23,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +15: [2023-04-29 11:37:23,463] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +15: [2023-04-29 11:37:23,463] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +15: [2023-04-29 11:37:23,463] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +15: [2023-04-29 11:37:23,463] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +15: [2023-04-29 11:37:23,464] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +15: [2023-04-29 11:37:23,464] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +15: [2023-04-29 11:37:23,464] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +13: [2023-04-29 11:37:23,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +13: [2023-04-29 11:37:23,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +13: [2023-04-29 11:37:23,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +13: [2023-04-29 11:37:23,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +15: [2023-04-29 11:37:23,464] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +13: [2023-04-29 11:37:23,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +13: [2023-04-29 11:37:23,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +13: [2023-04-29 11:37:23,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +13: [2023-04-29 11:37:23,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +13: [2023-04-29 11:37:23,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +13: [2023-04-29 11:37:23,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +13: [2023-04-29 11:37:23,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +13: [2023-04-29 11:37:23,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +15: [2023-04-29 11:37:23,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +15: [2023-04-29 11:37:23,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +15: [2023-04-29 11:37:23,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +15: [2023-04-29 11:37:23,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +15: [2023-04-29 11:37:23,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +15: [2023-04-29 11:37:23,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +15: [2023-04-29 11:37:23,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +15: [2023-04-29 11:37:23,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +15: [2023-04-29 11:37:23,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +15: [2023-04-29 11:37:23,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +15: [2023-04-29 11:37:23,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +15: [2023-04-29 11:37:23,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +16: [2023-04-29 11:37:23,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +16: [2023-04-29 11:37:23,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +16: [2023-04-29 11:37:23,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +16: [2023-04-29 11:37:23,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +16: [2023-04-29 11:37:23,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +16: [2023-04-29 11:37:23,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +16: [2023-04-29 11:37:23,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +16: [2023-04-29 11:37:23,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +16: [2023-04-29 11:37:23,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +16: [2023-04-29 11:37:23,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +16: [2023-04-29 11:37:23,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +16: [2023-04-29 11:37:23,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +16: [2023-04-29 11:37:23,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +16: [2023-04-29 11:37:23,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +16: [2023-04-29 11:37:23,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +16: [2023-04-29 11:37:23,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +16: [2023-04-29 11:37:23,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +16: [2023-04-29 11:37:23,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +16: [2023-04-29 11:37:23,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +16: [2023-04-29 11:37:23,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +16: [2023-04-29 11:37:23,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +16: [2023-04-29 11:37:23,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +16: [2023-04-29 11:37:23,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +16: [2023-04-29 11:37:23,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +20: [2023-04-29 11:37:23,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +20: [2023-04-29 11:37:23,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +20: [2023-04-29 11:37:23,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +20: [2023-04-29 11:37:23,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +20: [2023-04-29 11:37:23,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +20: [2023-04-29 11:37:23,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +20: [2023-04-29 11:37:23,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +20: [2023-04-29 11:37:23,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +20: [2023-04-29 11:37:23,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +20: [2023-04-29 11:37:23,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +16: [2023-04-29 11:37:23,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +16: [2023-04-29 11:37:23,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +16: [2023-04-29 11:37:23,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +16: [2023-04-29 11:37:23,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +16: [2023-04-29 11:37:23,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +16: [2023-04-29 11:37:23,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +16: [2023-04-29 11:37:23,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +16: [2023-04-29 11:37:23,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +19: [2023-04-29 11:37:23,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +19: [2023-04-29 11:37:23,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +19: [2023-04-29 11:37:23,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +19: [2023-04-29 11:37:23,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +19: [2023-04-29 11:37:23,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +19: [2023-04-29 11:37:23,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +19: [2023-04-29 11:37:23,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +19: [2023-04-29 11:37:23,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +19: [2023-04-29 11:37:23,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +19: [2023-04-29 11:37:23,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +19: [2023-04-29 11:37:23,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +19: [2023-04-29 11:37:23,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +19: [2023-04-29 11:37:23,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +19: [2023-04-29 11:37:23,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +19: [2023-04-29 11:37:23,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +19: [2023-04-29 11:37:23,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +19: [2023-04-29 11:37:23,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +19: [2023-04-29 11:37:23,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +19: [2023-04-29 11:37:23,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +19: [2023-04-29 11:37:23,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +19: [2023-04-29 11:37:23,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +19: [2023-04-29 11:37:23,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +19: [2023-04-29 11:37:23,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +20: [2023-04-29 11:37:23,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +19: [2023-04-29 11:37:23,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +20: [2023-04-29 11:37:23,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +20: [2023-04-29 11:37:23,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +20: [2023-04-29 11:37:23,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +20: [2023-04-29 11:37:23,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +20: [2023-04-29 11:37:23,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +19: [2023-04-29 11:37:23,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +20: [2023-04-29 11:37:23,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +19: [2023-04-29 11:37:23,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +20: [2023-04-29 11:37:23,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +19: [2023-04-29 11:37:23,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +20: [2023-04-29 11:37:23,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +20: [2023-04-29 11:37:23,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +19: [2023-04-29 11:37:23,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +19: [2023-04-29 11:37:23,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +19: [2023-04-29 11:37:23,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +20: [2023-04-29 11:37:23,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +20: [2023-04-29 11:37:23,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +20: [2023-04-29 11:37:23,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +20: [2023-04-29 11:37:23,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +20: [2023-04-29 11:37:23,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +20: [2023-04-29 11:37:23,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +20: [2023-04-29 11:37:23,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +20: [2023-04-29 11:37:23,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 1: [2023-04-29 11:37:23,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 1: [2023-04-29 11:37:23,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 1: [2023-04-29 11:37:23,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +20: [2023-04-29 11:37:23,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 1: [2023-04-29 11:37:23,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 1: [2023-04-29 11:37:23,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 1: [2023-04-29 11:37:23,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 1: [2023-04-29 11:37:23,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 1: [2023-04-29 11:37:23,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 1: [2023-04-29 11:37:23,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 1: [2023-04-29 11:37:23,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +20: [2023-04-29 11:37:23,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 1: [2023-04-29 11:37:23,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 1: [2023-04-29 11:37:23,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +20: [2023-04-29 11:37:23,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +20: [2023-04-29 11:37:23,493] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +19: [2023-04-29 11:37:23,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +19: [2023-04-29 11:37:23,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 1: [2023-04-29 11:37:23,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 1: [2023-04-29 11:37:23,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 1: [2023-04-29 11:37:23,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 1: [2023-04-29 11:37:23,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 1: [2023-04-29 11:37:23,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 1: [2023-04-29 11:37:23,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 1: [2023-04-29 11:37:23,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 1: [2023-04-29 11:37:23,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +21: [2023-04-29 11:37:23,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +21: [2023-04-29 11:37:23,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +21: [2023-04-29 11:37:23,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +21: [2023-04-29 11:37:23,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +21: [2023-04-29 11:37:23,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +21: [2023-04-29 11:37:23,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +21: [2023-04-29 11:37:23,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +21: [2023-04-29 11:37:23,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +21: [2023-04-29 11:37:23,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +21: [2023-04-29 11:37:23,502] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +21: [2023-04-29 11:37:23,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +21: [2023-04-29 11:37:23,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +21: [2023-04-29 11:37:23,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +21: [2023-04-29 11:37:23,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +21: [2023-04-29 11:37:23,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +21: [2023-04-29 11:37:23,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +21: [2023-04-29 11:37:23,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +21: [2023-04-29 11:37:23,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +21: [2023-04-29 11:37:23,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +21: [2023-04-29 11:37:23,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +21: [2023-04-29 11:37:23,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +21: [2023-04-29 11:37:23,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +21: [2023-04-29 11:37:23,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +21: [2023-04-29 11:37:23,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +21: [2023-04-29 11:37:23,505] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +21: [2023-04-29 11:37:23,505] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +21: [2023-04-29 11:37:23,505] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 5: [2023-04-29 11:37:23,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 5: [2023-04-29 11:37:23,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 5: [2023-04-29 11:37:23,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 5: [2023-04-29 11:37:23,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 5: [2023-04-29 11:37:23,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 5: [2023-04-29 11:37:23,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 5: [2023-04-29 11:37:23,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 5: [2023-04-29 11:37:23,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 5: [2023-04-29 11:37:23,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 5: [2023-04-29 11:37:23,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... + 5: [2023-04-29 11:37:23,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +30: [2023-04-29 11:37:23,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +21: [2023-04-29 11:37:23,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 1: [2023-04-29 11:37:23,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 1: [2023-04-29 11:37:23,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 1: [2023-04-29 11:37:23,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +17: [2023-04-29 11:37:23,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +17: [2023-04-29 11:37:23,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +17: [2023-04-29 11:37:23,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +17: [2023-04-29 11:37:23,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +17: [2023-04-29 11:37:23,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 1: [2023-04-29 11:37:23,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +17: [2023-04-29 11:37:23,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +17: [2023-04-29 11:37:23,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +17: [2023-04-29 11:37:23,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +17: [2023-04-29 11:37:23,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +17: [2023-04-29 11:37:23,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +17: [2023-04-29 11:37:23,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +30: [2023-04-29 11:37:23,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +30: [2023-04-29 11:37:23,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +30: [2023-04-29 11:37:23,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +30: [2023-04-29 11:37:23,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +30: [2023-04-29 11:37:23,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +30: [2023-04-29 11:37:23,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +30: [2023-04-29 11:37:23,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +30: [2023-04-29 11:37:23,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +30: [2023-04-29 11:37:23,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +30: [2023-04-29 11:37:23,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +17: [2023-04-29 11:37:23,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 5: [2023-04-29 11:37:23,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +17: [2023-04-29 11:37:23,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +17: [2023-04-29 11:37:23,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +17: [2023-04-29 11:37:23,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +17: [2023-04-29 11:37:23,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +17: [2023-04-29 11:37:23,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +17: [2023-04-29 11:37:23,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +30: [2023-04-29 11:37:23,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +17: [2023-04-29 11:37:23,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +17: [2023-04-29 11:37:23,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 1: [2023-04-29 11:37:23,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 1: [2023-04-29 11:37:23,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 1: [2023-04-29 11:37:23,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +17: [2023-04-29 11:37:23,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +17: [2023-04-29 11:37:23,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +17: [2023-04-29 11:37:23,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 1: [2023-04-29 11:37:23,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 1: [2023-04-29 11:37:23,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 1: [2023-04-29 11:37:23,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 1: [2023-04-29 11:37:23,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +17: [2023-04-29 11:37:23,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 1: [2023-04-29 11:37:23,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +17: [2023-04-29 11:37:23,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +17: [2023-04-29 11:37:23,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +17: [2023-04-29 11:37:23,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +17: [2023-04-29 11:37:23,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 5: [2023-04-29 11:37:23,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 5: [2023-04-29 11:37:23,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 5: [2023-04-29 11:37:23,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 5: [2023-04-29 11:37:23,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +17: [2023-04-29 11:37:23,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +17: [2023-04-29 11:37:23,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +17: [2023-04-29 11:37:23,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +17: [2023-04-29 11:37:23,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +30: [2023-04-29 11:37:23,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +30: [2023-04-29 11:37:23,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +30: [2023-04-29 11:37:23,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +21: [2023-04-29 11:37:23,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +21: [2023-04-29 11:37:23,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +21: [2023-04-29 11:37:23,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +21: [2023-04-29 11:37:23,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +30: [2023-04-29 11:37:23,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +27: [2023-04-29 11:37:23,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +27: [2023-04-29 11:37:23,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +27: [2023-04-29 11:37:23,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +27: [2023-04-29 11:37:23,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +27: [2023-04-29 11:37:23,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +27: [2023-04-29 11:37:23,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +27: [2023-04-29 11:37:23,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +27: [2023-04-29 11:37:23,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +27: [2023-04-29 11:37:23,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +27: [2023-04-29 11:37:23,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +27: [2023-04-29 11:37:23,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +27: [2023-04-29 11:37:23,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +27: [2023-04-29 11:37:23,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +27: [2023-04-29 11:37:23,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +27: [2023-04-29 11:37:23,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +27: [2023-04-29 11:37:23,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... + 5: [2023-04-29 11:37:23,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 5: [2023-04-29 11:37:23,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 5: [2023-04-29 11:37:23,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 5: [2023-04-29 11:37:23,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +30: [2023-04-29 11:37:23,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +30: [2023-04-29 11:37:23,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +30: [2023-04-29 11:37:23,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +30: [2023-04-29 11:37:23,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +27: [2023-04-29 11:37:23,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +27: [2023-04-29 11:37:23,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +27: [2023-04-29 11:37:23,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +27: [2023-04-29 11:37:23,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. + 5: [2023-04-29 11:37:23,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 5: [2023-04-29 11:37:23,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 5: [2023-04-29 11:37:23,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 5: [2023-04-29 11:37:23,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 5: [2023-04-29 11:37:23,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 5: [2023-04-29 11:37:23,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 5: [2023-04-29 11:37:23,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 5: [2023-04-29 11:37:23,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 5: [2023-04-29 11:37:23,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 5: [2023-04-29 11:37:23,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +30: [2023-04-29 11:37:23,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +30: [2023-04-29 11:37:23,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +30: [2023-04-29 11:37:23,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 5: [2023-04-29 11:37:23,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. + 5: [2023-04-29 11:37:23,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +27: [2023-04-29 11:37:23,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +27: [2023-04-29 11:37:23,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +27: [2023-04-29 11:37:23,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +30: [2023-04-29 11:37:23,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +30: [2023-04-29 11:37:23,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +27: [2023-04-29 11:37:23,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +30: [2023-04-29 11:37:23,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +30: [2023-04-29 11:37:23,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +30: [2023-04-29 11:37:23,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +30: [2023-04-29 11:37:23,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +30: [2023-04-29 11:37:23,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +30: [2023-04-29 11:37:23,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +30: [2023-04-29 11:37:23,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +27: [2023-04-29 11:37:23,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +27: [2023-04-29 11:37:23,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +27: [2023-04-29 11:37:23,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +27: [2023-04-29 11:37:23,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +27: [2023-04-29 11:37:23,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +27: [2023-04-29 11:37:23,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +27: [2023-04-29 11:37:23,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +27: [2023-04-29 11:37:23,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +18: [2023-04-29 11:37:23,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +18: [2023-04-29 11:37:23,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +18: [2023-04-29 11:37:23,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +18: [2023-04-29 11:37:23,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +18: [2023-04-29 11:37:23,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +18: [2023-04-29 11:37:23,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +18: [2023-04-29 11:37:23,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +18: [2023-04-29 11:37:23,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +18: [2023-04-29 11:37:23,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +18: [2023-04-29 11:37:23,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +18: [2023-04-29 11:37:23,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt... +18: [2023-04-29 11:37:23,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +18: [2023-04-29 11:37:23,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +18: [2023-04-29 11:37:23,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +18: [2023-04-29 11:37:23,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +18: [2023-04-29 11:37:23,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt... +18: [2023-04-29 11:37:23,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +18: [2023-04-29 11:37:23,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +18: [2023-04-29 11:37:23,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +18: [2023-04-29 11:37:23,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_00_model_states.pt. +18: [2023-04-29 11:37:23,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +18: [2023-04-29 11:37:23,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +18: [2023-04-29 11:37:23,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +18: [2023-04-29 11:37:23,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +18: [2023-04-29 11:37:23,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/mp_rank_01_model_states.pt. +18: [2023-04-29 11:37:23,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +18: [2023-04-29 11:37:23,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +18: [2023-04-29 11:37:23,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +18: [2023-04-29 11:37:23,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +18: [2023-04-29 11:37:23,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +18: [2023-04-29 11:37:23,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +18: [2023-04-29 11:37:23,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +48: [2023-04-29 11:37:23,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +48: [2023-04-29 11:37:23,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +48: [2023-04-29 11:37:23,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +48: [2023-04-29 11:37:23,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +59: [2023-04-29 11:37:23,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +59: [2023-04-29 11:37:23,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +59: [2023-04-29 11:37:23,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +59: [2023-04-29 11:37:23,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +59: [2023-04-29 11:37:23,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +48: [2023-04-29 11:37:23,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +59: [2023-04-29 11:37:23,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +59: [2023-04-29 11:37:23,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +48: [2023-04-29 11:37:23,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +48: [2023-04-29 11:37:23,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +59: [2023-04-29 11:37:23,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +48: [2023-04-29 11:37:23,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +48: [2023-04-29 11:37:23,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +48: [2023-04-29 11:37:23,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +48: [2023-04-29 11:37:23,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +48: [2023-04-29 11:37:23,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +48: [2023-04-29 11:37:23,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +48: [2023-04-29 11:37:23,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +48: [2023-04-29 11:37:23,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +48: [2023-04-29 11:37:23,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +59: [2023-04-29 11:37:23,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +59: [2023-04-29 11:37:23,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +59: [2023-04-29 11:37:23,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +59: [2023-04-29 11:37:23,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +59: [2023-04-29 11:37:23,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +59: [2023-04-29 11:37:23,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +59: [2023-04-29 11:37:23,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +59: [2023-04-29 11:37:23,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +33: [2023-04-29 11:37:23,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +33: [2023-04-29 11:37:23,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +33: [2023-04-29 11:37:23,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +33: [2023-04-29 11:37:23,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +33: [2023-04-29 11:37:23,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +33: [2023-04-29 11:37:23,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +33: [2023-04-29 11:37:23,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +33: [2023-04-29 11:37:23,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +33: [2023-04-29 11:37:23,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +33: [2023-04-29 11:37:23,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +33: [2023-04-29 11:37:23,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +33: [2023-04-29 11:37:23,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +33: [2023-04-29 11:37:23,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +33: [2023-04-29 11:37:23,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +33: [2023-04-29 11:37:23,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +33: [2023-04-29 11:37:23,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +48: [2023-04-29 11:37:23,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +32: [2023-04-29 11:37:23,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +32: [2023-04-29 11:37:23,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +32: [2023-04-29 11:37:23,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +32: [2023-04-29 11:37:23,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +32: [2023-04-29 11:37:23,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +32: [2023-04-29 11:37:23,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +32: [2023-04-29 11:37:23,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +32: [2023-04-29 11:37:23,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +48: [2023-04-29 11:37:23,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +59: [2023-04-29 11:37:23,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +59: [2023-04-29 11:37:23,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +48: [2023-04-29 11:37:23,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +48: [2023-04-29 11:37:23,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +32: [2023-04-29 11:37:23,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +32: [2023-04-29 11:37:23,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +32: [2023-04-29 11:37:23,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +32: [2023-04-29 11:37:23,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +59: [2023-04-29 11:37:23,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +59: [2023-04-29 11:37:23,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +32: [2023-04-29 11:37:23,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +32: [2023-04-29 11:37:23,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +32: [2023-04-29 11:37:23,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +32: [2023-04-29 11:37:23,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +48: [2023-04-29 11:37:23,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +48: [2023-04-29 11:37:23,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +48: [2023-04-29 11:37:23,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +48: [2023-04-29 11:37:23,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +59: [2023-04-29 11:37:23,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +59: [2023-04-29 11:37:23,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +54: [2023-04-29 11:37:23,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +54: [2023-04-29 11:37:23,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +54: [2023-04-29 11:37:23,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +54: [2023-04-29 11:37:23,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +54: [2023-04-29 11:37:23,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +54: [2023-04-29 11:37:23,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +54: [2023-04-29 11:37:23,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +54: [2023-04-29 11:37:23,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +59: [2023-04-29 11:37:23,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +54: [2023-04-29 11:37:23,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +54: [2023-04-29 11:37:23,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +54: [2023-04-29 11:37:23,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +54: [2023-04-29 11:37:23,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +59: [2023-04-29 11:37:23,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +54: [2023-04-29 11:37:23,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +54: [2023-04-29 11:37:23,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +54: [2023-04-29 11:37:23,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +54: [2023-04-29 11:37:23,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +33: [2023-04-29 11:37:23,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +33: [2023-04-29 11:37:23,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +33: [2023-04-29 11:37:23,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +33: [2023-04-29 11:37:23,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +46: [2023-04-29 11:37:23,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +46: [2023-04-29 11:37:23,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +46: [2023-04-29 11:37:23,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +46: [2023-04-29 11:37:23,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +46: [2023-04-29 11:37:23,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +46: [2023-04-29 11:37:23,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +46: [2023-04-29 11:37:23,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +46: [2023-04-29 11:37:23,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +33: [2023-04-29 11:37:23,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +33: [2023-04-29 11:37:23,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +33: [2023-04-29 11:37:23,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +46: [2023-04-29 11:37:23,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +46: [2023-04-29 11:37:23,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +46: [2023-04-29 11:37:23,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +46: [2023-04-29 11:37:23,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +33: [2023-04-29 11:37:23,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +46: [2023-04-29 11:37:23,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +35: [2023-04-29 11:37:23,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +35: [2023-04-29 11:37:23,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +35: [2023-04-29 11:37:23,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +35: [2023-04-29 11:37:23,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +35: [2023-04-29 11:37:23,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +35: [2023-04-29 11:37:23,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +35: [2023-04-29 11:37:23,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +46: [2023-04-29 11:37:23,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +35: [2023-04-29 11:37:23,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +46: [2023-04-29 11:37:23,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +46: [2023-04-29 11:37:23,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +32: [2023-04-29 11:37:23,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +56: [2023-04-29 11:37:23,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +56: [2023-04-29 11:37:23,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +56: [2023-04-29 11:37:23,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +56: [2023-04-29 11:37:23,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +56: [2023-04-29 11:37:23,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +56: [2023-04-29 11:37:23,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +56: [2023-04-29 11:37:23,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +56: [2023-04-29 11:37:23,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +47: [2023-04-29 11:37:23,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +47: [2023-04-29 11:37:23,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +47: [2023-04-29 11:37:23,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +47: [2023-04-29 11:37:23,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +47: [2023-04-29 11:37:23,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +47: [2023-04-29 11:37:23,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +47: [2023-04-29 11:37:23,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +24: [2023-04-29 11:37:23,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +24: [2023-04-29 11:37:23,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +47: [2023-04-29 11:37:23,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +32: [2023-04-29 11:37:23,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +24: [2023-04-29 11:37:23,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +24: [2023-04-29 11:37:23,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +24: [2023-04-29 11:37:23,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +24: [2023-04-29 11:37:23,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +24: [2023-04-29 11:37:23,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +24: [2023-04-29 11:37:23,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +35: [2023-04-29 11:37:23,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +47: [2023-04-29 11:37:23,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +32: [2023-04-29 11:37:23,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +24: [2023-04-29 11:37:23,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +24: [2023-04-29 11:37:23,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +47: [2023-04-29 11:37:23,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +32: [2023-04-29 11:37:23,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +24: [2023-04-29 11:37:23,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +56: [2023-04-29 11:37:23,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +56: [2023-04-29 11:37:23,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +24: [2023-04-29 11:37:23,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +56: [2023-04-29 11:37:23,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +47: [2023-04-29 11:37:23,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +56: [2023-04-29 11:37:23,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +47: [2023-04-29 11:37:23,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +47: [2023-04-29 11:37:23,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +47: [2023-04-29 11:37:23,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... + 2: [2023-04-29 11:37:23,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 2: [2023-04-29 11:37:23,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 2: [2023-04-29 11:37:23,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 2: [2023-04-29 11:37:23,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 2: [2023-04-29 11:37:23,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +47: [2023-04-29 11:37:23,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... + 2: [2023-04-29 11:37:23,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 2: [2023-04-29 11:37:23,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +56: [2023-04-29 11:37:23,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +56: [2023-04-29 11:37:23,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +24: [2023-04-29 11:37:23,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +35: [2023-04-29 11:37:23,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +35: [2023-04-29 11:37:23,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +56: [2023-04-29 11:37:23,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +56: [2023-04-29 11:37:23,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +35: [2023-04-29 11:37:23,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +24: [2023-04-29 11:37:23,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +35: [2023-04-29 11:37:23,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +47: [2023-04-29 11:37:23,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +35: [2023-04-29 11:37:23,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +24: [2023-04-29 11:37:23,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +24: [2023-04-29 11:37:23,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +35: [2023-04-29 11:37:23,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +35: [2023-04-29 11:37:23,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... + 2: [2023-04-29 11:37:23,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 2: [2023-04-29 11:37:23,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 2: [2023-04-29 11:37:23,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 2: [2023-04-29 11:37:23,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 2: [2023-04-29 11:37:23,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +36: [2023-04-29 11:37:23,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +36: [2023-04-29 11:37:23,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +36: [2023-04-29 11:37:23,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +36: [2023-04-29 11:37:23,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +36: [2023-04-29 11:37:23,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +36: [2023-04-29 11:37:23,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +36: [2023-04-29 11:37:23,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +36: [2023-04-29 11:37:23,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. + 2: [2023-04-29 11:37:23,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... + 2: [2023-04-29 11:37:23,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... + 2: [2023-04-29 11:37:23,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... + 2: [2023-04-29 11:37:23,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +54: [2023-04-29 11:37:23,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +32: [2023-04-29 11:37:23,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +32: [2023-04-29 11:37:23,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +36: [2023-04-29 11:37:23,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +36: [2023-04-29 11:37:23,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +36: [2023-04-29 11:37:23,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +36: [2023-04-29 11:37:23,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +54: [2023-04-29 11:37:23,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +36: [2023-04-29 11:37:23,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +36: [2023-04-29 11:37:23,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +36: [2023-04-29 11:37:23,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +32: [2023-04-29 11:37:23,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +36: [2023-04-29 11:37:23,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +32: [2023-04-29 11:37:23,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +54: [2023-04-29 11:37:23,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +54: [2023-04-29 11:37:23,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. + 8: [2023-04-29 11:37:24,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 8: [2023-04-29 11:37:24,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 8: [2023-04-29 11:37:24,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 8: [2023-04-29 11:37:24,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 8: [2023-04-29 11:37:24,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 8: [2023-04-29 11:37:24,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 8: [2023-04-29 11:37:24,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 8: [2023-04-29 11:37:24,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 8: [2023-04-29 11:37:24,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 8: [2023-04-29 11:37:24,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 8: [2023-04-29 11:37:24,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +54: [2023-04-29 11:37:24,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 8: [2023-04-29 11:37:24,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... + 8: [2023-04-29 11:37:24,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +54: [2023-04-29 11:37:24,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 8: [2023-04-29 11:37:24,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... + 8: [2023-04-29 11:37:24,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 8: [2023-04-29 11:37:24,016] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +54: [2023-04-29 11:37:24,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +54: [2023-04-29 11:37:24,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +46: [2023-04-29 11:37:24,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +47: [2023-04-29 11:37:24,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +35: [2023-04-29 11:37:24,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +24: [2023-04-29 11:37:24,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +24: [2023-04-29 11:37:24,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +24: [2023-04-29 11:37:24,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +46: [2023-04-29 11:37:24,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +46: [2023-04-29 11:37:24,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +46: [2023-04-29 11:37:24,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +47: [2023-04-29 11:37:24,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +56: [2023-04-29 11:37:24,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +24: [2023-04-29 11:37:24,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +25: [2023-04-29 11:37:24,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +25: [2023-04-29 11:37:24,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +25: [2023-04-29 11:37:24,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +25: [2023-04-29 11:37:24,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +25: [2023-04-29 11:37:24,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +25: [2023-04-29 11:37:24,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +25: [2023-04-29 11:37:24,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +56: [2023-04-29 11:37:24,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +56: [2023-04-29 11:37:24,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +56: [2023-04-29 11:37:24,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +25: [2023-04-29 11:37:24,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +47: [2023-04-29 11:37:24,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +47: [2023-04-29 11:37:24,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +21: [2023-04-29 11:37:24,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +21: [2023-04-29 11:37:24,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +21: [2023-04-29 11:37:24,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +21: [2023-04-29 11:37:24,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +21: [2023-04-29 11:37:24,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +21: [2023-04-29 11:37:24,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +21: [2023-04-29 11:37:24,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +21: [2023-04-29 11:37:24,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +35: [2023-04-29 11:37:24,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +35: [2023-04-29 11:37:24,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +25: [2023-04-29 11:37:24,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +25: [2023-04-29 11:37:24,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +25: [2023-04-29 11:37:24,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +25: [2023-04-29 11:37:24,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +25: [2023-04-29 11:37:24,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +21: [2023-04-29 11:37:24,052] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +21: [2023-04-29 11:37:24,052] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +21: [2023-04-29 11:37:24,052] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +35: [2023-04-29 11:37:24,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. + 6: [2023-04-29 11:37:24,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 6: [2023-04-29 11:37:24,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +25: [2023-04-29 11:37:24,052] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 6: [2023-04-29 11:37:24,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 6: [2023-04-29 11:37:24,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 6: [2023-04-29 11:37:24,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 6: [2023-04-29 11:37:24,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 6: [2023-04-29 11:37:24,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 6: [2023-04-29 11:37:24,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +47: [2023-04-29 11:37:24,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +25: [2023-04-29 11:37:24,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +25: [2023-04-29 11:37:24,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +36: [2023-04-29 11:37:24,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +36: [2023-04-29 11:37:24,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +21: [2023-04-29 11:37:24,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +21: [2023-04-29 11:37:24,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +21: [2023-04-29 11:37:24,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 2: [2023-04-29 11:37:24,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 2: [2023-04-29 11:37:24,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 2: [2023-04-29 11:37:24,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +46: [2023-04-29 11:37:24,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +21: [2023-04-29 11:37:24,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +21: [2023-04-29 11:37:24,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +24: [2023-04-29 11:37:24,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +47: [2023-04-29 11:37:24,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +35: [2023-04-29 11:37:24,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 2: [2023-04-29 11:37:24,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +24: [2023-04-29 11:37:24,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +24: [2023-04-29 11:37:24,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 6: [2023-04-29 11:37:24,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 6: [2023-04-29 11:37:24,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +24: [2023-04-29 11:37:24,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +20: [2023-04-29 11:37:24,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +20: [2023-04-29 11:37:24,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +20: [2023-04-29 11:37:24,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +20: [2023-04-29 11:37:24,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +20: [2023-04-29 11:37:24,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 6: [2023-04-29 11:37:24,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +20: [2023-04-29 11:37:24,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +20: [2023-04-29 11:37:24,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +14: [2023-04-29 11:37:24,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +14: [2023-04-29 11:37:24,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 6: [2023-04-29 11:37:24,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +20: [2023-04-29 11:37:24,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 6: [2023-04-29 11:37:24,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 5: [2023-04-29 11:37:24,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 5: [2023-04-29 11:37:24,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 5: [2023-04-29 11:37:24,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 5: [2023-04-29 11:37:24,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 5: [2023-04-29 11:37:24,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +14: [2023-04-29 11:37:24,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 5: [2023-04-29 11:37:24,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 5: [2023-04-29 11:37:24,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +14: [2023-04-29 11:37:24,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +14: [2023-04-29 11:37:24,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +14: [2023-04-29 11:37:24,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +14: [2023-04-29 11:37:24,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 3: [2023-04-29 11:37:24,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 3: [2023-04-29 11:37:24,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 3: [2023-04-29 11:37:24,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 3: [2023-04-29 11:37:24,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 5: [2023-04-29 11:37:24,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 3: [2023-04-29 11:37:24,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 3: [2023-04-29 11:37:24,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 3: [2023-04-29 11:37:24,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +14: [2023-04-29 11:37:24,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +47: [2023-04-29 11:37:24,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 3: [2023-04-29 11:37:24,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +47: [2023-04-29 11:37:24,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +29: [2023-04-29 11:37:24,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +29: [2023-04-29 11:37:24,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +29: [2023-04-29 11:37:24,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +29: [2023-04-29 11:37:24,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +29: [2023-04-29 11:37:24,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +29: [2023-04-29 11:37:24,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +29: [2023-04-29 11:37:24,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +29: [2023-04-29 11:37:24,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 6: [2023-04-29 11:37:24,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... + 6: [2023-04-29 11:37:24,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +36: [2023-04-29 11:37:24,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. + 7: [2023-04-29 11:37:24,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +56: [2023-04-29 11:37:24,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +20: [2023-04-29 11:37:24,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +36: [2023-04-29 11:37:24,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. + 6: [2023-04-29 11:37:24,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +15: [2023-04-29 11:37:24,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +15: [2023-04-29 11:37:24,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +15: [2023-04-29 11:37:24,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +15: [2023-04-29 11:37:24,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +15: [2023-04-29 11:37:24,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +46: [2023-04-29 11:37:24,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +15: [2023-04-29 11:37:24,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +15: [2023-04-29 11:37:24,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 8: [2023-04-29 11:37:24,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +56: [2023-04-29 11:37:24,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 7: [2023-04-29 11:37:24,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 3: [2023-04-29 11:37:24,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 7: [2023-04-29 11:37:24,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 7: [2023-04-29 11:37:24,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 7: [2023-04-29 11:37:24,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 5: [2023-04-29 11:37:24,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +56: [2023-04-29 11:37:24,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 3: [2023-04-29 11:37:24,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... + 3: [2023-04-29 11:37:24,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... + 3: [2023-04-29 11:37:24,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +14: [2023-04-29 11:37:24,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... + 3: [2023-04-29 11:37:24,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... + 5: [2023-04-29 11:37:24,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... + 3: [2023-04-29 11:37:24,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +14: [2023-04-29 11:37:24,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +56: [2023-04-29 11:37:24,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 5: [2023-04-29 11:37:24,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... + 5: [2023-04-29 11:37:24,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +30: [2023-04-29 11:37:24,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +30: [2023-04-29 11:37:24,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +46: [2023-04-29 11:37:24,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +46: [2023-04-29 11:37:24,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +30: [2023-04-29 11:37:24,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +30: [2023-04-29 11:37:24,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +30: [2023-04-29 11:37:24,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +30: [2023-04-29 11:37:24,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +30: [2023-04-29 11:37:24,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 3: [2023-04-29 11:37:24,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +30: [2023-04-29 11:37:24,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +14: [2023-04-29 11:37:24,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +15: [2023-04-29 11:37:24,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +20: [2023-04-29 11:37:24,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +20: [2023-04-29 11:37:24,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +20: [2023-04-29 11:37:24,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +14: [2023-04-29 11:37:24,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +29: [2023-04-29 11:37:24,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +29: [2023-04-29 11:37:24,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... + 3: [2023-04-29 11:37:24,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +20: [2023-04-29 11:37:24,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +20: [2023-04-29 11:37:24,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +20: [2023-04-29 11:37:24,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +35: [2023-04-29 11:37:24,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 5: [2023-04-29 11:37:24,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 5: [2023-04-29 11:37:24,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +29: [2023-04-29 11:37:24,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +14: [2023-04-29 11:37:24,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... + 5: [2023-04-29 11:37:24,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 5: [2023-04-29 11:37:24,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +29: [2023-04-29 11:37:24,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +29: [2023-04-29 11:37:24,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... + 8: [2023-04-29 11:37:24,075] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +35: [2023-04-29 11:37:24,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +20: [2023-04-29 11:37:24,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +29: [2023-04-29 11:37:24,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +29: [2023-04-29 11:37:24,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +14: [2023-04-29 11:37:24,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +29: [2023-04-29 11:37:24,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +14: [2023-04-29 11:37:24,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +14: [2023-04-29 11:37:24,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +36: [2023-04-29 11:37:24,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +15: [2023-04-29 11:37:24,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +15: [2023-04-29 11:37:24,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +15: [2023-04-29 11:37:24,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +30: [2023-04-29 11:37:24,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +15: [2023-04-29 11:37:24,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +15: [2023-04-29 11:37:24,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +15: [2023-04-29 11:37:24,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +15: [2023-04-29 11:37:24,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +30: [2023-04-29 11:37:24,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +35: [2023-04-29 11:37:24,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +15: [2023-04-29 11:37:24,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +30: [2023-04-29 11:37:24,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +30: [2023-04-29 11:37:24,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... + 7: [2023-04-29 11:37:24,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +36: [2023-04-29 11:37:24,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +30: [2023-04-29 11:37:24,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +30: [2023-04-29 11:37:24,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +30: [2023-04-29 11:37:24,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +30: [2023-04-29 11:37:24,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 2: [2023-04-29 11:37:24,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 2: [2023-04-29 11:37:24,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... + 8: [2023-04-29 11:37:24,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 8: [2023-04-29 11:37:24,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 2: [2023-04-29 11:37:24,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 2: [2023-04-29 11:37:24,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +36: [2023-04-29 11:37:24,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +36: [2023-04-29 11:37:24,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 8: [2023-04-29 11:37:24,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +51: [2023-04-29 11:37:24,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +51: [2023-04-29 11:37:24,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +51: [2023-04-29 11:37:24,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +51: [2023-04-29 11:37:24,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +51: [2023-04-29 11:37:24,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +51: [2023-04-29 11:37:24,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +51: [2023-04-29 11:37:24,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +51: [2023-04-29 11:37:24,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +12: [2023-04-29 11:37:24,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +12: [2023-04-29 11:37:24,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +12: [2023-04-29 11:37:24,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +12: [2023-04-29 11:37:24,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +12: [2023-04-29 11:37:24,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +12: [2023-04-29 11:37:24,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +12: [2023-04-29 11:37:24,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 8: [2023-04-29 11:37:24,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +12: [2023-04-29 11:37:24,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +51: [2023-04-29 11:37:24,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +51: [2023-04-29 11:37:24,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +42: [2023-04-29 11:37:24,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +42: [2023-04-29 11:37:24,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +12: [2023-04-29 11:37:24,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +50: [2023-04-29 11:37:24,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +50: [2023-04-29 11:37:24,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +50: [2023-04-29 11:37:24,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +50: [2023-04-29 11:37:24,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +50: [2023-04-29 11:37:24,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +50: [2023-04-29 11:37:24,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +50: [2023-04-29 11:37:24,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +50: [2023-04-29 11:37:24,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +12: [2023-04-29 11:37:24,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +42: [2023-04-29 11:37:24,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +51: [2023-04-29 11:37:24,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +42: [2023-04-29 11:37:24,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +42: [2023-04-29 11:37:24,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +42: [2023-04-29 11:37:24,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +42: [2023-04-29 11:37:24,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +12: [2023-04-29 11:37:24,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +42: [2023-04-29 11:37:24,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +51: [2023-04-29 11:37:24,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +12: [2023-04-29 11:37:24,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +51: [2023-04-29 11:37:24,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +51: [2023-04-29 11:37:24,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +51: [2023-04-29 11:37:24,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +51: [2023-04-29 11:37:24,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +12: [2023-04-29 11:37:24,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +12: [2023-04-29 11:37:24,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... + 8: [2023-04-29 11:37:24,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 8: [2023-04-29 11:37:24,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +42: [2023-04-29 11:37:24,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +42: [2023-04-29 11:37:24,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +50: [2023-04-29 11:37:24,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +50: [2023-04-29 11:37:24,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +42: [2023-04-29 11:37:24,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +12: [2023-04-29 11:37:24,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +12: [2023-04-29 11:37:24,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +42: [2023-04-29 11:37:24,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +50: [2023-04-29 11:37:24,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +25: [2023-04-29 11:37:24,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +21: [2023-04-29 11:37:24,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +42: [2023-04-29 11:37:24,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +25: [2023-04-29 11:37:24,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +42: [2023-04-29 11:37:24,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +42: [2023-04-29 11:37:24,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +42: [2023-04-29 11:37:24,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +50: [2023-04-29 11:37:24,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +50: [2023-04-29 11:37:24,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +50: [2023-04-29 11:37:24,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +50: [2023-04-29 11:37:24,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +50: [2023-04-29 11:37:24,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +16: [2023-04-29 11:37:24,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +16: [2023-04-29 11:37:24,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +11: [2023-04-29 11:37:24,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +11: [2023-04-29 11:37:24,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +11: [2023-04-29 11:37:24,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +11: [2023-04-29 11:37:24,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +11: [2023-04-29 11:37:24,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +11: [2023-04-29 11:37:24,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +11: [2023-04-29 11:37:24,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +16: [2023-04-29 11:37:24,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +16: [2023-04-29 11:37:24,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +16: [2023-04-29 11:37:24,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +16: [2023-04-29 11:37:24,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +16: [2023-04-29 11:37:24,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +11: [2023-04-29 11:37:24,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +25: [2023-04-29 11:37:24,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +16: [2023-04-29 11:37:24,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +23: [2023-04-29 11:37:24,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +23: [2023-04-29 11:37:24,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +23: [2023-04-29 11:37:24,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +23: [2023-04-29 11:37:24,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +23: [2023-04-29 11:37:24,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +23: [2023-04-29 11:37:24,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +23: [2023-04-29 11:37:24,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +23: [2023-04-29 11:37:24,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +60: [2023-04-29 11:37:24,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +60: [2023-04-29 11:37:24,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +60: [2023-04-29 11:37:24,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +60: [2023-04-29 11:37:24,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +60: [2023-04-29 11:37:24,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +60: [2023-04-29 11:37:24,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +60: [2023-04-29 11:37:24,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +60: [2023-04-29 11:37:24,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +25: [2023-04-29 11:37:24,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +21: [2023-04-29 11:37:24,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +21: [2023-04-29 11:37:24,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +21: [2023-04-29 11:37:24,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +27: [2023-04-29 11:37:24,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +27: [2023-04-29 11:37:24,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +27: [2023-04-29 11:37:24,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +27: [2023-04-29 11:37:24,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +27: [2023-04-29 11:37:24,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +27: [2023-04-29 11:37:24,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +27: [2023-04-29 11:37:24,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +27: [2023-04-29 11:37:24,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +16: [2023-04-29 11:37:24,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +16: [2023-04-29 11:37:24,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +23: [2023-04-29 11:37:24,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +23: [2023-04-29 11:37:24,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 6: [2023-04-29 11:37:24,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 6: [2023-04-29 11:37:24,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +23: [2023-04-29 11:37:24,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +23: [2023-04-29 11:37:24,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +60: [2023-04-29 11:37:24,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +60: [2023-04-29 11:37:24,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +60: [2023-04-29 11:37:24,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... + 3: [2023-04-29 11:37:24,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +23: [2023-04-29 11:37:24,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +11: [2023-04-29 11:37:24,133] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +11: [2023-04-29 11:37:24,133] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +11: [2023-04-29 11:37:24,133] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +60: [2023-04-29 11:37:24,133] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +23: [2023-04-29 11:37:24,133] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +20: [2023-04-29 11:37:24,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +60: [2023-04-29 11:37:24,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +23: [2023-04-29 11:37:24,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +38: [2023-04-29 11:37:24,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +44: [2023-04-29 11:37:24,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +44: [2023-04-29 11:37:24,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +44: [2023-04-29 11:37:24,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +44: [2023-04-29 11:37:24,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +44: [2023-04-29 11:37:24,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +44: [2023-04-29 11:37:24,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +44: [2023-04-29 11:37:24,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +38: [2023-04-29 11:37:24,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +38: [2023-04-29 11:37:24,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +38: [2023-04-29 11:37:24,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +38: [2023-04-29 11:37:24,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +60: [2023-04-29 11:37:24,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +38: [2023-04-29 11:37:24,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +38: [2023-04-29 11:37:24,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +44: [2023-04-29 11:37:24,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +38: [2023-04-29 11:37:24,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. + 6: [2023-04-29 11:37:24,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 6: [2023-04-29 11:37:24,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +11: [2023-04-29 11:37:24,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +27: [2023-04-29 11:37:24,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +60: [2023-04-29 11:37:24,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +60: [2023-04-29 11:37:24,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +11: [2023-04-29 11:37:24,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +28: [2023-04-29 11:37:24,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +28: [2023-04-29 11:37:24,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +23: [2023-04-29 11:37:24,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +11: [2023-04-29 11:37:24,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +29: [2023-04-29 11:37:24,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +11: [2023-04-29 11:37:24,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +28: [2023-04-29 11:37:24,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +28: [2023-04-29 11:37:24,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +28: [2023-04-29 11:37:24,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +28: [2023-04-29 11:37:24,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +28: [2023-04-29 11:37:24,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +11: [2023-04-29 11:37:24,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +27: [2023-04-29 11:37:24,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +27: [2023-04-29 11:37:24,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +27: [2023-04-29 11:37:24,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +28: [2023-04-29 11:37:24,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +27: [2023-04-29 11:37:24,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +27: [2023-04-29 11:37:24,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... + 0: [2023-04-29 11:37:24,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 0: [2023-04-29 11:37:24,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 0: [2023-04-29 11:37:24,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 0: [2023-04-29 11:37:24,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +27: [2023-04-29 11:37:24,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 0: [2023-04-29 11:37:24,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 0: [2023-04-29 11:37:24,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 0: [2023-04-29 11:37:24,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +39: [2023-04-29 11:37:24,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +27: [2023-04-29 11:37:24,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... + 0: [2023-04-29 11:37:24,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +39: [2023-04-29 11:37:24,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +39: [2023-04-29 11:37:24,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +39: [2023-04-29 11:37:24,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +39: [2023-04-29 11:37:24,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +39: [2023-04-29 11:37:24,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +39: [2023-04-29 11:37:24,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. + 3: [2023-04-29 11:37:24,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +39: [2023-04-29 11:37:24,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +61: [2023-04-29 11:37:24,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +61: [2023-04-29 11:37:24,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +21: [2023-04-29 11:37:24,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +45: [2023-04-29 11:37:24,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +45: [2023-04-29 11:37:24,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +45: [2023-04-29 11:37:24,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +45: [2023-04-29 11:37:24,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +45: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +45: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +61: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +41: [2023-04-29 11:37:24,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +41: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +41: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +45: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +62: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +62: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +62: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +41: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +34: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +34: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +41: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +61: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +61: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +61: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +61: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +41: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +41: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +45: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +61: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +41: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +40: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +40: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +40: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +62: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +62: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +62: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +62: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +62: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +40: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +40: [2023-04-29 11:37:24,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +40: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +40: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +37: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +40: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +31: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +31: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +16: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +16: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +38: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +16: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +57: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +57: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +37: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +31: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +31: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +31: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +31: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +31: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +57: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +57: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +10: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +10: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +10: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +10: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +10: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +44: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +43: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +10: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +10: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +57: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +57: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +43: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +10: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 1: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 1: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +52: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +52: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +52: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +52: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +52: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +14: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +57: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +43: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +31: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +16: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +52: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +52: [2023-04-29 11:37:24,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +25: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +43: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +43: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +16: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +43: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +44: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +52: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +43: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +57: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +44: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +44: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +43: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. + 1: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 1: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +37: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. + 1: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 1: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +30: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 1: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +37: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +37: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +37: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +37: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +16: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 1: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +44: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +44: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +37: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +55: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +55: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +55: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +55: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +55: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +55: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +55: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +34: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +34: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +34: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +34: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +34: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +44: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +63: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +63: [2023-04-29 11:37:24,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +63: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +63: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +55: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +63: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +63: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. + 9: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 9: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +63: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +34: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +26: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +26: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +26: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +26: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +26: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +63: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +44: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... + 9: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 9: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 9: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 9: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 9: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +26: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +26: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +13: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +13: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +13: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +13: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +13: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +38: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +13: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +13: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +13: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +38: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +38: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... + 9: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +19: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +19: [2023-04-29 11:37:24,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +22: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +22: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +26: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +19: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +19: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +19: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +19: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +19: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +39: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +49: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +49: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +49: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +19: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 7: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +22: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +22: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +22: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +22: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +22: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +49: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +49: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +49: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +49: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. + 4: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 4: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 4: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 4: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 4: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 4: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 4: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 3: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 3: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 4: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +49: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +22: [2023-04-29 11:37:24,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +25: [2023-04-29 11:37:24,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +28: [2023-04-29 11:37:24,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +28: [2023-04-29 11:37:24,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +28: [2023-04-29 11:37:24,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +28: [2023-04-29 11:37:24,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +28: [2023-04-29 11:37:24,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +28: [2023-04-29 11:37:24,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +38: [2023-04-29 11:37:24,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +28: [2023-04-29 11:37:24,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +38: [2023-04-29 11:37:24,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +40: [2023-04-29 11:37:24,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +38: [2023-04-29 11:37:24,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +15: [2023-04-29 11:37:24,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +15: [2023-04-29 11:37:24,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +15: [2023-04-29 11:37:24,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 0: [2023-04-29 11:37:24,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +40: [2023-04-29 11:37:24,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +40: [2023-04-29 11:37:24,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +38: [2023-04-29 11:37:24,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +52: [2023-04-29 11:37:24,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... + 0: [2023-04-29 11:37:24,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 0: [2023-04-29 11:37:24,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +37: [2023-04-29 11:37:24,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +45: [2023-04-29 11:37:24,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +39: [2023-04-29 11:37:24,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +28: [2023-04-29 11:37:24,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 0: [2023-04-29 11:37:24,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... + 0: [2023-04-29 11:37:24,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +45: [2023-04-29 11:37:24,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... + 0: [2023-04-29 11:37:24,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +29: [2023-04-29 11:37:24,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +29: [2023-04-29 11:37:24,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +29: [2023-04-29 11:37:24,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 0: [2023-04-29 11:37:24,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +37: [2023-04-29 11:37:24,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +20: [2023-04-29 11:37:24,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +20: [2023-04-29 11:37:24,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +45: [2023-04-29 11:37:24,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +45: [2023-04-29 11:37:24,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +52: [2023-04-29 11:37:24,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +15: [2023-04-29 11:37:24,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +41: [2023-04-29 11:37:24,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... + 0: [2023-04-29 11:37:24,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +43: [2023-04-29 11:37:24,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +57: [2023-04-29 11:37:24,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +57: [2023-04-29 11:37:24,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +57: [2023-04-29 11:37:24,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +10: [2023-04-29 11:37:24,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +61: [2023-04-29 11:37:24,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +52: [2023-04-29 11:37:24,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +61: [2023-04-29 11:37:24,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +61: [2023-04-29 11:37:24,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +61: [2023-04-29 11:37:24,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +57: [2023-04-29 11:37:24,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +41: [2023-04-29 11:37:24,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +41: [2023-04-29 11:37:24,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +52: [2023-04-29 11:37:24,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +39: [2023-04-29 11:37:24,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... + 1: [2023-04-29 11:37:24,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +61: [2023-04-29 11:37:24,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +62: [2023-04-29 11:37:24,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... + 1: [2023-04-29 11:37:24,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +57: [2023-04-29 11:37:24,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +40: [2023-04-29 11:37:24,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +39: [2023-04-29 11:37:24,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +43: [2023-04-29 11:37:24,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +39: [2023-04-29 11:37:24,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +45: [2023-04-29 11:37:24,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +39: [2023-04-29 11:37:24,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +39: [2023-04-29 11:37:24,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +62: [2023-04-29 11:37:24,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +43: [2023-04-29 11:37:24,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +40: [2023-04-29 11:37:24,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +17: [2023-04-29 11:37:24,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +17: [2023-04-29 11:37:24,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +17: [2023-04-29 11:37:24,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +17: [2023-04-29 11:37:24,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +17: [2023-04-29 11:37:24,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +17: [2023-04-29 11:37:24,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +17: [2023-04-29 11:37:24,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +45: [2023-04-29 11:37:24,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +57: [2023-04-29 11:37:24,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +17: [2023-04-29 11:37:24,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 5: [2023-04-29 11:37:24,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +10: [2023-04-29 11:37:24,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +45: [2023-04-29 11:37:24,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +43: [2023-04-29 11:37:24,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +43: [2023-04-29 11:37:24,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +19: [2023-04-29 11:37:24,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +19: [2023-04-29 11:37:24,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +10: [2023-04-29 11:37:24,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +40: [2023-04-29 11:37:24,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +26: [2023-04-29 11:37:24,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +39: [2023-04-29 11:37:24,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +55: [2023-04-29 11:37:24,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +26: [2023-04-29 11:37:24,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +10: [2023-04-29 11:37:24,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +45: [2023-04-29 11:37:24,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +57: [2023-04-29 11:37:24,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +57: [2023-04-29 11:37:24,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +43: [2023-04-29 11:37:24,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +10: [2023-04-29 11:37:24,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +63: [2023-04-29 11:37:24,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +40: [2023-04-29 11:37:24,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... + 1: [2023-04-29 11:37:24,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +40: [2023-04-29 11:37:24,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +22: [2023-04-29 11:37:24,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +13: [2023-04-29 11:37:24,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +10: [2023-04-29 11:37:24,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... + 1: [2023-04-29 11:37:24,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 1: [2023-04-29 11:37:24,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +21: [2023-04-29 11:37:24,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +13: [2023-04-29 11:37:24,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +31: [2023-04-29 11:37:24,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +31: [2023-04-29 11:37:24,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +31: [2023-04-29 11:37:24,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +10: [2023-04-29 11:37:24,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... + 9: [2023-04-29 11:37:24,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +14: [2023-04-29 11:37:24,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +10: [2023-04-29 11:37:24,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +43: [2023-04-29 11:37:24,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +13: [2023-04-29 11:37:24,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +63: [2023-04-29 11:37:24,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +31: [2023-04-29 11:37:24,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +22: [2023-04-29 11:37:24,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +31: [2023-04-29 11:37:24,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +34: [2023-04-29 11:37:24,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +34: [2023-04-29 11:37:24,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... + 4: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 9: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... + 9: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... + 9: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... + 9: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +43: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... + 1: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +52: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +25: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 4: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... + 4: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +63: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +63: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +26: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +52: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... + 9: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +34: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... + 1: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +31: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... + 5: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 5: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 5: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +22: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +22: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +61: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +61: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +63: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +22: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +34: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +34: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... + 1: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +31: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +26: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +19: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +26: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +49: [2023-04-29 11:37:24,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +63: [2023-04-29 11:37:24,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +22: [2023-04-29 11:37:24,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +34: [2023-04-29 11:37:24,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... + 9: [2023-04-29 11:37:24,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +26: [2023-04-29 11:37:24,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +26: [2023-04-29 11:37:24,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +61: [2023-04-29 11:37:24,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +63: [2023-04-29 11:37:24,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +22: [2023-04-29 11:37:24,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +21: [2023-04-29 11:37:24,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +49: [2023-04-29 11:37:24,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +49: [2023-04-29 11:37:24,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +26: [2023-04-29 11:37:24,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +52: [2023-04-29 11:37:24,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +19: [2023-04-29 11:37:24,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +21: [2023-04-29 11:37:24,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +52: [2023-04-29 11:37:24,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +55: [2023-04-29 11:37:24,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +31: [2023-04-29 11:37:24,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +63: [2023-04-29 11:37:24,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +41: [2023-04-29 11:37:24,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +55: [2023-04-29 11:37:24,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +55: [2023-04-29 11:37:24,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +37: [2023-04-29 11:37:24,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +55: [2023-04-29 11:37:24,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +20: [2023-04-29 11:37:24,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +41: [2023-04-29 11:37:24,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +30: [2023-04-29 11:37:24,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +30: [2023-04-29 11:37:24,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +37: [2023-04-29 11:37:24,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +22: [2023-04-29 11:37:24,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +17: [2023-04-29 11:37:24,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +41: [2023-04-29 11:37:24,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +37: [2023-04-29 11:37:24,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... + 9: [2023-04-29 11:37:24,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +55: [2023-04-29 11:37:24,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +30: [2023-04-29 11:37:24,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +37: [2023-04-29 11:37:24,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +41: [2023-04-29 11:37:24,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +37: [2023-04-29 11:37:24,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +13: [2023-04-29 11:37:24,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +41: [2023-04-29 11:37:24,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +55: [2023-04-29 11:37:24,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +37: [2023-04-29 11:37:24,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +62: [2023-04-29 11:37:24,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +19: [2023-04-29 11:37:24,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +49: [2023-04-29 11:37:24,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +49: [2023-04-29 11:37:24,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +14: [2023-04-29 11:37:24,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +62: [2023-04-29 11:37:24,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +19: [2023-04-29 11:37:24,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +13: [2023-04-29 11:37:24,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +19: [2023-04-29 11:37:24,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +62: [2023-04-29 11:37:24,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +13: [2023-04-29 11:37:24,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +62: [2023-04-29 11:37:24,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +49: [2023-04-29 11:37:24,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +14: [2023-04-29 11:37:24,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 4: [2023-04-29 11:37:24,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 4: [2023-04-29 11:37:24,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +19: [2023-04-29 11:37:24,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +13: [2023-04-29 11:37:24,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +49: [2023-04-29 11:37:24,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... + 4: [2023-04-29 11:37:24,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +17: [2023-04-29 11:37:24,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +62: [2023-04-29 11:37:24,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... + 4: [2023-04-29 11:37:24,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +13: [2023-04-29 11:37:24,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +49: [2023-04-29 11:37:24,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +17: [2023-04-29 11:37:24,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +62: [2023-04-29 11:37:24,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +25: [2023-04-29 11:37:24,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +34: [2023-04-29 11:37:24,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +34: [2023-04-29 11:37:24,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +17: [2023-04-29 11:37:24,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 4: [2023-04-29 11:37:24,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +17: [2023-04-29 11:37:24,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +17: [2023-04-29 11:37:24,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +55: [2023-04-29 11:37:24,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +20: [2023-04-29 11:37:24,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 3: [2023-04-29 11:37:24,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +17: [2023-04-29 11:37:24,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +17: [2023-04-29 11:37:24,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... + 7: [2023-04-29 11:37:24,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 7: [2023-04-29 11:37:24,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +29: [2023-04-29 11:37:24,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 3: [2023-04-29 11:37:24,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 6: [2023-04-29 11:37:24,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 6: [2023-04-29 11:37:24,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 6: [2023-04-29 11:37:24,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 6: [2023-04-29 11:37:24,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +14: [2023-04-29 11:37:24,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +30: [2023-04-29 11:37:24,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +58: [2023-04-29 11:37:24,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +58: [2023-04-29 11:37:24,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +58: [2023-04-29 11:37:24,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +58: [2023-04-29 11:37:24,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +58: [2023-04-29 11:37:24,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +58: [2023-04-29 11:37:24,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +58: [2023-04-29 11:37:24,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +58: [2023-04-29 11:37:24,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. + 3: [2023-04-29 11:37:24,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 3: [2023-04-29 11:37:24,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +15: [2023-04-29 11:37:24,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +15: [2023-04-29 11:37:24,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +29: [2023-04-29 11:37:24,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +12: [2023-04-29 11:37:24,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +15: [2023-04-29 11:37:24,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +29: [2023-04-29 11:37:24,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +29: [2023-04-29 11:37:24,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +15: [2023-04-29 11:37:24,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +12: [2023-04-29 11:37:24,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +50: [2023-04-29 11:37:24,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +20: [2023-04-29 11:37:24,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +58: [2023-04-29 11:37:24,175] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +58: [2023-04-29 11:37:24,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... + 5: [2023-04-29 11:37:24,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 5: [2023-04-29 11:37:24,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +20: [2023-04-29 11:37:24,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +58: [2023-04-29 11:37:24,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +58: [2023-04-29 11:37:24,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +12: [2023-04-29 11:37:24,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +12: [2023-04-29 11:37:24,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +58: [2023-04-29 11:37:24,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +58: [2023-04-29 11:37:24,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +58: [2023-04-29 11:37:24,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +58: [2023-04-29 11:37:24,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +42: [2023-04-29 11:37:24,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +42: [2023-04-29 11:37:24,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +42: [2023-04-29 11:37:24,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +51: [2023-04-29 11:37:24,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. + 5: [2023-04-29 11:37:24,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 5: [2023-04-29 11:37:24,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +14: [2023-04-29 11:37:24,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +20: [2023-04-29 11:37:24,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +30: [2023-04-29 11:37:24,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +30: [2023-04-29 11:37:24,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +42: [2023-04-29 11:37:24,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +14: [2023-04-29 11:37:24,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +14: [2023-04-29 11:37:24,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +51: [2023-04-29 11:37:24,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +51: [2023-04-29 11:37:24,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +51: [2023-04-29 11:37:24,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +50: [2023-04-29 11:37:24,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +30: [2023-04-29 11:37:24,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +23: [2023-04-29 11:37:24,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +50: [2023-04-29 11:37:24,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +50: [2023-04-29 11:37:24,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +12: [2023-04-29 11:37:24,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +23: [2023-04-29 11:37:24,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +11: [2023-04-29 11:37:24,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +50: [2023-04-29 11:37:24,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +60: [2023-04-29 11:37:24,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +60: [2023-04-29 11:37:24,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +53: [2023-04-29 11:37:24,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +53: [2023-04-29 11:37:24,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +12: [2023-04-29 11:37:24,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +27: [2023-04-29 11:37:24,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +23: [2023-04-29 11:37:24,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +23: [2023-04-29 11:37:24,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +12: [2023-04-29 11:37:24,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +12: [2023-04-29 11:37:24,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +44: [2023-04-29 11:37:24,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +53: [2023-04-29 11:37:24,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +53: [2023-04-29 11:37:24,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +53: [2023-04-29 11:37:24,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +53: [2023-04-29 11:37:24,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +53: [2023-04-29 11:37:24,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +38: [2023-04-29 11:37:24,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +42: [2023-04-29 11:37:24,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +53: [2023-04-29 11:37:24,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +39: [2023-04-29 11:37:24,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +42: [2023-04-29 11:37:24,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +42: [2023-04-29 11:37:24,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +41: [2023-04-29 11:37:24,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +37: [2023-04-29 11:37:24,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +11: [2023-04-29 11:37:24,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +11: [2023-04-29 11:37:24,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +51: [2023-04-29 11:37:24,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +52: [2023-04-29 11:37:24,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +40: [2023-04-29 11:37:24,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +43: [2023-04-29 11:37:24,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +45: [2023-04-29 11:37:24,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +42: [2023-04-29 11:37:24,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +61: [2023-04-29 11:37:24,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +60: [2023-04-29 11:37:24,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +60: [2023-04-29 11:37:24,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +53: [2023-04-29 11:37:24,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +44: [2023-04-29 11:37:24,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +53: [2023-04-29 11:37:24,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +53: [2023-04-29 11:37:24,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +61: [2023-04-29 11:37:24,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +53: [2023-04-29 11:37:24,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +11: [2023-04-29 11:37:24,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +27: [2023-04-29 11:37:24,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +27: [2023-04-29 11:37:24,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +57: [2023-04-29 11:37:24,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +57: [2023-04-29 11:37:24,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +63: [2023-04-29 11:37:24,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +55: [2023-04-29 11:37:24,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +27: [2023-04-29 11:37:24,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 1: [2023-04-29 11:37:24,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +53: [2023-04-29 11:37:24,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt... +28: [2023-04-29 11:37:24,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +28: [2023-04-29 11:37:24,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +53: [2023-04-29 11:37:24,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +63: [2023-04-29 11:37:24,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +53: [2023-04-29 11:37:24,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +53: [2023-04-29 11:37:24,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt... +45: [2023-04-29 11:37:24,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +44: [2023-04-29 11:37:24,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +57: [2023-04-29 11:37:24,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +57: [2023-04-29 11:37:24,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +44: [2023-04-29 11:37:24,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. + 4: [2023-04-29 11:37:24,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +62: [2023-04-29 11:37:24,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +62: [2023-04-29 11:37:24,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. + 9: [2023-04-29 11:37:24,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +52: [2023-04-29 11:37:24,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +52: [2023-04-29 11:37:24,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +16: [2023-04-29 11:37:24,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +16: [2023-04-29 11:37:24,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +16: [2023-04-29 11:37:24,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +34: [2023-04-29 11:37:24,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +34: [2023-04-29 11:37:24,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +39: [2023-04-29 11:37:24,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +39: [2023-04-29 11:37:24,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +39: [2023-04-29 11:37:24,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. + 0: [2023-04-29 11:37:24,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +38: [2023-04-29 11:37:24,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +38: [2023-04-29 11:37:24,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +38: [2023-04-29 11:37:24,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +26: [2023-04-29 11:37:24,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +51: [2023-04-29 11:37:24,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +49: [2023-04-29 11:37:24,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +19: [2023-04-29 11:37:24,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +19: [2023-04-29 11:37:24,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +43: [2023-04-29 11:37:24,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +52: [2023-04-29 11:37:24,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +13: [2023-04-29 11:37:24,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +13: [2023-04-29 11:37:24,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +45: [2023-04-29 11:37:24,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +45: [2023-04-29 11:37:24,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +43: [2023-04-29 11:37:24,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +43: [2023-04-29 11:37:24,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +10: [2023-04-29 11:37:24,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +63: [2023-04-29 11:37:24,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +63: [2023-04-29 11:37:24,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +61: [2023-04-29 11:37:24,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. + 1: [2023-04-29 11:37:24,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +55: [2023-04-29 11:37:24,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +55: [2023-04-29 11:37:24,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +51: [2023-04-29 11:37:24,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +51: [2023-04-29 11:37:24,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +10: [2023-04-29 11:37:24,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +10: [2023-04-29 11:37:24,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +10: [2023-04-29 11:37:24,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +23: [2023-04-29 11:37:24,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +31: [2023-04-29 11:37:24,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +31: [2023-04-29 11:37:24,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +31: [2023-04-29 11:37:24,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +34: [2023-04-29 11:37:24,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. + 0: [2023-04-29 11:37:24,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +40: [2023-04-29 11:37:24,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +40: [2023-04-29 11:37:24,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +40: [2023-04-29 11:37:24,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +23: [2023-04-29 11:37:24,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +60: [2023-04-29 11:37:24,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +60: [2023-04-29 11:37:24,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +26: [2023-04-29 11:37:24,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +22: [2023-04-29 11:37:24,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +22: [2023-04-29 11:37:24,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +22: [2023-04-29 11:37:24,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +16: [2023-04-29 11:37:24,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +62: [2023-04-29 11:37:24,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +62: [2023-04-29 11:37:24,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +50: [2023-04-29 11:37:24,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +31: [2023-04-29 11:37:24,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +61: [2023-04-29 11:37:24,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +19: [2023-04-29 11:37:24,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +50: [2023-04-29 11:37:24,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +19: [2023-04-29 11:37:24,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 0: [2023-04-29 11:37:24,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 0: [2023-04-29 11:37:24,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +26: [2023-04-29 11:37:24,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +26: [2023-04-29 11:37:24,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +28: [2023-04-29 11:37:24,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +22: [2023-04-29 11:37:24,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +28: [2023-04-29 11:37:24,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +37: [2023-04-29 11:37:24,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +37: [2023-04-29 11:37:24,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +37: [2023-04-29 11:37:24,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +13: [2023-04-29 11:37:24,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +13: [2023-04-29 11:37:24,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +18: [2023-04-29 11:37:24,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +18: [2023-04-29 11:37:24,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +18: [2023-04-29 11:37:24,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +18: [2023-04-29 11:37:24,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +18: [2023-04-29 11:37:24,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +18: [2023-04-29 11:37:24,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +18: [2023-04-29 11:37:24,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 9: [2023-04-29 11:37:24,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 9: [2023-04-29 11:37:24,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +38: [2023-04-29 11:37:24,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +11: [2023-04-29 11:37:24,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +34: [2023-04-29 11:37:24,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +41: [2023-04-29 11:37:24,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +41: [2023-04-29 11:37:24,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +39: [2023-04-29 11:37:24,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +55: [2023-04-29 11:37:24,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +41: [2023-04-29 11:37:24,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +50: [2023-04-29 11:37:24,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +17: [2023-04-29 11:37:24,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +17: [2023-04-29 11:37:24,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +17: [2023-04-29 11:37:24,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 1: [2023-04-29 11:37:24,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +23: [2023-04-29 11:37:24,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +23: [2023-04-29 11:37:24,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +44: [2023-04-29 11:37:24,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +49: [2023-04-29 11:37:24,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +49: [2023-04-29 11:37:24,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +49: [2023-04-29 11:37:24,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. + 1: [2023-04-29 11:37:24,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +27: [2023-04-29 11:37:24,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 9: [2023-04-29 11:37:24,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 4: [2023-04-29 11:37:24,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 4: [2023-04-29 11:37:24,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. + 4: [2023-04-29 11:37:24,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +17: [2023-04-29 11:37:24,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +52: [2023-04-29 11:37:24,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +37: [2023-04-29 11:37:24,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +18: [2023-04-29 11:37:24,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +18: [2023-04-29 11:37:24,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +40: [2023-04-29 11:37:24,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +45: [2023-04-29 11:37:24,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 1: [2023-04-29 11:37:24,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +60: [2023-04-29 11:37:24,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +60: [2023-04-29 11:37:24,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +11: [2023-04-29 11:37:24,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +63: [2023-04-29 11:37:24,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +41: [2023-04-29 11:37:24,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 9: [2023-04-29 11:37:24,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +57: [2023-04-29 11:37:24,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +57: [2023-04-29 11:37:24,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +44: [2023-04-29 11:37:24,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +57: [2023-04-29 11:37:24,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +18: [2023-04-29 11:37:24,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +57: [2023-04-29 11:37:24,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 4: [2023-04-29 11:37:24,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +55: [2023-04-29 11:37:24,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +52: [2023-04-29 11:37:24,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +11: [2023-04-29 11:37:24,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +63: [2023-04-29 11:37:24,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +39: [2023-04-29 11:37:24,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +52: [2023-04-29 11:37:24,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +44: [2023-04-29 11:37:24,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +18: [2023-04-29 11:37:24,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +61: [2023-04-29 11:37:24,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +18: [2023-04-29 11:37:24,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt... +39: [2023-04-29 11:37:24,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +39: [2023-04-29 11:37:24,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +44: [2023-04-29 11:37:24,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +43: [2023-04-29 11:37:24,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 0: [2023-04-29 11:37:24,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +34: [2023-04-29 11:37:24,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +38: [2023-04-29 11:37:24,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +26: [2023-04-29 11:37:24,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +28: [2023-04-29 11:37:24,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +28: [2023-04-29 11:37:24,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +32: [2023-04-29 11:37:24,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +52: [2023-04-29 11:37:24,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +27: [2023-04-29 11:37:24,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +27: [2023-04-29 11:37:24,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +19: [2023-04-29 11:37:24,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +19: [2023-04-29 11:37:24,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +34: [2023-04-29 11:37:24,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +62: [2023-04-29 11:37:24,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +62: [2023-04-29 11:37:24,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +32: [2023-04-29 11:37:24,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +32: [2023-04-29 11:37:24,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +32: [2023-04-29 11:37:24,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +61: [2023-04-29 11:37:24,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 1: [2023-04-29 11:37:24,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +43: [2023-04-29 11:37:24,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +18: [2023-04-29 11:37:24,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +18: [2023-04-29 11:37:24,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +18: [2023-04-29 11:37:24,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +18: [2023-04-29 11:37:24,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt... +45: [2023-04-29 11:37:24,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +16: [2023-04-29 11:37:24,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +55: [2023-04-29 11:37:24,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +55: [2023-04-29 11:37:24,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +58: [2023-04-29 11:37:24,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +58: [2023-04-29 11:37:24,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +10: [2023-04-29 11:37:24,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +27: [2023-04-29 11:37:24,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +49: [2023-04-29 11:37:24,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +10: [2023-04-29 11:37:24,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +63: [2023-04-29 11:37:24,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +63: [2023-04-29 11:37:24,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +16: [2023-04-29 11:37:24,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +16: [2023-04-29 11:37:24,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +38: [2023-04-29 11:37:24,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +10: [2023-04-29 11:37:24,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +38: [2023-04-29 11:37:24,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +45: [2023-04-29 11:37:24,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +10: [2023-04-29 11:37:24,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +11: [2023-04-29 11:37:24,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +13: [2023-04-29 11:37:24,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +45: [2023-04-29 11:37:24,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +43: [2023-04-29 11:37:24,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +43: [2023-04-29 11:37:24,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +40: [2023-04-29 11:37:24,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +40: [2023-04-29 11:37:24,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +34: [2023-04-29 11:37:24,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +19: [2023-04-29 11:37:24,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +19: [2023-04-29 11:37:24,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +13: [2023-04-29 11:37:24,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +37: [2023-04-29 11:37:24,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +58: [2023-04-29 11:37:24,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +58: [2023-04-29 11:37:24,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +22: [2023-04-29 11:37:24,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +61: [2023-04-29 11:37:24,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +62: [2023-04-29 11:37:24,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +37: [2023-04-29 11:37:24,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +37: [2023-04-29 11:37:24,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +40: [2023-04-29 11:37:24,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +62: [2023-04-29 11:37:24,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 0: [2023-04-29 11:37:24,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +16: [2023-04-29 11:37:24,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +26: [2023-04-29 11:37:24,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 0: [2023-04-29 11:37:24,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +22: [2023-04-29 11:37:24,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 1: [2023-04-29 11:37:24,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 9: [2023-04-29 11:37:24,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +59: [2023-04-29 11:37:24,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +59: [2023-04-29 11:37:24,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +59: [2023-04-29 11:37:24,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +59: [2023-04-29 11:37:24,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +13: [2023-04-29 11:37:24,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 1: [2023-04-29 11:37:24,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +22: [2023-04-29 11:37:24,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +22: [2023-04-29 11:37:24,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +26: [2023-04-29 11:37:24,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +26: [2023-04-29 11:37:24,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 9: [2023-04-29 11:37:24,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 0: [2023-04-29 11:37:24,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +61: [2023-04-29 11:37:24,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +49: [2023-04-29 11:37:24,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +13: [2023-04-29 11:37:24,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +17: [2023-04-29 11:37:24,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +49: [2023-04-29 11:37:24,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +49: [2023-04-29 11:37:24,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +17: [2023-04-29 11:37:24,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +34: [2023-04-29 11:37:24,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +55: [2023-04-29 11:37:24,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 4: [2023-04-29 11:37:24,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +17: [2023-04-29 11:37:24,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +31: [2023-04-29 11:37:24,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 9: [2023-04-29 11:37:24,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +17: [2023-04-29 11:37:24,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +33: [2023-04-29 11:37:24,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +33: [2023-04-29 11:37:24,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +33: [2023-04-29 11:37:24,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +33: [2023-04-29 11:37:24,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. + 4: [2023-04-29 11:37:24,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 4: [2023-04-29 11:37:24,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +31: [2023-04-29 11:37:24,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +41: [2023-04-29 11:37:24,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +31: [2023-04-29 11:37:24,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +28: [2023-04-29 11:37:24,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +48: [2023-04-29 11:37:24,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +48: [2023-04-29 11:37:24,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +48: [2023-04-29 11:37:24,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +48: [2023-04-29 11:37:24,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +28: [2023-04-29 11:37:24,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +41: [2023-04-29 11:37:24,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +31: [2023-04-29 11:37:24,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +41: [2023-04-29 11:37:24,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +32: [2023-04-29 11:37:24,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +32: [2023-04-29 11:37:24,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +32: [2023-04-29 11:37:24,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +32: [2023-04-29 11:37:24,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +58: [2023-04-29 11:37:24,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +58: [2023-04-29 11:37:24,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +53: [2023-04-29 11:37:24,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +58: [2023-04-29 11:37:24,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +58: [2023-04-29 11:37:24,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +59: [2023-04-29 11:37:24,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +59: [2023-04-29 11:37:24,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +59: [2023-04-29 11:37:24,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +59: [2023-04-29 11:37:24,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +48: [2023-04-29 11:37:24,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +48: [2023-04-29 11:37:24,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +48: [2023-04-29 11:37:24,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +33: [2023-04-29 11:37:24,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +33: [2023-04-29 11:37:24,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +33: [2023-04-29 11:37:24,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +48: [2023-04-29 11:37:24,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +33: [2023-04-29 11:37:24,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +53: [2023-04-29 11:37:24,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +53: [2023-04-29 11:37:24,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +53: [2023-04-29 11:37:24,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_00-model_states.pt. +56: [2023-04-29 11:37:24,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +56: [2023-04-29 11:37:24,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +56: [2023-04-29 11:37:24,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +56: [2023-04-29 11:37:24,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +53: [2023-04-29 11:37:24,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +18: [2023-04-29 11:37:24,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +53: [2023-04-29 11:37:24,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +53: [2023-04-29 11:37:24,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +53: [2023-04-29 11:37:24,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +56: [2023-04-29 11:37:24,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +18: [2023-04-29 11:37:24,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +18: [2023-04-29 11:37:24,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +56: [2023-04-29 11:37:24,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +56: [2023-04-29 11:37:24,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +56: [2023-04-29 11:37:24,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +18: [2023-04-29 11:37:24,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_00-model_states.pt. +18: [2023-04-29 11:37:24,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +54: [2023-04-29 11:37:24,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +54: [2023-04-29 11:37:24,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +54: [2023-04-29 11:37:24,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +54: [2023-04-29 11:37:24,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +18: [2023-04-29 11:37:24,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +18: [2023-04-29 11:37:24,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +47: [2023-04-29 11:37:24,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +47: [2023-04-29 11:37:24,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +47: [2023-04-29 11:37:24,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +47: [2023-04-29 11:37:24,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +18: [2023-04-29 11:37:24,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +54: [2023-04-29 11:37:24,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +54: [2023-04-29 11:37:24,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +54: [2023-04-29 11:37:24,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +54: [2023-04-29 11:37:24,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +47: [2023-04-29 11:37:24,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +47: [2023-04-29 11:37:24,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +47: [2023-04-29 11:37:24,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +47: [2023-04-29 11:37:24,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +35: [2023-04-29 11:37:24,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +35: [2023-04-29 11:37:24,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +35: [2023-04-29 11:37:24,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +35: [2023-04-29 11:37:24,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +46: [2023-04-29 11:37:24,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +46: [2023-04-29 11:37:24,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +46: [2023-04-29 11:37:24,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +46: [2023-04-29 11:37:24,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +36: [2023-04-29 11:37:24,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +36: [2023-04-29 11:37:24,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +36: [2023-04-29 11:37:24,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +36: [2023-04-29 11:37:24,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +35: [2023-04-29 11:37:24,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +35: [2023-04-29 11:37:24,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +35: [2023-04-29 11:37:24,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +35: [2023-04-29 11:37:24,462] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +51: [2023-04-29 11:37:24,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +51: [2023-04-29 11:37:24,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +51: [2023-04-29 11:37:24,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +51: [2023-04-29 11:37:24,464] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +33: [2023-04-29 11:37:24,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +33: [2023-04-29 11:37:24,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +33: [2023-04-29 11:37:24,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +33: [2023-04-29 11:37:24,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +33: [2023-04-29 11:37:24,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +33: [2023-04-29 11:37:24,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +33: [2023-04-29 11:37:24,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +33: [2023-04-29 11:37:24,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +36: [2023-04-29 11:37:24,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +46: [2023-04-29 11:37:24,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +36: [2023-04-29 11:37:24,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +36: [2023-04-29 11:37:24,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +36: [2023-04-29 11:37:24,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +46: [2023-04-29 11:37:24,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +46: [2023-04-29 11:37:24,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +46: [2023-04-29 11:37:24,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +33: [2023-04-29 11:37:24,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +33: [2023-04-29 11:37:24,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +33: [2023-04-29 11:37:24,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +33: [2023-04-29 11:37:24,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +33: [2023-04-29 11:37:24,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +33: [2023-04-29 11:37:24,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +33: [2023-04-29 11:37:24,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +33: [2023-04-29 11:37:24,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +44: [2023-04-29 11:37:24,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +44: [2023-04-29 11:37:24,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +44: [2023-04-29 11:37:24,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +44: [2023-04-29 11:37:24,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +51: [2023-04-29 11:37:24,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +51: [2023-04-29 11:37:24,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +51: [2023-04-29 11:37:24,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +51: [2023-04-29 11:37:24,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +44: [2023-04-29 11:37:24,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +44: [2023-04-29 11:37:24,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +44: [2023-04-29 11:37:24,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +44: [2023-04-29 11:37:24,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +46: [2023-04-29 11:37:24,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +46: [2023-04-29 11:37:24,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +46: [2023-04-29 11:37:24,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +46: [2023-04-29 11:37:24,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +48: [2023-04-29 11:37:24,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +48: [2023-04-29 11:37:24,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +48: [2023-04-29 11:37:24,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +48: [2023-04-29 11:37:24,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +48: [2023-04-29 11:37:24,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +48: [2023-04-29 11:37:24,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +48: [2023-04-29 11:37:24,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +48: [2023-04-29 11:37:24,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +46: [2023-04-29 11:37:24,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +48: [2023-04-29 11:37:24,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +48: [2023-04-29 11:37:24,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +46: [2023-04-29 11:37:24,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +46: [2023-04-29 11:37:24,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +46: [2023-04-29 11:37:24,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +48: [2023-04-29 11:37:24,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +48: [2023-04-29 11:37:24,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +48: [2023-04-29 11:37:24,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +48: [2023-04-29 11:37:24,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +48: [2023-04-29 11:37:24,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +48: [2023-04-29 11:37:24,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +46: [2023-04-29 11:37:24,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +46: [2023-04-29 11:37:24,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +33: [2023-04-29 11:37:24,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +33: [2023-04-29 11:37:24,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +33: [2023-04-29 11:37:24,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +46: [2023-04-29 11:37:24,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +33: [2023-04-29 11:37:24,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +46: [2023-04-29 11:37:24,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +46: [2023-04-29 11:37:24,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +46: [2023-04-29 11:37:24,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +38: [2023-04-29 11:37:24,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +38: [2023-04-29 11:37:24,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +38: [2023-04-29 11:37:24,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +38: [2023-04-29 11:37:24,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +46: [2023-04-29 11:37:24,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +42: [2023-04-29 11:37:24,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +42: [2023-04-29 11:37:24,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +42: [2023-04-29 11:37:24,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +50: [2023-04-29 11:37:24,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +50: [2023-04-29 11:37:24,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +42: [2023-04-29 11:37:24,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +50: [2023-04-29 11:37:24,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +50: [2023-04-29 11:37:24,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +54: [2023-04-29 11:37:24,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +54: [2023-04-29 11:37:24,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +54: [2023-04-29 11:37:24,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +54: [2023-04-29 11:37:24,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +54: [2023-04-29 11:37:24,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +54: [2023-04-29 11:37:24,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +54: [2023-04-29 11:37:24,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +54: [2023-04-29 11:37:24,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +60: [2023-04-29 11:37:24,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +60: [2023-04-29 11:37:24,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +60: [2023-04-29 11:37:24,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +60: [2023-04-29 11:37:24,558] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +46: [2023-04-29 11:37:24,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +54: [2023-04-29 11:37:24,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +54: [2023-04-29 11:37:24,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +54: [2023-04-29 11:37:24,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +54: [2023-04-29 11:37:24,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +54: [2023-04-29 11:37:24,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +54: [2023-04-29 11:37:24,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +54: [2023-04-29 11:37:24,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +54: [2023-04-29 11:37:24,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +48: [2023-04-29 11:37:24,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +38: [2023-04-29 11:37:24,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +38: [2023-04-29 11:37:24,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +42: [2023-04-29 11:37:24,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +38: [2023-04-29 11:37:24,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +33: [2023-04-29 11:37:24,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +46: [2023-04-29 11:37:24,579] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +33: [2023-04-29 11:37:24,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +33: [2023-04-29 11:37:24,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +42: [2023-04-29 11:37:24,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +42: [2023-04-29 11:37:24,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +42: [2023-04-29 11:37:24,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +38: [2023-04-29 11:37:24,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +50: [2023-04-29 11:37:24,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +48: [2023-04-29 11:37:24,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +48: [2023-04-29 11:37:24,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +48: [2023-04-29 11:37:24,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +50: [2023-04-29 11:37:24,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +60: [2023-04-29 11:37:24,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +60: [2023-04-29 11:37:24,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +33: [2023-04-29 11:37:24,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +60: [2023-04-29 11:37:24,584] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +60: [2023-04-29 11:37:24,584] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +50: [2023-04-29 11:37:24,584] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +50: [2023-04-29 11:37:24,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 8: [2023-04-29 11:37:24,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 8: [2023-04-29 11:37:24,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 8: [2023-04-29 11:37:24,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 8: [2023-04-29 11:37:24,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +40: [2023-04-29 11:37:24,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +40: [2023-04-29 11:37:24,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +40: [2023-04-29 11:37:24,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +40: [2023-04-29 11:37:24,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +46: [2023-04-29 11:37:24,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +46: [2023-04-29 11:37:24,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +46: [2023-04-29 11:37:24,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +48: [2023-04-29 11:37:24,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +48: [2023-04-29 11:37:24,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 8: [2023-04-29 11:37:24,609] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +46: [2023-04-29 11:37:24,609] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +48: [2023-04-29 11:37:24,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +40: [2023-04-29 11:37:24,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +40: [2023-04-29 11:37:24,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +48: [2023-04-29 11:37:24,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +40: [2023-04-29 11:37:24,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +40: [2023-04-29 11:37:24,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 8: [2023-04-29 11:37:24,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +45: [2023-04-29 11:37:24,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +45: [2023-04-29 11:37:24,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +45: [2023-04-29 11:37:24,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. + 8: [2023-04-29 11:37:24,614] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +45: [2023-04-29 11:37:24,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. + 8: [2023-04-29 11:37:24,614] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +35: [2023-04-29 11:37:24,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +35: [2023-04-29 11:37:24,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +35: [2023-04-29 11:37:24,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +35: [2023-04-29 11:37:24,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +35: [2023-04-29 11:37:24,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +35: [2023-04-29 11:37:24,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +35: [2023-04-29 11:37:24,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +35: [2023-04-29 11:37:24,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +35: [2023-04-29 11:37:24,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +57: [2023-04-29 11:37:24,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +57: [2023-04-29 11:37:24,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +57: [2023-04-29 11:37:24,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +54: [2023-04-29 11:37:24,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +57: [2023-04-29 11:37:24,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +46: [2023-04-29 11:37:24,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +35: [2023-04-29 11:37:24,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +35: [2023-04-29 11:37:24,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +54: [2023-04-29 11:37:24,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +35: [2023-04-29 11:37:24,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +35: [2023-04-29 11:37:24,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +46: [2023-04-29 11:37:24,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +35: [2023-04-29 11:37:24,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +46: [2023-04-29 11:37:24,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +35: [2023-04-29 11:37:24,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +35: [2023-04-29 11:37:24,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +39: [2023-04-29 11:37:24,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +39: [2023-04-29 11:37:24,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +54: [2023-04-29 11:37:24,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +54: [2023-04-29 11:37:24,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +39: [2023-04-29 11:37:24,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +39: [2023-04-29 11:37:24,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +45: [2023-04-29 11:37:24,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +24: [2023-04-29 11:37:24,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +24: [2023-04-29 11:37:24,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +24: [2023-04-29 11:37:24,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +45: [2023-04-29 11:37:24,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +24: [2023-04-29 11:37:24,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +45: [2023-04-29 11:37:24,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +45: [2023-04-29 11:37:24,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +54: [2023-04-29 11:37:24,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +57: [2023-04-29 11:37:24,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +57: [2023-04-29 11:37:24,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +54: [2023-04-29 11:37:24,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +14: [2023-04-29 11:37:24,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +14: [2023-04-29 11:37:24,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +14: [2023-04-29 11:37:24,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +14: [2023-04-29 11:37:24,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +57: [2023-04-29 11:37:24,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +39: [2023-04-29 11:37:24,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +57: [2023-04-29 11:37:24,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +39: [2023-04-29 11:37:24,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +39: [2023-04-29 11:37:24,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +39: [2023-04-29 11:37:24,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +54: [2023-04-29 11:37:24,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +54: [2023-04-29 11:37:24,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +21: [2023-04-29 11:37:24,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +21: [2023-04-29 11:37:24,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +21: [2023-04-29 11:37:24,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +21: [2023-04-29 11:37:24,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +12: [2023-04-29 11:37:24,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +12: [2023-04-29 11:37:24,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +12: [2023-04-29 11:37:24,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +12: [2023-04-29 11:37:24,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +24: [2023-04-29 11:37:24,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +24: [2023-04-29 11:37:24,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +24: [2023-04-29 11:37:24,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +24: [2023-04-29 11:37:24,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +14: [2023-04-29 11:37:24,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +12: [2023-04-29 11:37:24,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +14: [2023-04-29 11:37:24,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +14: [2023-04-29 11:37:24,683] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +35: [2023-04-29 11:37:24,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +14: [2023-04-29 11:37:24,683] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +12: [2023-04-29 11:37:24,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +21: [2023-04-29 11:37:24,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +21: [2023-04-29 11:37:24,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +21: [2023-04-29 11:37:24,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +21: [2023-04-29 11:37:24,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +12: [2023-04-29 11:37:24,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +12: [2023-04-29 11:37:24,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +35: [2023-04-29 11:37:24,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +35: [2023-04-29 11:37:24,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +35: [2023-04-29 11:37:24,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +37: [2023-04-29 11:37:24,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +37: [2023-04-29 11:37:24,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +37: [2023-04-29 11:37:24,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +37: [2023-04-29 11:37:24,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +35: [2023-04-29 11:37:24,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +63: [2023-04-29 11:37:24,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +63: [2023-04-29 11:37:24,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +63: [2023-04-29 11:37:24,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +63: [2023-04-29 11:37:24,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +49: [2023-04-29 11:37:24,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +49: [2023-04-29 11:37:24,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +49: [2023-04-29 11:37:24,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +49: [2023-04-29 11:37:24,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +37: [2023-04-29 11:37:24,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +35: [2023-04-29 11:37:24,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +55: [2023-04-29 11:37:24,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +55: [2023-04-29 11:37:24,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +55: [2023-04-29 11:37:24,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +55: [2023-04-29 11:37:24,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +37: [2023-04-29 11:37:24,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +37: [2023-04-29 11:37:24,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +35: [2023-04-29 11:37:24,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +37: [2023-04-29 11:37:24,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +35: [2023-04-29 11:37:24,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +61: [2023-04-29 11:37:24,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +61: [2023-04-29 11:37:24,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +61: [2023-04-29 11:37:24,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +61: [2023-04-29 11:37:24,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +58: [2023-04-29 11:37:24,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +58: [2023-04-29 11:37:24,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +58: [2023-04-29 11:37:24,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +58: [2023-04-29 11:37:24,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +63: [2023-04-29 11:37:24,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +63: [2023-04-29 11:37:24,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +52: [2023-04-29 11:37:24,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +52: [2023-04-29 11:37:24,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +63: [2023-04-29 11:37:24,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +49: [2023-04-29 11:37:24,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +41: [2023-04-29 11:37:24,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +41: [2023-04-29 11:37:24,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +62: [2023-04-29 11:37:24,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +62: [2023-04-29 11:37:24,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +62: [2023-04-29 11:37:24,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +52: [2023-04-29 11:37:24,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +62: [2023-04-29 11:37:24,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +49: [2023-04-29 11:37:24,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +43: [2023-04-29 11:37:24,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +43: [2023-04-29 11:37:24,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +43: [2023-04-29 11:37:24,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +52: [2023-04-29 11:37:24,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +41: [2023-04-29 11:37:24,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +43: [2023-04-29 11:37:24,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +41: [2023-04-29 11:37:24,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +63: [2023-04-29 11:37:24,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +49: [2023-04-29 11:37:24,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +49: [2023-04-29 11:37:24,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +55: [2023-04-29 11:37:24,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +55: [2023-04-29 11:37:24,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +55: [2023-04-29 11:37:24,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +55: [2023-04-29 11:37:24,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +10: [2023-04-29 11:37:24,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +10: [2023-04-29 11:37:24,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +10: [2023-04-29 11:37:24,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +10: [2023-04-29 11:37:24,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +29: [2023-04-29 11:37:24,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +29: [2023-04-29 11:37:24,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +29: [2023-04-29 11:37:24,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +29: [2023-04-29 11:37:24,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +58: [2023-04-29 11:37:24,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +58: [2023-04-29 11:37:24,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +58: [2023-04-29 11:37:24,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +58: [2023-04-29 11:37:24,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +52: [2023-04-29 11:37:24,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +52: [2023-04-29 11:37:24,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +52: [2023-04-29 11:37:24,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +41: [2023-04-29 11:37:24,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +41: [2023-04-29 11:37:24,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +52: [2023-04-29 11:37:24,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +61: [2023-04-29 11:37:24,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +41: [2023-04-29 11:37:24,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +47: [2023-04-29 11:37:24,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +61: [2023-04-29 11:37:24,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +41: [2023-04-29 11:37:24,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +61: [2023-04-29 11:37:24,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +62: [2023-04-29 11:37:24,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +47: [2023-04-29 11:37:24,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +51: [2023-04-29 11:37:24,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +51: [2023-04-29 11:37:24,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +51: [2023-04-29 11:37:24,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +51: [2023-04-29 11:37:24,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +51: [2023-04-29 11:37:24,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +51: [2023-04-29 11:37:24,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +51: [2023-04-29 11:37:24,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +47: [2023-04-29 11:37:24,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +61: [2023-04-29 11:37:24,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +51: [2023-04-29 11:37:24,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +47: [2023-04-29 11:37:24,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +47: [2023-04-29 11:37:24,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +47: [2023-04-29 11:37:24,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +47: [2023-04-29 11:37:24,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +43: [2023-04-29 11:37:24,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +43: [2023-04-29 11:37:24,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +47: [2023-04-29 11:37:24,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +62: [2023-04-29 11:37:24,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +43: [2023-04-29 11:37:24,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +25: [2023-04-29 11:37:24,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +25: [2023-04-29 11:37:24,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +25: [2023-04-29 11:37:24,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +25: [2023-04-29 11:37:24,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +62: [2023-04-29 11:37:24,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +43: [2023-04-29 11:37:24,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +62: [2023-04-29 11:37:24,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +47: [2023-04-29 11:37:24,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +51: [2023-04-29 11:37:24,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +51: [2023-04-29 11:37:24,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +47: [2023-04-29 11:37:24,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +47: [2023-04-29 11:37:24,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +56: [2023-04-29 11:37:24,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +56: [2023-04-29 11:37:24,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +47: [2023-04-29 11:37:24,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +56: [2023-04-29 11:37:24,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +56: [2023-04-29 11:37:24,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +56: [2023-04-29 11:37:24,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +56: [2023-04-29 11:37:24,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +56: [2023-04-29 11:37:24,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +47: [2023-04-29 11:37:24,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +47: [2023-04-29 11:37:24,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +56: [2023-04-29 11:37:24,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +47: [2023-04-29 11:37:24,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +10: [2023-04-29 11:37:24,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +47: [2023-04-29 11:37:24,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +10: [2023-04-29 11:37:24,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +10: [2023-04-29 11:37:24,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +10: [2023-04-29 11:37:24,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +51: [2023-04-29 11:37:24,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +51: [2023-04-29 11:37:24,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +20: [2023-04-29 11:37:24,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 9: [2023-04-29 11:37:24,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +20: [2023-04-29 11:37:24,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 9: [2023-04-29 11:37:24,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +51: [2023-04-29 11:37:24,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... + 9: [2023-04-29 11:37:24,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +51: [2023-04-29 11:37:24,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 9: [2023-04-29 11:37:24,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +51: [2023-04-29 11:37:24,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +20: [2023-04-29 11:37:24,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +51: [2023-04-29 11:37:24,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 5: [2023-04-29 11:37:24,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 5: [2023-04-29 11:37:24,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +20: [2023-04-29 11:37:24,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +13: [2023-04-29 11:37:24,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 5: [2023-04-29 11:37:24,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +30: [2023-04-29 11:37:24,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +30: [2023-04-29 11:37:24,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +22: [2023-04-29 11:37:24,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 5: [2023-04-29 11:37:24,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +30: [2023-04-29 11:37:24,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +22: [2023-04-29 11:37:24,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +22: [2023-04-29 11:37:24,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +22: [2023-04-29 11:37:24,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +13: [2023-04-29 11:37:24,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +30: [2023-04-29 11:37:24,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +13: [2023-04-29 11:37:24,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 4: [2023-04-29 11:37:24,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 4: [2023-04-29 11:37:24,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 4: [2023-04-29 11:37:24,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +27: [2023-04-29 11:37:24,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +27: [2023-04-29 11:37:24,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +27: [2023-04-29 11:37:24,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 4: [2023-04-29 11:37:24,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +13: [2023-04-29 11:37:24,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +27: [2023-04-29 11:37:24,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +56: [2023-04-29 11:37:24,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +56: [2023-04-29 11:37:24,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +56: [2023-04-29 11:37:24,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +29: [2023-04-29 11:37:24,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +56: [2023-04-29 11:37:24,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +56: [2023-04-29 11:37:24,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +56: [2023-04-29 11:37:24,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +56: [2023-04-29 11:37:24,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +56: [2023-04-29 11:37:24,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +29: [2023-04-29 11:37:24,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 3: [2023-04-29 11:37:24,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 3: [2023-04-29 11:37:24,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 3: [2023-04-29 11:37:24,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +29: [2023-04-29 11:37:24,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +29: [2023-04-29 11:37:24,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 3: [2023-04-29 11:37:24,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 0: [2023-04-29 11:37:24,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 0: [2023-04-29 11:37:24,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 6: [2023-04-29 11:37:24,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 6: [2023-04-29 11:37:24,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 6: [2023-04-29 11:37:24,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 6: [2023-04-29 11:37:24,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 7: [2023-04-29 11:37:24,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 7: [2023-04-29 11:37:24,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 7: [2023-04-29 11:37:24,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 7: [2023-04-29 11:37:24,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 7: [2023-04-29 11:37:24,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 7: [2023-04-29 11:37:24,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 7: [2023-04-29 11:37:24,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 7: [2023-04-29 11:37:24,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 0: [2023-04-29 11:37:24,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +26: [2023-04-29 11:37:24,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +26: [2023-04-29 11:37:24,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +26: [2023-04-29 11:37:24,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 0: [2023-04-29 11:37:24,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +26: [2023-04-29 11:37:24,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +29: [2023-04-29 11:37:24,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +29: [2023-04-29 11:37:24,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +29: [2023-04-29 11:37:24,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +29: [2023-04-29 11:37:24,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 7: [2023-04-29 11:37:24,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +25: [2023-04-29 11:37:24,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 9: [2023-04-29 11:37:24,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +45: [2023-04-29 11:37:24,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +45: [2023-04-29 11:37:24,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. + 7: [2023-04-29 11:37:24,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +45: [2023-04-29 11:37:24,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +45: [2023-04-29 11:37:24,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +29: [2023-04-29 11:37:24,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +45: [2023-04-29 11:37:24,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +45: [2023-04-29 11:37:24,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +45: [2023-04-29 11:37:24,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +45: [2023-04-29 11:37:24,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +25: [2023-04-29 11:37:24,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +25: [2023-04-29 11:37:24,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +25: [2023-04-29 11:37:24,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +22: [2023-04-29 11:37:24,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +29: [2023-04-29 11:37:24,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +29: [2023-04-29 11:37:24,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +22: [2023-04-29 11:37:24,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +29: [2023-04-29 11:37:24,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 9: [2023-04-29 11:37:24,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 9: [2023-04-29 11:37:24,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 4: [2023-04-29 11:37:24,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +22: [2023-04-29 11:37:24,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +22: [2023-04-29 11:37:24,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 5: [2023-04-29 11:37:24,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 9: [2023-04-29 11:37:24,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +13: [2023-04-29 11:37:24,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 4: [2023-04-29 11:37:24,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 4: [2023-04-29 11:37:24,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +45: [2023-04-29 11:37:24,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +20: [2023-04-29 11:37:24,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +45: [2023-04-29 11:37:24,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +30: [2023-04-29 11:37:24,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +45: [2023-04-29 11:37:24,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +45: [2023-04-29 11:37:24,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... + 5: [2023-04-29 11:37:24,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 5: [2023-04-29 11:37:24,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 5: [2023-04-29 11:37:24,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 4: [2023-04-29 11:37:24,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +45: [2023-04-29 11:37:24,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... + 3: [2023-04-29 11:37:24,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +20: [2023-04-29 11:37:24,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +45: [2023-04-29 11:37:24,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +45: [2023-04-29 11:37:24,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +45: [2023-04-29 11:37:24,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +13: [2023-04-29 11:37:24,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +13: [2023-04-29 11:37:24,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +20: [2023-04-29 11:37:24,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +13: [2023-04-29 11:37:24,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 3: [2023-04-29 11:37:24,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +27: [2023-04-29 11:37:24,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +20: [2023-04-29 11:37:24,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +23: [2023-04-29 11:37:24,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +23: [2023-04-29 11:37:24,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +23: [2023-04-29 11:37:24,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +23: [2023-04-29 11:37:24,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +27: [2023-04-29 11:37:24,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +27: [2023-04-29 11:37:24,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +27: [2023-04-29 11:37:24,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 3: [2023-04-29 11:37:24,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 0: [2023-04-29 11:37:24,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 3: [2023-04-29 11:37:24,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +30: [2023-04-29 11:37:24,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +30: [2023-04-29 11:37:24,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 0: [2023-04-29 11:37:24,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +30: [2023-04-29 11:37:24,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 0: [2023-04-29 11:37:24,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +26: [2023-04-29 11:37:24,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +26: [2023-04-29 11:37:24,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +26: [2023-04-29 11:37:24,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 6: [2023-04-29 11:37:24,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 0: [2023-04-29 11:37:24,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +21: [2023-04-29 11:37:24,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +21: [2023-04-29 11:37:24,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +24: [2023-04-29 11:37:24,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +24: [2023-04-29 11:37:24,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +24: [2023-04-29 11:37:24,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +24: [2023-04-29 11:37:24,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +24: [2023-04-29 11:37:24,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +24: [2023-04-29 11:37:24,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +24: [2023-04-29 11:37:24,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +24: [2023-04-29 11:37:24,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +21: [2023-04-29 11:37:24,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 6: [2023-04-29 11:37:24,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +21: [2023-04-29 11:37:24,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +21: [2023-04-29 11:37:24,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +21: [2023-04-29 11:37:24,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +21: [2023-04-29 11:37:24,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +21: [2023-04-29 11:37:24,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +34: [2023-04-29 11:37:24,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +34: [2023-04-29 11:37:24,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +26: [2023-04-29 11:37:24,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +34: [2023-04-29 11:37:24,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +34: [2023-04-29 11:37:24,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. + 6: [2023-04-29 11:37:24,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +24: [2023-04-29 11:37:24,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +24: [2023-04-29 11:37:24,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +24: [2023-04-29 11:37:24,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 6: [2023-04-29 11:37:24,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +24: [2023-04-29 11:37:24,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +11: [2023-04-29 11:37:24,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +11: [2023-04-29 11:37:24,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +11: [2023-04-29 11:37:24,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +24: [2023-04-29 11:37:24,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +21: [2023-04-29 11:37:24,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +11: [2023-04-29 11:37:24,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +24: [2023-04-29 11:37:24,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +21: [2023-04-29 11:37:24,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +24: [2023-04-29 11:37:24,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +24: [2023-04-29 11:37:24,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +21: [2023-04-29 11:37:24,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +21: [2023-04-29 11:37:24,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +21: [2023-04-29 11:37:24,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +21: [2023-04-29 11:37:24,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +21: [2023-04-29 11:37:24,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +21: [2023-04-29 11:37:24,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +53: [2023-04-29 11:37:24,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +53: [2023-04-29 11:37:24,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +53: [2023-04-29 11:37:24,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +53: [2023-04-29 11:37:24,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_24-model_01-model_states.pt. +47: [2023-04-29 11:37:24,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +16: [2023-04-29 11:37:24,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +16: [2023-04-29 11:37:24,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +16: [2023-04-29 11:37:24,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +16: [2023-04-29 11:37:24,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +23: [2023-04-29 11:37:24,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +23: [2023-04-29 11:37:24,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +31: [2023-04-29 11:37:24,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +31: [2023-04-29 11:37:24,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +31: [2023-04-29 11:37:24,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +31: [2023-04-29 11:37:24,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +28: [2023-04-29 11:37:24,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +28: [2023-04-29 11:37:24,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +28: [2023-04-29 11:37:24,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +28: [2023-04-29 11:37:24,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +47: [2023-04-29 11:37:24,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +56: [2023-04-29 11:37:24,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +23: [2023-04-29 11:37:24,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +23: [2023-04-29 11:37:24,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +34: [2023-04-29 11:37:24,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +47: [2023-04-29 11:37:24,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +47: [2023-04-29 11:37:24,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +34: [2023-04-29 11:37:24,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +34: [2023-04-29 11:37:24,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +34: [2023-04-29 11:37:24,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +44: [2023-04-29 11:37:24,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +44: [2023-04-29 11:37:24,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +44: [2023-04-29 11:37:24,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +44: [2023-04-29 11:37:24,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +44: [2023-04-29 11:37:24,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +44: [2023-04-29 11:37:24,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +44: [2023-04-29 11:37:24,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +44: [2023-04-29 11:37:24,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +51: [2023-04-29 11:37:24,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +29: [2023-04-29 11:37:24,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +11: [2023-04-29 11:37:24,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +56: [2023-04-29 11:37:24,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +56: [2023-04-29 11:37:24,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +11: [2023-04-29 11:37:24,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +11: [2023-04-29 11:37:24,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +56: [2023-04-29 11:37:24,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +15: [2023-04-29 11:37:24,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +15: [2023-04-29 11:37:24,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +15: [2023-04-29 11:37:24,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +15: [2023-04-29 11:37:24,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +11: [2023-04-29 11:37:24,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +51: [2023-04-29 11:37:24,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +51: [2023-04-29 11:37:24,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +51: [2023-04-29 11:37:24,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +53: [2023-04-29 11:37:24,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +19: [2023-04-29 11:37:24,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +19: [2023-04-29 11:37:24,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +63: [2023-04-29 11:37:24,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +63: [2023-04-29 11:37:24,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +63: [2023-04-29 11:37:24,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +63: [2023-04-29 11:37:24,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +63: [2023-04-29 11:37:24,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +63: [2023-04-29 11:37:24,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +63: [2023-04-29 11:37:24,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +63: [2023-04-29 11:37:24,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +29: [2023-04-29 11:37:24,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +53: [2023-04-29 11:37:24,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +19: [2023-04-29 11:37:24,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +53: [2023-04-29 11:37:24,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +53: [2023-04-29 11:37:24,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +44: [2023-04-29 11:37:24,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +44: [2023-04-29 11:37:24,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +44: [2023-04-29 11:37:24,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +19: [2023-04-29 11:37:24,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +44: [2023-04-29 11:37:24,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +44: [2023-04-29 11:37:24,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +44: [2023-04-29 11:37:24,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +16: [2023-04-29 11:37:24,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +58: [2023-04-29 11:37:24,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +58: [2023-04-29 11:37:24,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +58: [2023-04-29 11:37:24,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +58: [2023-04-29 11:37:24,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +58: [2023-04-29 11:37:24,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +44: [2023-04-29 11:37:24,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +58: [2023-04-29 11:37:24,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +58: [2023-04-29 11:37:24,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +58: [2023-04-29 11:37:24,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +16: [2023-04-29 11:37:24,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 2: [2023-04-29 11:37:24,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 2: [2023-04-29 11:37:24,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +16: [2023-04-29 11:37:24,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +47: [2023-04-29 11:37:24,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +63: [2023-04-29 11:37:24,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +44: [2023-04-29 11:37:24,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +63: [2023-04-29 11:37:24,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +31: [2023-04-29 11:37:24,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +63: [2023-04-29 11:37:24,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +63: [2023-04-29 11:37:24,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +16: [2023-04-29 11:37:24,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +63: [2023-04-29 11:37:24,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +63: [2023-04-29 11:37:24,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +29: [2023-04-29 11:37:24,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +29: [2023-04-29 11:37:24,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +63: [2023-04-29 11:37:24,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +28: [2023-04-29 11:37:24,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +63: [2023-04-29 11:37:24,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +31: [2023-04-29 11:37:24,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 2: [2023-04-29 11:37:24,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 2: [2023-04-29 11:37:24,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +47: [2023-04-29 11:37:24,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +58: [2023-04-29 11:37:24,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +31: [2023-04-29 11:37:24,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +31: [2023-04-29 11:37:24,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +58: [2023-04-29 11:37:24,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +58: [2023-04-29 11:37:24,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +58: [2023-04-29 11:37:24,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +58: [2023-04-29 11:37:24,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +58: [2023-04-29 11:37:24,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +58: [2023-04-29 11:37:24,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +45: [2023-04-29 11:37:24,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +58: [2023-04-29 11:37:24,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +29: [2023-04-29 11:37:24,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +29: [2023-04-29 11:37:24,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +56: [2023-04-29 11:37:24,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 1: [2023-04-29 11:37:24,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 1: [2023-04-29 11:37:24,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +47: [2023-04-29 11:37:24,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +45: [2023-04-29 11:37:24,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +29: [2023-04-29 11:37:24,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +29: [2023-04-29 11:37:24,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +28: [2023-04-29 11:37:24,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 8: [2023-04-29 11:37:24,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 8: [2023-04-29 11:37:24,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 8: [2023-04-29 11:37:24,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 8: [2023-04-29 11:37:24,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 8: [2023-04-29 11:37:24,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 8: [2023-04-29 11:37:24,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +28: [2023-04-29 11:37:24,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 8: [2023-04-29 11:37:24,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 8: [2023-04-29 11:37:24,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +57: [2023-04-29 11:37:24,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +57: [2023-04-29 11:37:24,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +57: [2023-04-29 11:37:24,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +57: [2023-04-29 11:37:24,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +57: [2023-04-29 11:37:24,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +57: [2023-04-29 11:37:24,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +57: [2023-04-29 11:37:24,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +57: [2023-04-29 11:37:24,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +36: [2023-04-29 11:37:24,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +36: [2023-04-29 11:37:24,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +36: [2023-04-29 11:37:24,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +36: [2023-04-29 11:37:24,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +36: [2023-04-29 11:37:24,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +36: [2023-04-29 11:37:24,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +36: [2023-04-29 11:37:24,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +36: [2023-04-29 11:37:24,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +28: [2023-04-29 11:37:24,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +47: [2023-04-29 11:37:24,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +15: [2023-04-29 11:37:24,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 5: [2023-04-29 11:37:24,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 5: [2023-04-29 11:37:24,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 5: [2023-04-29 11:37:24,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 5: [2023-04-29 11:37:24,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +45: [2023-04-29 11:37:24,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +45: [2023-04-29 11:37:24,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. + 7: [2023-04-29 11:37:24,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 8: [2023-04-29 11:37:24,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +29: [2023-04-29 11:37:24,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 8: [2023-04-29 11:37:24,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 8: [2023-04-29 11:37:24,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +36: [2023-04-29 11:37:24,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... + 5: [2023-04-29 11:37:24,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +15: [2023-04-29 11:37:24,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 1: [2023-04-29 11:37:24,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +36: [2023-04-29 11:37:24,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +36: [2023-04-29 11:37:24,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... + 5: [2023-04-29 11:37:24,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 5: [2023-04-29 11:37:24,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 5: [2023-04-29 11:37:24,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +36: [2023-04-29 11:37:24,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 1: [2023-04-29 11:37:24,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +29: [2023-04-29 11:37:24,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +29: [2023-04-29 11:37:24,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +57: [2023-04-29 11:37:24,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +29: [2023-04-29 11:37:24,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +17: [2023-04-29 11:37:24,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +17: [2023-04-29 11:37:24,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +17: [2023-04-29 11:37:24,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +57: [2023-04-29 11:37:24,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +51: [2023-04-29 11:37:24,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +17: [2023-04-29 11:37:24,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +24: [2023-04-29 11:37:24,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +57: [2023-04-29 11:37:24,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +57: [2023-04-29 11:37:24,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 7: [2023-04-29 11:37:24,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +57: [2023-04-29 11:37:24,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +48: [2023-04-29 11:37:24,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +48: [2023-04-29 11:37:24,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +48: [2023-04-29 11:37:24,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +15: [2023-04-29 11:37:24,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +15: [2023-04-29 11:37:24,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +57: [2023-04-29 11:37:24,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... + 7: [2023-04-29 11:37:24,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +57: [2023-04-29 11:37:24,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +36: [2023-04-29 11:37:24,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +36: [2023-04-29 11:37:24,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +36: [2023-04-29 11:37:24,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +36: [2023-04-29 11:37:24,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +19: [2023-04-29 11:37:24,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +20: [2023-04-29 11:37:24,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +20: [2023-04-29 11:37:24,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +20: [2023-04-29 11:37:24,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +56: [2023-04-29 11:37:24,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +20: [2023-04-29 11:37:24,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +56: [2023-04-29 11:37:24,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 8: [2023-04-29 11:37:24,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 8: [2023-04-29 11:37:24,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +20: [2023-04-29 11:37:24,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +20: [2023-04-29 11:37:24,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +20: [2023-04-29 11:37:24,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +20: [2023-04-29 11:37:24,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +37: [2023-04-29 11:37:24,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +37: [2023-04-29 11:37:24,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +19: [2023-04-29 11:37:24,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +19: [2023-04-29 11:37:24,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +57: [2023-04-29 11:37:24,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +48: [2023-04-29 11:37:24,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +37: [2023-04-29 11:37:24,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +37: [2023-04-29 11:37:24,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +37: [2023-04-29 11:37:24,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +37: [2023-04-29 11:37:24,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +37: [2023-04-29 11:37:24,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. + 5: [2023-04-29 11:37:24,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +54: [2023-04-29 11:37:24,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +54: [2023-04-29 11:37:24,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +37: [2023-04-29 11:37:24,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +56: [2023-04-29 11:37:24,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +54: [2023-04-29 11:37:24,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +54: [2023-04-29 11:37:24,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. + 5: [2023-04-29 11:37:24,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +24: [2023-04-29 11:37:24,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +24: [2023-04-29 11:37:24,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 2: [2023-04-29 11:37:24,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 8: [2023-04-29 11:37:24,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 8: [2023-04-29 11:37:24,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 8: [2023-04-29 11:37:24,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 2: [2023-04-29 11:37:24,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 5: [2023-04-29 11:37:24,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 5: [2023-04-29 11:37:24,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 5: [2023-04-29 11:37:24,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 5: [2023-04-29 11:37:24,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +21: [2023-04-29 11:37:24,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 3: [2023-04-29 11:37:24,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 3: [2023-04-29 11:37:24,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 3: [2023-04-29 11:37:24,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 3: [2023-04-29 11:37:24,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 3: [2023-04-29 11:37:24,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 3: [2023-04-29 11:37:24,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 3: [2023-04-29 11:37:24,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +19: [2023-04-29 11:37:24,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 5: [2023-04-29 11:37:24,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 3: [2023-04-29 11:37:24,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 5: [2023-04-29 11:37:24,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 2: [2023-04-29 11:37:24,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 4: [2023-04-29 11:37:24,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 4: [2023-04-29 11:37:24,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 4: [2023-04-29 11:37:24,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 0: [2023-04-29 11:37:24,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 0: [2023-04-29 11:37:24,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 0: [2023-04-29 11:37:24,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 4: [2023-04-29 11:37:24,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 4: [2023-04-29 11:37:24,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 4: [2023-04-29 11:37:24,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 4: [2023-04-29 11:37:24,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 0: [2023-04-29 11:37:24,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 4: [2023-04-29 11:37:24,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +37: [2023-04-29 11:37:24,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +24: [2023-04-29 11:37:24,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +20: [2023-04-29 11:37:24,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 2: [2023-04-29 11:37:24,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +37: [2023-04-29 11:37:24,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +51: [2023-04-29 11:37:24,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 0: [2023-04-29 11:37:24,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 0: [2023-04-29 11:37:24,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 0: [2023-04-29 11:37:24,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +51: [2023-04-29 11:37:24,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +51: [2023-04-29 11:37:24,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +45: [2023-04-29 11:37:24,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 3: [2023-04-29 11:37:24,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 3: [2023-04-29 11:37:24,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 3: [2023-04-29 11:37:24,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 3: [2023-04-29 11:37:24,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 3: [2023-04-29 11:37:24,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +20: [2023-04-29 11:37:24,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +20: [2023-04-29 11:37:24,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 3: [2023-04-29 11:37:24,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 4: [2023-04-29 11:37:24,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 4: [2023-04-29 11:37:24,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +20: [2023-04-29 11:37:24,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +20: [2023-04-29 11:37:24,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +20: [2023-04-29 11:37:24,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 4: [2023-04-29 11:37:24,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 0: [2023-04-29 11:37:24,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 3: [2023-04-29 11:37:24,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +20: [2023-04-29 11:37:24,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 2: [2023-04-29 11:37:24,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 2: [2023-04-29 11:37:24,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 2: [2023-04-29 11:37:24,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 2: [2023-04-29 11:37:24,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 0: [2023-04-29 11:37:24,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +20: [2023-04-29 11:37:24,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 0: [2023-04-29 11:37:24,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 0: [2023-04-29 11:37:24,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +37: [2023-04-29 11:37:24,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 1: [2023-04-29 11:37:24,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +49: [2023-04-29 11:37:24,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. + 0: [2023-04-29 11:37:24,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 3: [2023-04-29 11:37:24,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 1: [2023-04-29 11:37:24,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +49: [2023-04-29 11:37:24,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +49: [2023-04-29 11:37:24,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +37: [2023-04-29 11:37:24,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +49: [2023-04-29 11:37:24,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +49: [2023-04-29 11:37:24,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +49: [2023-04-29 11:37:24,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +49: [2023-04-29 11:37:24,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +37: [2023-04-29 11:37:24,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +37: [2023-04-29 11:37:24,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +29: [2023-04-29 11:37:24,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +37: [2023-04-29 11:37:24,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +49: [2023-04-29 11:37:24,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +37: [2023-04-29 11:37:24,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... + 4: [2023-04-29 11:37:24,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 4: [2023-04-29 11:37:24,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 4: [2023-04-29 11:37:24,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 4: [2023-04-29 11:37:24,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 4: [2023-04-29 11:37:24,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +21: [2023-04-29 11:37:24,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +21: [2023-04-29 11:37:24,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +21: [2023-04-29 11:37:24,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 2: [2023-04-29 11:37:24,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 0: [2023-04-29 11:37:24,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 0: [2023-04-29 11:37:24,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 0: [2023-04-29 11:37:24,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +45: [2023-04-29 11:37:24,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 0: [2023-04-29 11:37:24,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 2: [2023-04-29 11:37:24,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +18: [2023-04-29 11:37:24,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +18: [2023-04-29 11:37:24,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +18: [2023-04-29 11:37:24,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. +18: [2023-04-29 11:37:24,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_01-model_01-model_states.pt. + 2: [2023-04-29 11:37:24,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 2: [2023-04-29 11:37:24,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 7: [2023-04-29 11:37:24,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +14: [2023-04-29 11:37:24,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +14: [2023-04-29 11:37:24,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +14: [2023-04-29 11:37:24,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +14: [2023-04-29 11:37:24,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 1: [2023-04-29 11:37:24,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +14: [2023-04-29 11:37:24,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 1: [2023-04-29 11:37:24,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +14: [2023-04-29 11:37:24,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +14: [2023-04-29 11:37:24,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +14: [2023-04-29 11:37:24,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +17: [2023-04-29 11:37:24,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +49: [2023-04-29 11:37:24,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +49: [2023-04-29 11:37:24,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +17: [2023-04-29 11:37:24,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +17: [2023-04-29 11:37:24,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +49: [2023-04-29 11:37:24,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +17: [2023-04-29 11:37:24,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +45: [2023-04-29 11:37:24,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +45: [2023-04-29 11:37:24,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +24: [2023-04-29 11:37:24,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 7: [2023-04-29 11:37:24,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +33: [2023-04-29 11:37:24,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +33: [2023-04-29 11:37:24,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +33: [2023-04-29 11:37:24,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +49: [2023-04-29 11:37:24,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +33: [2023-04-29 11:37:24,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +29: [2023-04-29 11:37:24,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +49: [2023-04-29 11:37:24,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +49: [2023-04-29 11:37:24,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +49: [2023-04-29 11:37:24,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +49: [2023-04-29 11:37:24,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +29: [2023-04-29 11:37:24,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +29: [2023-04-29 11:37:24,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +54: [2023-04-29 11:37:24,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +21: [2023-04-29 11:37:24,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +48: [2023-04-29 11:37:24,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +48: [2023-04-29 11:37:24,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +48: [2023-04-29 11:37:24,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +24: [2023-04-29 11:37:24,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +14: [2023-04-29 11:37:24,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +54: [2023-04-29 11:37:24,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +54: [2023-04-29 11:37:24,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +54: [2023-04-29 11:37:24,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +14: [2023-04-29 11:37:24,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +48: [2023-04-29 11:37:24,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +14: [2023-04-29 11:37:24,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +24: [2023-04-29 11:37:24,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +14: [2023-04-29 11:37:24,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +14: [2023-04-29 11:37:24,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +14: [2023-04-29 11:37:24,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +14: [2023-04-29 11:37:24,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +14: [2023-04-29 11:37:24,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +24: [2023-04-29 11:37:24,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +18: [2023-04-29 11:37:24,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +18: [2023-04-29 11:37:24,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 7: [2023-04-29 11:37:24,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +18: [2023-04-29 11:37:24,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +18: [2023-04-29 11:37:24,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +44: [2023-04-29 11:37:24,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +63: [2023-04-29 11:37:24,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +63: [2023-04-29 11:37:24,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +59: [2023-04-29 11:37:24,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +59: [2023-04-29 11:37:24,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +59: [2023-04-29 11:37:24,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +59: [2023-04-29 11:37:24,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +59: [2023-04-29 11:37:24,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +59: [2023-04-29 11:37:24,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +59: [2023-04-29 11:37:24,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +59: [2023-04-29 11:37:24,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +21: [2023-04-29 11:37:24,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +44: [2023-04-29 11:37:24,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +44: [2023-04-29 11:37:24,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +63: [2023-04-29 11:37:24,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +63: [2023-04-29 11:37:24,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +21: [2023-04-29 11:37:24,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +44: [2023-04-29 11:37:24,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +21: [2023-04-29 11:37:24,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +58: [2023-04-29 11:37:24,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +58: [2023-04-29 11:37:24,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +59: [2023-04-29 11:37:24,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +59: [2023-04-29 11:37:24,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +59: [2023-04-29 11:37:24,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +59: [2023-04-29 11:37:24,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +59: [2023-04-29 11:37:24,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +59: [2023-04-29 11:37:24,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +59: [2023-04-29 11:37:24,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +59: [2023-04-29 11:37:24,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +58: [2023-04-29 11:37:24,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +33: [2023-04-29 11:37:24,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +58: [2023-04-29 11:37:24,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +46: [2023-04-29 11:37:24,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +46: [2023-04-29 11:37:24,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. + 8: [2023-04-29 11:37:24,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +46: [2023-04-29 11:37:24,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +46: [2023-04-29 11:37:24,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +48: [2023-04-29 11:37:24,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +48: [2023-04-29 11:37:24,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. + 8: [2023-04-29 11:37:24,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +33: [2023-04-29 11:37:24,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +33: [2023-04-29 11:37:24,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +33: [2023-04-29 11:37:24,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +48: [2023-04-29 11:37:24,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +48: [2023-04-29 11:37:24,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +57: [2023-04-29 11:37:24,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +57: [2023-04-29 11:37:24,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +36: [2023-04-29 11:37:24,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +48: [2023-04-29 11:37:24,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +48: [2023-04-29 11:37:24,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +44: [2023-04-29 11:37:24,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +57: [2023-04-29 11:37:24,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +36: [2023-04-29 11:37:24,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +63: [2023-04-29 11:37:24,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +48: [2023-04-29 11:37:24,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +17: [2023-04-29 11:37:24,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +17: [2023-04-29 11:37:24,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +17: [2023-04-29 11:37:24,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +17: [2023-04-29 11:37:24,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +63: [2023-04-29 11:37:24,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +57: [2023-04-29 11:37:24,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +48: [2023-04-29 11:37:24,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +37: [2023-04-29 11:37:24,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +23: [2023-04-29 11:37:24,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +23: [2023-04-29 11:37:24,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +23: [2023-04-29 11:37:24,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +23: [2023-04-29 11:37:24,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +23: [2023-04-29 11:37:24,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +20: [2023-04-29 11:37:24,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +23: [2023-04-29 11:37:24,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +23: [2023-04-29 11:37:24,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +23: [2023-04-29 11:37:24,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 3: [2023-04-29 11:37:24,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 4: [2023-04-29 11:37:24,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 8: [2023-04-29 11:37:24,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 8: [2023-04-29 11:37:24,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 2: [2023-04-29 11:37:24,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +17: [2023-04-29 11:37:24,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +20: [2023-04-29 11:37:24,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 3: [2023-04-29 11:37:24,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +17: [2023-04-29 11:37:24,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +17: [2023-04-29 11:37:24,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +46: [2023-04-29 11:37:24,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +46: [2023-04-29 11:37:24,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +17: [2023-04-29 11:37:24,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +46: [2023-04-29 11:37:24,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +30: [2023-04-29 11:37:24,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +30: [2023-04-29 11:37:24,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +30: [2023-04-29 11:37:24,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +30: [2023-04-29 11:37:24,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +30: [2023-04-29 11:37:24,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +30: [2023-04-29 11:37:24,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +30: [2023-04-29 11:37:24,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +58: [2023-04-29 11:37:24,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +63: [2023-04-29 11:37:24,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +30: [2023-04-29 11:37:24,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +63: [2023-04-29 11:37:24,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +46: [2023-04-29 11:37:24,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +23: [2023-04-29 11:37:24,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +20: [2023-04-29 11:37:24,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +20: [2023-04-29 11:37:24,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 2: [2023-04-29 11:37:24,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 2: [2023-04-29 11:37:24,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +58: [2023-04-29 11:37:24,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +23: [2023-04-29 11:37:24,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 2: [2023-04-29 11:37:24,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +23: [2023-04-29 11:37:24,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +23: [2023-04-29 11:37:24,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 3: [2023-04-29 11:37:24,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 3: [2023-04-29 11:37:24,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +25: [2023-04-29 11:37:24,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +25: [2023-04-29 11:37:24,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 0: [2023-04-29 11:37:24,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 5: [2023-04-29 11:37:24,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 5: [2023-04-29 11:37:24,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 5: [2023-04-29 11:37:24,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +36: [2023-04-29 11:37:24,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +36: [2023-04-29 11:37:24,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +23: [2023-04-29 11:37:24,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +23: [2023-04-29 11:37:24,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +23: [2023-04-29 11:37:24,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +55: [2023-04-29 11:37:24,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +55: [2023-04-29 11:37:24,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +55: [2023-04-29 11:37:24,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +55: [2023-04-29 11:37:24,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +55: [2023-04-29 11:37:24,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +55: [2023-04-29 11:37:24,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +55: [2023-04-29 11:37:24,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +55: [2023-04-29 11:37:24,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +38: [2023-04-29 11:37:24,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +38: [2023-04-29 11:37:24,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +38: [2023-04-29 11:37:24,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +38: [2023-04-29 11:37:24,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +38: [2023-04-29 11:37:24,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +38: [2023-04-29 11:37:24,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +38: [2023-04-29 11:37:24,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +38: [2023-04-29 11:37:24,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +44: [2023-04-29 11:37:24,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +44: [2023-04-29 11:37:24,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 2: [2023-04-29 11:37:24,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 2: [2023-04-29 11:37:24,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +23: [2023-04-29 11:37:24,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +30: [2023-04-29 11:37:24,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +58: [2023-04-29 11:37:24,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +30: [2023-04-29 11:37:24,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 0: [2023-04-29 11:37:24,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 0: [2023-04-29 11:37:24,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 0: [2023-04-29 11:37:24,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +25: [2023-04-29 11:37:24,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +25: [2023-04-29 11:37:24,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +25: [2023-04-29 11:37:24,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +25: [2023-04-29 11:37:24,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +25: [2023-04-29 11:37:24,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +25: [2023-04-29 11:37:24,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +46: [2023-04-29 11:37:24,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +30: [2023-04-29 11:37:24,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +44: [2023-04-29 11:37:24,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +30: [2023-04-29 11:37:24,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +46: [2023-04-29 11:37:24,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +46: [2023-04-29 11:37:24,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +49: [2023-04-29 11:37:24,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +58: [2023-04-29 11:37:24,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 4: [2023-04-29 11:37:24,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 4: [2023-04-29 11:37:24,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +30: [2023-04-29 11:37:24,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 4: [2023-04-29 11:37:24,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +46: [2023-04-29 11:37:24,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 8: [2023-04-29 11:37:24,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +46: [2023-04-29 11:37:24,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +30: [2023-04-29 11:37:24,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +37: [2023-04-29 11:37:24,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +37: [2023-04-29 11:37:24,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +37: [2023-04-29 11:37:24,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +30: [2023-04-29 11:37:24,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 5: [2023-04-29 11:37:24,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +25: [2023-04-29 11:37:24,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +38: [2023-04-29 11:37:24,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +30: [2023-04-29 11:37:24,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +25: [2023-04-29 11:37:24,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +55: [2023-04-29 11:37:24,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 2: [2023-04-29 11:37:24,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 8: [2023-04-29 11:37:24,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 2: [2023-04-29 11:37:24,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +46: [2023-04-29 11:37:24,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +55: [2023-04-29 11:37:24,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +38: [2023-04-29 11:37:24,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +55: [2023-04-29 11:37:24,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +55: [2023-04-29 11:37:24,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +55: [2023-04-29 11:37:24,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +46: [2023-04-29 11:37:24,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +38: [2023-04-29 11:37:24,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +38: [2023-04-29 11:37:24,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +55: [2023-04-29 11:37:24,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +55: [2023-04-29 11:37:24,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +55: [2023-04-29 11:37:24,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +46: [2023-04-29 11:37:24,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +52: [2023-04-29 11:37:24,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +52: [2023-04-29 11:37:24,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +25: [2023-04-29 11:37:24,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +36: [2023-04-29 11:37:24,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +38: [2023-04-29 11:37:24,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +25: [2023-04-29 11:37:24,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +17: [2023-04-29 11:37:24,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +52: [2023-04-29 11:37:24,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +38: [2023-04-29 11:37:24,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +52: [2023-04-29 11:37:24,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +25: [2023-04-29 11:37:24,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +52: [2023-04-29 11:37:24,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +52: [2023-04-29 11:37:24,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +38: [2023-04-29 11:37:24,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +52: [2023-04-29 11:37:24,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +52: [2023-04-29 11:37:24,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +38: [2023-04-29 11:37:24,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 9: [2023-04-29 11:37:24,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 9: [2023-04-29 11:37:24,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 9: [2023-04-29 11:37:24,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 9: [2023-04-29 11:37:24,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +25: [2023-04-29 11:37:24,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 9: [2023-04-29 11:37:24,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 9: [2023-04-29 11:37:24,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 9: [2023-04-29 11:37:24,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 9: [2023-04-29 11:37:24,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +36: [2023-04-29 11:37:24,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +25: [2023-04-29 11:37:24,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 4: [2023-04-29 11:37:24,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 2: [2023-04-29 11:37:24,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 2: [2023-04-29 11:37:24,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 2: [2023-04-29 11:37:24,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 2: [2023-04-29 11:37:24,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +37: [2023-04-29 11:37:24,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +25: [2023-04-29 11:37:24,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +57: [2023-04-29 11:37:24,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +52: [2023-04-29 11:37:24,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +52: [2023-04-29 11:37:24,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +52: [2023-04-29 11:37:24,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +17: [2023-04-29 11:37:24,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +20: [2023-04-29 11:37:24,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 3: [2023-04-29 11:37:24,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +52: [2023-04-29 11:37:24,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +17: [2023-04-29 11:37:24,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +57: [2023-04-29 11:37:24,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +17: [2023-04-29 11:37:24,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +17: [2023-04-29 11:37:24,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 3: [2023-04-29 11:37:24,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +57: [2023-04-29 11:37:24,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +52: [2023-04-29 11:37:24,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +40: [2023-04-29 11:37:24,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +40: [2023-04-29 11:37:24,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +40: [2023-04-29 11:37:24,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +40: [2023-04-29 11:37:24,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +14: [2023-04-29 11:37:24,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +40: [2023-04-29 11:37:24,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +40: [2023-04-29 11:37:24,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +40: [2023-04-29 11:37:24,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +57: [2023-04-29 11:37:24,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +40: [2023-04-29 11:37:24,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +49: [2023-04-29 11:37:24,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +49: [2023-04-29 11:37:24,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +49: [2023-04-29 11:37:24,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +52: [2023-04-29 11:37:24,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +52: [2023-04-29 11:37:24,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +52: [2023-04-29 11:37:24,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... + 8: [2023-04-29 11:37:24,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 8: [2023-04-29 11:37:24,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +17: [2023-04-29 11:37:24,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 0: [2023-04-29 11:37:24,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +17: [2023-04-29 11:37:24,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +20: [2023-04-29 11:37:24,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 9: [2023-04-29 11:37:24,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 9: [2023-04-29 11:37:24,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +40: [2023-04-29 11:37:24,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +40: [2023-04-29 11:37:24,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +40: [2023-04-29 11:37:24,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... + 9: [2023-04-29 11:37:24,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 9: [2023-04-29 11:37:24,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 9: [2023-04-29 11:37:24,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +14: [2023-04-29 11:37:24,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 9: [2023-04-29 11:37:24,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 9: [2023-04-29 11:37:24,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 9: [2023-04-29 11:37:24,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 3: [2023-04-29 11:37:24,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +17: [2023-04-29 11:37:24,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +40: [2023-04-29 11:37:24,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +40: [2023-04-29 11:37:24,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +40: [2023-04-29 11:37:24,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +34: [2023-04-29 11:37:24,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +34: [2023-04-29 11:37:24,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +40: [2023-04-29 11:37:24,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +32: [2023-04-29 11:37:24,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +32: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +32: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +32: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +36: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +40: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +50: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +50: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +50: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +32: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +34: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +34: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +48: [2023-04-29 11:37:24,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +48: [2023-04-29 11:37:24,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +48: [2023-04-29 11:37:24,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +50: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +50: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +50: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +50: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +34: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +34: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +34: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +32: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +32: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +60: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +60: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +60: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +60: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +60: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +60: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +60: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +20: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +62: [2023-04-29 11:37:24,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +62: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +62: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +62: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +62: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +34: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +36: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +20: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +50: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +32: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +62: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +62: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +60: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +62: [2023-04-29 11:37:24,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. + 3: [2023-04-29 11:37:24,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 5: [2023-04-29 11:37:24,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +49: [2023-04-29 11:37:24,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +43: [2023-04-29 11:37:24,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +43: [2023-04-29 11:37:24,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +43: [2023-04-29 11:37:24,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +43: [2023-04-29 11:37:24,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +43: [2023-04-29 11:37:24,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +43: [2023-04-29 11:37:24,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +43: [2023-04-29 11:37:24,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +43: [2023-04-29 11:37:24,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. + 5: [2023-04-29 11:37:24,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +37: [2023-04-29 11:37:24,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 4: [2023-04-29 11:37:24,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +39: [2023-04-29 11:37:24,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +39: [2023-04-29 11:37:24,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. + 2: [2023-04-29 11:37:24,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 0: [2023-04-29 11:37:24,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 0: [2023-04-29 11:37:24,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 0: [2023-04-29 11:37:24,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +48: [2023-04-29 11:37:24,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. + 4: [2023-04-29 11:37:24,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 4: [2023-04-29 11:37:24,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 5: [2023-04-29 11:37:24,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +62: [2023-04-29 11:37:24,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +62: [2023-04-29 11:37:24,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +34: [2023-04-29 11:37:24,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +34: [2023-04-29 11:37:24,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +37: [2023-04-29 11:37:24,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +37: [2023-04-29 11:37:24,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +59: [2023-04-29 11:37:24,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +59: [2023-04-29 11:37:24,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +34: [2023-04-29 11:37:24,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +34: [2023-04-29 11:37:24,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +60: [2023-04-29 11:37:24,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +60: [2023-04-29 11:37:24,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +60: [2023-04-29 11:37:24,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +60: [2023-04-29 11:37:24,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +60: [2023-04-29 11:37:24,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +50: [2023-04-29 11:37:24,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +43: [2023-04-29 11:37:24,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +48: [2023-04-29 11:37:24,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +48: [2023-04-29 11:37:24,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +48: [2023-04-29 11:37:24,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +39: [2023-04-29 11:37:24,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +39: [2023-04-29 11:37:24,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +39: [2023-04-29 11:37:24,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +60: [2023-04-29 11:37:24,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +60: [2023-04-29 11:37:24,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +39: [2023-04-29 11:37:24,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +39: [2023-04-29 11:37:24,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +60: [2023-04-29 11:37:24,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +39: [2023-04-29 11:37:24,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +14: [2023-04-29 11:37:24,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +43: [2023-04-29 11:37:24,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +48: [2023-04-29 11:37:24,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +62: [2023-04-29 11:37:24,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +43: [2023-04-29 11:37:24,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +32: [2023-04-29 11:37:24,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +43: [2023-04-29 11:37:24,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +43: [2023-04-29 11:37:24,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +43: [2023-04-29 11:37:24,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +43: [2023-04-29 11:37:24,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... + 5: [2023-04-29 11:37:24,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +59: [2023-04-29 11:37:24,992] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +59: [2023-04-29 11:37:24,992] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +34: [2023-04-29 11:37:24,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +39: [2023-04-29 11:37:24,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +43: [2023-04-29 11:37:24,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +32: [2023-04-29 11:37:24,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +34: [2023-04-29 11:37:24,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +39: [2023-04-29 11:37:24,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +50: [2023-04-29 11:37:24,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +50: [2023-04-29 11:37:24,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +39: [2023-04-29 11:37:24,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +32: [2023-04-29 11:37:24,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +32: [2023-04-29 11:37:24,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +34: [2023-04-29 11:37:24,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +34: [2023-04-29 11:37:24,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +62: [2023-04-29 11:37:24,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +62: [2023-04-29 11:37:24,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +62: [2023-04-29 11:37:24,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +62: [2023-04-29 11:37:24,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +62: [2023-04-29 11:37:24,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +50: [2023-04-29 11:37:24,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +50: [2023-04-29 11:37:24,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 2: [2023-04-29 11:37:24,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 2: [2023-04-29 11:37:24,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +32: [2023-04-29 11:37:24,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +50: [2023-04-29 11:37:24,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... + 2: [2023-04-29 11:37:24,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +39: [2023-04-29 11:37:24,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +39: [2023-04-29 11:37:24,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +39: [2023-04-29 11:37:24,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +32: [2023-04-29 11:37:24,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +50: [2023-04-29 11:37:24,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +50: [2023-04-29 11:37:24,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +39: [2023-04-29 11:37:24,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +32: [2023-04-29 11:37:24,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +32: [2023-04-29 11:37:24,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +39: [2023-04-29 11:37:24,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +14: [2023-04-29 11:37:24,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +14: [2023-04-29 11:37:24,999] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +28: [2023-04-29 11:37:25,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +28: [2023-04-29 11:37:25,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +28: [2023-04-29 11:37:25,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +28: [2023-04-29 11:37:25,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +28: [2023-04-29 11:37:25,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +28: [2023-04-29 11:37:25,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +28: [2023-04-29 11:37:25,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 1: [2023-04-29 11:37:25,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 1: [2023-04-29 11:37:25,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +28: [2023-04-29 11:37:25,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +22: [2023-04-29 11:37:25,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +22: [2023-04-29 11:37:25,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +22: [2023-04-29 11:37:25,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +22: [2023-04-29 11:37:25,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +22: [2023-04-29 11:37:25,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +22: [2023-04-29 11:37:25,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +22: [2023-04-29 11:37:25,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +22: [2023-04-29 11:37:25,003] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +49: [2023-04-29 11:37:25,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 1: [2023-04-29 11:37:25,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 1: [2023-04-29 11:37:25,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 1: [2023-04-29 11:37:25,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +49: [2023-04-29 11:37:25,004] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 1: [2023-04-29 11:37:25,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 1: [2023-04-29 11:37:25,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +49: [2023-04-29 11:37:25,004] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +48: [2023-04-29 11:37:25,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. + 1: [2023-04-29 11:37:25,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +12: [2023-04-29 11:37:25,006] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +12: [2023-04-29 11:37:25,006] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 1: [2023-04-29 11:37:25,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 1: [2023-04-29 11:37:25,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +12: [2023-04-29 11:37:25,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +15: [2023-04-29 11:37:25,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +15: [2023-04-29 11:37:25,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +15: [2023-04-29 11:37:25,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +15: [2023-04-29 11:37:25,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +15: [2023-04-29 11:37:25,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +22: [2023-04-29 11:37:25,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +15: [2023-04-29 11:37:25,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +15: [2023-04-29 11:37:25,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +15: [2023-04-29 11:37:25,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +12: [2023-04-29 11:37:25,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +12: [2023-04-29 11:37:25,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +12: [2023-04-29 11:37:25,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +12: [2023-04-29 11:37:25,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +48: [2023-04-29 11:37:25,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +12: [2023-04-29 11:37:25,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +28: [2023-04-29 11:37:25,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +28: [2023-04-29 11:37:25,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +28: [2023-04-29 11:37:25,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +28: [2023-04-29 11:37:25,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +28: [2023-04-29 11:37:25,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +28: [2023-04-29 11:37:25,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +22: [2023-04-29 11:37:25,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +28: [2023-04-29 11:37:25,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +22: [2023-04-29 11:37:25,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +14: [2023-04-29 11:37:25,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +28: [2023-04-29 11:37:25,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +22: [2023-04-29 11:37:25,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +22: [2023-04-29 11:37:25,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +22: [2023-04-29 11:37:25,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +22: [2023-04-29 11:37:25,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +22: [2023-04-29 11:37:25,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +23: [2023-04-29 11:37:25,010] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 1: [2023-04-29 11:37:25,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 1: [2023-04-29 11:37:25,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 1: [2023-04-29 11:37:25,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 1: [2023-04-29 11:37:25,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 6: [2023-04-29 11:37:25,012] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 6: [2023-04-29 11:37:25,012] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 1: [2023-04-29 11:37:25,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +48: [2023-04-29 11:37:25,012] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +17: [2023-04-29 11:37:25,012] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +23: [2023-04-29 11:37:25,012] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 1: [2023-04-29 11:37:25,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +15: [2023-04-29 11:37:25,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +15: [2023-04-29 11:37:25,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +15: [2023-04-29 11:37:25,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +15: [2023-04-29 11:37:25,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +15: [2023-04-29 11:37:25,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +59: [2023-04-29 11:37:25,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +59: [2023-04-29 11:37:25,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +15: [2023-04-29 11:37:25,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +15: [2023-04-29 11:37:25,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +48: [2023-04-29 11:37:25,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +15: [2023-04-29 11:37:25,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +30: [2023-04-29 11:37:25,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +12: [2023-04-29 11:37:25,016] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +27: [2023-04-29 11:37:25,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +27: [2023-04-29 11:37:25,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +27: [2023-04-29 11:37:25,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +27: [2023-04-29 11:37:25,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +27: [2023-04-29 11:37:25,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +27: [2023-04-29 11:37:25,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +27: [2023-04-29 11:37:25,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +27: [2023-04-29 11:37:25,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 6: [2023-04-29 11:37:25,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 6: [2023-04-29 11:37:25,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 6: [2023-04-29 11:37:25,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 6: [2023-04-29 11:37:25,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 6: [2023-04-29 11:37:25,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 6: [2023-04-29 11:37:25,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +35: [2023-04-29 11:37:25,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +35: [2023-04-29 11:37:25,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +35: [2023-04-29 11:37:25,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +35: [2023-04-29 11:37:25,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +25: [2023-04-29 11:37:25,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +38: [2023-04-29 11:37:25,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +10: [2023-04-29 11:37:25,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +10: [2023-04-29 11:37:25,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +10: [2023-04-29 11:37:25,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +10: [2023-04-29 11:37:25,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +10: [2023-04-29 11:37:25,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +10: [2023-04-29 11:37:25,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +10: [2023-04-29 11:37:25,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +10: [2023-04-29 11:37:25,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +23: [2023-04-29 11:37:25,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +23: [2023-04-29 11:37:25,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 6: [2023-04-29 11:37:25,019] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +12: [2023-04-29 11:37:25,019] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 6: [2023-04-29 11:37:25,019] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +42: [2023-04-29 11:37:25,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +42: [2023-04-29 11:37:25,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +55: [2023-04-29 11:37:25,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +17: [2023-04-29 11:37:25,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +17: [2023-04-29 11:37:25,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +42: [2023-04-29 11:37:25,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +42: [2023-04-29 11:37:25,020] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +17: [2023-04-29 11:37:25,020] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +12: [2023-04-29 11:37:25,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +42: [2023-04-29 11:37:25,020] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +42: [2023-04-29 11:37:25,020] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +42: [2023-04-29 11:37:25,020] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +42: [2023-04-29 11:37:25,020] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +59: [2023-04-29 11:37:25,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +59: [2023-04-29 11:37:25,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +30: [2023-04-29 11:37:25,022] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +27: [2023-04-29 11:37:25,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +12: [2023-04-29 11:37:25,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +46: [2023-04-29 11:37:25,022] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +27: [2023-04-29 11:37:25,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +27: [2023-04-29 11:37:25,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +27: [2023-04-29 11:37:25,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +27: [2023-04-29 11:37:25,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +27: [2023-04-29 11:37:25,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +38: [2023-04-29 11:37:25,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +27: [2023-04-29 11:37:25,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +27: [2023-04-29 11:37:25,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +12: [2023-04-29 11:37:25,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 6: [2023-04-29 11:37:25,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 6: [2023-04-29 11:37:25,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +12: [2023-04-29 11:37:25,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +10: [2023-04-29 11:37:25,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 6: [2023-04-29 11:37:25,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +30: [2023-04-29 11:37:25,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +30: [2023-04-29 11:37:25,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +55: [2023-04-29 11:37:25,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +10: [2023-04-29 11:37:25,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +42: [2023-04-29 11:37:25,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... + 6: [2023-04-29 11:37:25,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +10: [2023-04-29 11:37:25,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +12: [2023-04-29 11:37:25,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +10: [2023-04-29 11:37:25,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +46: [2023-04-29 11:37:25,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +10: [2023-04-29 11:37:25,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +12: [2023-04-29 11:37:25,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +42: [2023-04-29 11:37:25,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 6: [2023-04-29 11:37:25,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +42: [2023-04-29 11:37:25,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +10: [2023-04-29 11:37:25,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +10: [2023-04-29 11:37:25,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +52: [2023-04-29 11:37:25,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +25: [2023-04-29 11:37:25,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +42: [2023-04-29 11:37:25,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... + 6: [2023-04-29 11:37:25,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +10: [2023-04-29 11:37:25,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +55: [2023-04-29 11:37:25,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +55: [2023-04-29 11:37:25,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +46: [2023-04-29 11:37:25,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +46: [2023-04-29 11:37:25,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +46: [2023-04-29 11:37:25,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +38: [2023-04-29 11:37:25,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +38: [2023-04-29 11:37:25,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +42: [2023-04-29 11:37:25,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +42: [2023-04-29 11:37:25,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +42: [2023-04-29 11:37:25,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +42: [2023-04-29 11:37:25,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +54: [2023-04-29 11:37:25,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +54: [2023-04-29 11:37:25,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +54: [2023-04-29 11:37:25,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +54: [2023-04-29 11:37:25,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +54: [2023-04-29 11:37:25,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +54: [2023-04-29 11:37:25,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +54: [2023-04-29 11:37:25,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +54: [2023-04-29 11:37:25,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +46: [2023-04-29 11:37:25,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +48: [2023-04-29 11:37:25,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +52: [2023-04-29 11:37:25,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +52: [2023-04-29 11:37:25,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +46: [2023-04-29 11:37:25,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +46: [2023-04-29 11:37:25,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +46: [2023-04-29 11:37:25,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +46: [2023-04-29 11:37:25,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +14: [2023-04-29 11:37:25,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +52: [2023-04-29 11:37:25,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +41: [2023-04-29 11:37:25,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +41: [2023-04-29 11:37:25,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +41: [2023-04-29 11:37:25,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +41: [2023-04-29 11:37:25,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +41: [2023-04-29 11:37:25,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +41: [2023-04-29 11:37:25,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +41: [2023-04-29 11:37:25,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +41: [2023-04-29 11:37:25,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +25: [2023-04-29 11:37:25,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +46: [2023-04-29 11:37:25,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +48: [2023-04-29 11:37:25,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +54: [2023-04-29 11:37:25,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +54: [2023-04-29 11:37:25,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +23: [2023-04-29 11:37:25,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +40: [2023-04-29 11:37:25,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +54: [2023-04-29 11:37:25,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +54: [2023-04-29 11:37:25,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +54: [2023-04-29 11:37:25,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +25: [2023-04-29 11:37:25,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +54: [2023-04-29 11:37:25,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +54: [2023-04-29 11:37:25,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +54: [2023-04-29 11:37:25,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +14: [2023-04-29 11:37:25,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +19: [2023-04-29 11:37:25,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +19: [2023-04-29 11:37:25,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +41: [2023-04-29 11:37:25,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +48: [2023-04-29 11:37:25,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +17: [2023-04-29 11:37:25,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +30: [2023-04-29 11:37:25,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +41: [2023-04-29 11:37:25,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +41: [2023-04-29 11:37:25,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +19: [2023-04-29 11:37:25,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +19: [2023-04-29 11:37:25,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +19: [2023-04-29 11:37:25,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +19: [2023-04-29 11:37:25,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +19: [2023-04-29 11:37:25,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +19: [2023-04-29 11:37:25,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +23: [2023-04-29 11:37:25,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +46: [2023-04-29 11:37:25,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +38: [2023-04-29 11:37:25,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +48: [2023-04-29 11:37:25,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +41: [2023-04-29 11:37:25,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +41: [2023-04-29 11:37:25,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +55: [2023-04-29 11:37:25,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +41: [2023-04-29 11:37:25,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +19: [2023-04-29 11:37:25,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +19: [2023-04-29 11:37:25,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +41: [2023-04-29 11:37:25,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +41: [2023-04-29 11:37:25,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +35: [2023-04-29 11:37:25,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +19: [2023-04-29 11:37:25,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +19: [2023-04-29 11:37:25,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +25: [2023-04-29 11:37:25,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +19: [2023-04-29 11:37:25,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +35: [2023-04-29 11:37:25,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +19: [2023-04-29 11:37:25,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +19: [2023-04-29 11:37:25,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +43: [2023-04-29 11:37:25,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +50: [2023-04-29 11:37:25,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +23: [2023-04-29 11:37:25,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +23: [2023-04-29 11:37:25,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +19: [2023-04-29 11:37:25,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +17: [2023-04-29 11:37:25,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +62: [2023-04-29 11:37:25,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +62: [2023-04-29 11:37:25,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +35: [2023-04-29 11:37:25,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +34: [2023-04-29 11:37:25,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +34: [2023-04-29 11:37:25,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +35: [2023-04-29 11:37:25,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +17: [2023-04-29 11:37:25,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +38: [2023-04-29 11:37:25,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +40: [2023-04-29 11:37:25,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +40: [2023-04-29 11:37:25,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +40: [2023-04-29 11:37:25,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +17: [2023-04-29 11:37:25,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +52: [2023-04-29 11:37:25,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +55: [2023-04-29 11:37:25,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +61: [2023-04-29 11:37:25,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +61: [2023-04-29 11:37:25,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. + 9: [2023-04-29 11:37:25,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +13: [2023-04-29 11:37:25,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +13: [2023-04-29 11:37:25,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +13: [2023-04-29 11:37:25,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +55: [2023-04-29 11:37:25,052] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +55: [2023-04-29 11:37:25,052] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +13: [2023-04-29 11:37:25,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +13: [2023-04-29 11:37:25,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +13: [2023-04-29 11:37:25,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +13: [2023-04-29 11:37:25,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +60: [2023-04-29 11:37:25,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +60: [2023-04-29 11:37:25,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +13: [2023-04-29 11:37:25,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +61: [2023-04-29 11:37:25,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +61: [2023-04-29 11:37:25,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +61: [2023-04-29 11:37:25,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +61: [2023-04-29 11:37:25,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +61: [2023-04-29 11:37:25,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +61: [2023-04-29 11:37:25,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +30: [2023-04-29 11:37:25,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +30: [2023-04-29 11:37:25,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +39: [2023-04-29 11:37:25,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +25: [2023-04-29 11:37:25,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +46: [2023-04-29 11:37:25,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +38: [2023-04-29 11:37:25,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +38: [2023-04-29 11:37:25,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +43: [2023-04-29 11:37:25,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +39: [2023-04-29 11:37:25,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +30: [2023-04-29 11:37:25,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +43: [2023-04-29 11:37:25,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +43: [2023-04-29 11:37:25,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +33: [2023-04-29 11:37:25,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +33: [2023-04-29 11:37:25,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +33: [2023-04-29 11:37:25,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +33: [2023-04-29 11:37:25,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +33: [2023-04-29 11:37:25,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +33: [2023-04-29 11:37:25,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +33: [2023-04-29 11:37:25,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +52: [2023-04-29 11:37:25,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 9: [2023-04-29 11:37:25,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +33: [2023-04-29 11:37:25,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +13: [2023-04-29 11:37:25,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +13: [2023-04-29 11:37:25,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +60: [2023-04-29 11:37:25,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +60: [2023-04-29 11:37:25,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +13: [2023-04-29 11:37:25,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 9: [2023-04-29 11:37:25,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 9: [2023-04-29 11:37:25,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +52: [2023-04-29 11:37:25,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +61: [2023-04-29 11:37:25,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +62: [2023-04-29 11:37:25,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +62: [2023-04-29 11:37:25,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +34: [2023-04-29 11:37:25,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +52: [2023-04-29 11:37:25,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +61: [2023-04-29 11:37:25,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +61: [2023-04-29 11:37:25,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +61: [2023-04-29 11:37:25,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +61: [2023-04-29 11:37:25,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +34: [2023-04-29 11:37:25,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +40: [2023-04-29 11:37:25,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +39: [2023-04-29 11:37:25,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +39: [2023-04-29 11:37:25,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +13: [2023-04-29 11:37:25,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +61: [2023-04-29 11:37:25,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +13: [2023-04-29 11:37:25,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +13: [2023-04-29 11:37:25,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +13: [2023-04-29 11:37:25,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +13: [2023-04-29 11:37:25,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +46: [2023-04-29 11:37:25,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +61: [2023-04-29 11:37:25,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +61: [2023-04-29 11:37:25,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +46: [2023-04-29 11:37:25,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +46: [2023-04-29 11:37:25,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +50: [2023-04-29 11:37:25,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +33: [2023-04-29 11:37:25,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +50: [2023-04-29 11:37:25,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +33: [2023-04-29 11:37:25,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +25: [2023-04-29 11:37:25,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +33: [2023-04-29 11:37:25,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +33: [2023-04-29 11:37:25,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 1: [2023-04-29 11:37:25,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +33: [2023-04-29 11:37:25,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +33: [2023-04-29 11:37:25,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +33: [2023-04-29 11:37:25,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +33: [2023-04-29 11:37:25,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +32: [2023-04-29 11:37:25,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +32: [2023-04-29 11:37:25,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +32: [2023-04-29 11:37:25,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +50: [2023-04-29 11:37:25,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +11: [2023-04-29 11:37:25,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +11: [2023-04-29 11:37:25,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +11: [2023-04-29 11:37:25,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +11: [2023-04-29 11:37:25,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +11: [2023-04-29 11:37:25,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +28: [2023-04-29 11:37:25,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +11: [2023-04-29 11:37:25,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +11: [2023-04-29 11:37:25,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +11: [2023-04-29 11:37:25,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +22: [2023-04-29 11:37:25,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +15: [2023-04-29 11:37:25,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +50: [2023-04-29 11:37:25,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +25: [2023-04-29 11:37:25,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +43: [2023-04-29 11:37:25,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +34: [2023-04-29 11:37:25,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 1: [2023-04-29 11:37:25,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +34: [2023-04-29 11:37:25,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +26: [2023-04-29 11:37:25,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +26: [2023-04-29 11:37:25,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +28: [2023-04-29 11:37:25,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +28: [2023-04-29 11:37:25,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +28: [2023-04-29 11:37:25,075] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +11: [2023-04-29 11:37:25,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +62: [2023-04-29 11:37:25,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +62: [2023-04-29 11:37:25,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +11: [2023-04-29 11:37:25,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +11: [2023-04-29 11:37:25,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +32: [2023-04-29 11:37:25,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +11: [2023-04-29 11:37:25,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +11: [2023-04-29 11:37:25,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +40: [2023-04-29 11:37:25,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +11: [2023-04-29 11:37:25,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +26: [2023-04-29 11:37:25,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +26: [2023-04-29 11:37:25,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +26: [2023-04-29 11:37:25,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +26: [2023-04-29 11:37:25,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +26: [2023-04-29 11:37:25,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +26: [2023-04-29 11:37:25,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +11: [2023-04-29 11:37:25,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 1: [2023-04-29 11:37:25,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +11: [2023-04-29 11:37:25,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +40: [2023-04-29 11:37:25,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +60: [2023-04-29 11:37:25,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +16: [2023-04-29 11:37:25,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +16: [2023-04-29 11:37:25,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +60: [2023-04-29 11:37:25,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +22: [2023-04-29 11:37:25,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +22: [2023-04-29 11:37:25,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +22: [2023-04-29 11:37:25,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +16: [2023-04-29 11:37:25,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +16: [2023-04-29 11:37:25,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +16: [2023-04-29 11:37:25,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +16: [2023-04-29 11:37:25,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +16: [2023-04-29 11:37:25,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +39: [2023-04-29 11:37:25,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +16: [2023-04-29 11:37:25,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +39: [2023-04-29 11:37:25,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +15: [2023-04-29 11:37:25,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +15: [2023-04-29 11:37:25,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +15: [2023-04-29 11:37:25,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +40: [2023-04-29 11:37:25,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +43: [2023-04-29 11:37:25,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +26: [2023-04-29 11:37:25,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +26: [2023-04-29 11:37:25,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +43: [2023-04-29 11:37:25,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 1: [2023-04-29 11:37:25,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 6: [2023-04-29 11:37:25,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +26: [2023-04-29 11:37:25,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +26: [2023-04-29 11:37:25,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +27: [2023-04-29 11:37:25,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +43: [2023-04-29 11:37:25,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +26: [2023-04-29 11:37:25,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +62: [2023-04-29 11:37:25,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +62: [2023-04-29 11:37:25,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +26: [2023-04-29 11:37:25,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +16: [2023-04-29 11:37:25,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +16: [2023-04-29 11:37:25,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +26: [2023-04-29 11:37:25,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +26: [2023-04-29 11:37:25,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +39: [2023-04-29 11:37:25,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +39: [2023-04-29 11:37:25,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +34: [2023-04-29 11:37:25,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +60: [2023-04-29 11:37:25,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +12: [2023-04-29 11:37:25,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 1: [2023-04-29 11:37:25,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +31: [2023-04-29 11:37:25,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +31: [2023-04-29 11:37:25,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +27: [2023-04-29 11:37:25,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +31: [2023-04-29 11:37:25,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +31: [2023-04-29 11:37:25,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +31: [2023-04-29 11:37:25,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +31: [2023-04-29 11:37:25,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +31: [2023-04-29 11:37:25,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +31: [2023-04-29 11:37:25,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +27: [2023-04-29 11:37:25,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +27: [2023-04-29 11:37:25,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 6: [2023-04-29 11:37:25,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +60: [2023-04-29 11:37:25,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +10: [2023-04-29 11:37:25,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. + 9: [2023-04-29 11:37:25,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 6: [2023-04-29 11:37:25,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +34: [2023-04-29 11:37:25,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +12: [2023-04-29 11:37:25,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +12: [2023-04-29 11:37:25,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +42: [2023-04-29 11:37:25,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +42: [2023-04-29 11:37:25,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +42: [2023-04-29 11:37:25,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +42: [2023-04-29 11:37:25,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +16: [2023-04-29 11:37:25,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... + 6: [2023-04-29 11:37:25,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +16: [2023-04-29 11:37:25,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +10: [2023-04-29 11:37:25,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +10: [2023-04-29 11:37:25,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +10: [2023-04-29 11:37:25,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +16: [2023-04-29 11:37:25,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +16: [2023-04-29 11:37:25,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +16: [2023-04-29 11:37:25,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +31: [2023-04-29 11:37:25,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +16: [2023-04-29 11:37:25,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +31: [2023-04-29 11:37:25,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +31: [2023-04-29 11:37:25,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +31: [2023-04-29 11:37:25,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +15: [2023-04-29 11:37:25,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +54: [2023-04-29 11:37:25,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +41: [2023-04-29 11:37:25,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +22: [2023-04-29 11:37:25,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +50: [2023-04-29 11:37:25,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +50: [2023-04-29 11:37:25,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +28: [2023-04-29 11:37:25,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +31: [2023-04-29 11:37:25,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +31: [2023-04-29 11:37:25,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +31: [2023-04-29 11:37:25,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... + 1: [2023-04-29 11:37:25,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +12: [2023-04-29 11:37:25,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +31: [2023-04-29 11:37:25,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +32: [2023-04-29 11:37:25,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +54: [2023-04-29 11:37:25,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +28: [2023-04-29 11:37:25,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +28: [2023-04-29 11:37:25,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +54: [2023-04-29 11:37:25,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +50: [2023-04-29 11:37:25,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 9: [2023-04-29 11:37:25,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +32: [2023-04-29 11:37:25,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +32: [2023-04-29 11:37:25,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +22: [2023-04-29 11:37:25,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 1: [2023-04-29 11:37:25,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 9: [2023-04-29 11:37:25,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +15: [2023-04-29 11:37:25,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 9: [2023-04-29 11:37:25,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +22: [2023-04-29 11:37:25,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +22: [2023-04-29 11:37:25,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +19: [2023-04-29 11:37:25,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +19: [2023-04-29 11:37:25,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +15: [2023-04-29 11:37:25,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +54: [2023-04-29 11:37:25,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +15: [2023-04-29 11:37:25,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +28: [2023-04-29 11:37:25,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +41: [2023-04-29 11:37:25,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. + 6: [2023-04-29 11:37:25,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +27: [2023-04-29 11:37:25,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +41: [2023-04-29 11:37:25,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. + 1: [2023-04-29 11:37:25,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +41: [2023-04-29 11:37:25,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +19: [2023-04-29 11:37:25,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +19: [2023-04-29 11:37:25,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +10: [2023-04-29 11:37:25,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +18: [2023-04-29 11:37:25,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +18: [2023-04-29 11:37:25,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +18: [2023-04-29 11:37:25,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +18: [2023-04-29 11:37:25,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +18: [2023-04-29 11:37:25,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +18: [2023-04-29 11:37:25,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +18: [2023-04-29 11:37:25,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +18: [2023-04-29 11:37:25,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +27: [2023-04-29 11:37:25,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +41: [2023-04-29 11:37:25,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +61: [2023-04-29 11:37:25,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +13: [2023-04-29 11:37:25,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +13: [2023-04-29 11:37:25,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +42: [2023-04-29 11:37:25,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +27: [2023-04-29 11:37:25,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +27: [2023-04-29 11:37:25,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +47: [2023-04-29 11:37:25,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +47: [2023-04-29 11:37:25,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +47: [2023-04-29 11:37:25,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. + 6: [2023-04-29 11:37:25,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +47: [2023-04-29 11:37:25,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. + 6: [2023-04-29 11:37:25,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +42: [2023-04-29 11:37:25,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +10: [2023-04-29 11:37:25,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +61: [2023-04-29 11:37:25,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +12: [2023-04-29 11:37:25,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +18: [2023-04-29 11:37:25,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +10: [2023-04-29 11:37:25,123] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +18: [2023-04-29 11:37:25,123] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +18: [2023-04-29 11:37:25,123] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +10: [2023-04-29 11:37:25,123] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 6: [2023-04-29 11:37:25,123] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +54: [2023-04-29 11:37:25,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +13: [2023-04-29 11:37:25,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +13: [2023-04-29 11:37:25,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +32: [2023-04-29 11:37:25,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +18: [2023-04-29 11:37:25,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +54: [2023-04-29 11:37:25,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +18: [2023-04-29 11:37:25,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +42: [2023-04-29 11:37:25,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +42: [2023-04-29 11:37:25,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +18: [2023-04-29 11:37:25,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +12: [2023-04-29 11:37:25,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +18: [2023-04-29 11:37:25,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt... +18: [2023-04-29 11:37:25,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt... +12: [2023-04-29 11:37:25,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +61: [2023-04-29 11:37:25,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +61: [2023-04-29 11:37:25,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +54: [2023-04-29 11:37:25,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +33: [2023-04-29 11:37:25,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +33: [2023-04-29 11:37:25,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +19: [2023-04-29 11:37:25,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +53: [2023-04-29 11:37:25,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +53: [2023-04-29 11:37:25,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +11: [2023-04-29 11:37:25,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +33: [2023-04-29 11:37:25,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +19: [2023-04-29 11:37:25,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +53: [2023-04-29 11:37:25,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +53: [2023-04-29 11:37:25,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +53: [2023-04-29 11:37:25,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +53: [2023-04-29 11:37:25,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +53: [2023-04-29 11:37:25,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +54: [2023-04-29 11:37:25,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +53: [2023-04-29 11:37:25,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +19: [2023-04-29 11:37:25,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +33: [2023-04-29 11:37:25,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +53: [2023-04-29 11:37:25,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +41: [2023-04-29 11:37:25,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +19: [2023-04-29 11:37:25,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +11: [2023-04-29 11:37:25,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +53: [2023-04-29 11:37:25,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +53: [2023-04-29 11:37:25,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +41: [2023-04-29 11:37:25,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +53: [2023-04-29 11:37:25,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +41: [2023-04-29 11:37:25,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +53: [2023-04-29 11:37:25,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +12: [2023-04-29 11:37:25,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +61: [2023-04-29 11:37:25,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +53: [2023-04-29 11:37:25,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +53: [2023-04-29 11:37:25,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt... +53: [2023-04-29 11:37:25,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt... +11: [2023-04-29 11:37:25,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +11: [2023-04-29 11:37:25,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +47: [2023-04-29 11:37:25,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +13: [2023-04-29 11:37:25,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +26: [2023-04-29 11:37:25,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +13: [2023-04-29 11:37:25,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +47: [2023-04-29 11:37:25,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +61: [2023-04-29 11:37:25,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +47: [2023-04-29 11:37:25,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +47: [2023-04-29 11:37:25,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +26: [2023-04-29 11:37:25,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +26: [2023-04-29 11:37:25,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +13: [2023-04-29 11:37:25,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +13: [2023-04-29 11:37:25,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +26: [2023-04-29 11:37:25,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +33: [2023-04-29 11:37:25,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +33: [2023-04-29 11:37:25,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +61: [2023-04-29 11:37:25,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +11: [2023-04-29 11:37:25,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +31: [2023-04-29 11:37:25,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +31: [2023-04-29 11:37:25,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +31: [2023-04-29 11:37:25,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +61: [2023-04-29 11:37:25,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +31: [2023-04-29 11:37:25,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +16: [2023-04-29 11:37:25,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +16: [2023-04-29 11:37:25,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +16: [2023-04-29 11:37:25,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +33: [2023-04-29 11:37:25,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +33: [2023-04-29 11:37:25,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +16: [2023-04-29 11:37:25,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +11: [2023-04-29 11:37:25,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +26: [2023-04-29 11:37:25,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +11: [2023-04-29 11:37:25,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +11: [2023-04-29 11:37:25,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +26: [2023-04-29 11:37:25,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +26: [2023-04-29 11:37:25,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +26: [2023-04-29 11:37:25,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +18: [2023-04-29 11:37:25,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +18: [2023-04-29 11:37:25,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +18: [2023-04-29 11:37:25,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +31: [2023-04-29 11:37:25,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +31: [2023-04-29 11:37:25,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +31: [2023-04-29 11:37:25,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +31: [2023-04-29 11:37:25,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +18: [2023-04-29 11:37:25,197] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_00-model_states.pt. +16: [2023-04-29 11:37:25,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +16: [2023-04-29 11:37:25,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +53: [2023-04-29 11:37:25,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +16: [2023-04-29 11:37:25,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +16: [2023-04-29 11:37:25,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +18: [2023-04-29 11:37:25,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +53: [2023-04-29 11:37:25,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +53: [2023-04-29 11:37:25,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +53: [2023-04-29 11:37:25,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_00-model_states.pt. +18: [2023-04-29 11:37:25,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +18: [2023-04-29 11:37:25,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +53: [2023-04-29 11:37:25,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +18: [2023-04-29 11:37:25,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +53: [2023-04-29 11:37:25,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +53: [2023-04-29 11:37:25,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +53: [2023-04-29 11:37:25,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +44: [2023-04-29 11:37:25,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +44: [2023-04-29 11:37:25,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +44: [2023-04-29 11:37:25,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +44: [2023-04-29 11:37:25,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +44: [2023-04-29 11:37:25,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +44: [2023-04-29 11:37:25,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +44: [2023-04-29 11:37:25,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +44: [2023-04-29 11:37:25,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +63: [2023-04-29 11:37:25,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +63: [2023-04-29 11:37:25,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +63: [2023-04-29 11:37:25,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +63: [2023-04-29 11:37:25,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +63: [2023-04-29 11:37:25,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +63: [2023-04-29 11:37:25,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +63: [2023-04-29 11:37:25,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +63: [2023-04-29 11:37:25,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +51: [2023-04-29 11:37:25,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +51: [2023-04-29 11:37:25,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +51: [2023-04-29 11:37:25,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +51: [2023-04-29 11:37:25,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +33: [2023-04-29 11:37:25,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +33: [2023-04-29 11:37:25,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +33: [2023-04-29 11:37:25,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +33: [2023-04-29 11:37:25,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +57: [2023-04-29 11:37:25,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +57: [2023-04-29 11:37:25,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +57: [2023-04-29 11:37:25,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +57: [2023-04-29 11:37:25,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +54: [2023-04-29 11:37:25,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +54: [2023-04-29 11:37:25,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +54: [2023-04-29 11:37:25,345] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +54: [2023-04-29 11:37:25,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +51: [2023-04-29 11:37:25,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +51: [2023-04-29 11:37:25,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +51: [2023-04-29 11:37:25,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +51: [2023-04-29 11:37:25,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +46: [2023-04-29 11:37:25,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +46: [2023-04-29 11:37:25,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +33: [2023-04-29 11:37:25,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +33: [2023-04-29 11:37:25,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +33: [2023-04-29 11:37:25,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +33: [2023-04-29 11:37:25,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +46: [2023-04-29 11:37:25,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +46: [2023-04-29 11:37:25,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +57: [2023-04-29 11:37:25,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +57: [2023-04-29 11:37:25,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +46: [2023-04-29 11:37:25,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +46: [2023-04-29 11:37:25,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +46: [2023-04-29 11:37:25,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +57: [2023-04-29 11:37:25,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +46: [2023-04-29 11:37:25,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +57: [2023-04-29 11:37:25,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +48: [2023-04-29 11:37:25,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +48: [2023-04-29 11:37:25,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +48: [2023-04-29 11:37:25,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +54: [2023-04-29 11:37:25,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +54: [2023-04-29 11:37:25,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +48: [2023-04-29 11:37:25,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +54: [2023-04-29 11:37:25,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +54: [2023-04-29 11:37:25,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +48: [2023-04-29 11:37:25,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +48: [2023-04-29 11:37:25,405] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +48: [2023-04-29 11:37:25,405] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +48: [2023-04-29 11:37:25,405] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +36: [2023-04-29 11:37:25,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +36: [2023-04-29 11:37:25,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +36: [2023-04-29 11:37:25,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +49: [2023-04-29 11:37:25,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +49: [2023-04-29 11:37:25,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +49: [2023-04-29 11:37:25,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +36: [2023-04-29 11:37:25,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +58: [2023-04-29 11:37:25,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +58: [2023-04-29 11:37:25,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +58: [2023-04-29 11:37:25,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +49: [2023-04-29 11:37:25,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +58: [2023-04-29 11:37:25,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +56: [2023-04-29 11:37:25,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +56: [2023-04-29 11:37:25,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +56: [2023-04-29 11:37:25,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +56: [2023-04-29 11:37:25,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +48: [2023-04-29 11:37:25,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +48: [2023-04-29 11:37:25,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +48: [2023-04-29 11:37:25,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +48: [2023-04-29 11:37:25,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +29: [2023-04-29 11:37:25,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +29: [2023-04-29 11:37:25,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +29: [2023-04-29 11:37:25,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +29: [2023-04-29 11:37:25,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +48: [2023-04-29 11:37:25,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +48: [2023-04-29 11:37:25,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +48: [2023-04-29 11:37:25,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +48: [2023-04-29 11:37:25,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +46: [2023-04-29 11:37:25,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +38: [2023-04-29 11:37:25,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +38: [2023-04-29 11:37:25,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +38: [2023-04-29 11:37:25,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +38: [2023-04-29 11:37:25,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +46: [2023-04-29 11:37:25,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +36: [2023-04-29 11:37:25,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +40: [2023-04-29 11:37:25,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +40: [2023-04-29 11:37:25,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +40: [2023-04-29 11:37:25,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +40: [2023-04-29 11:37:25,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +58: [2023-04-29 11:37:25,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +36: [2023-04-29 11:37:25,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +58: [2023-04-29 11:37:25,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +56: [2023-04-29 11:37:25,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +56: [2023-04-29 11:37:25,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +56: [2023-04-29 11:37:25,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +56: [2023-04-29 11:37:25,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +49: [2023-04-29 11:37:25,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +49: [2023-04-29 11:37:25,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 3: [2023-04-29 11:37:25,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 3: [2023-04-29 11:37:25,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +49: [2023-04-29 11:37:25,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 3: [2023-04-29 11:37:25,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +49: [2023-04-29 11:37:25,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +58: [2023-04-29 11:37:25,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +58: [2023-04-29 11:37:25,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 3: [2023-04-29 11:37:25,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +46: [2023-04-29 11:37:25,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +46: [2023-04-29 11:37:25,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +36: [2023-04-29 11:37:25,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +36: [2023-04-29 11:37:25,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 8: [2023-04-29 11:37:25,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 8: [2023-04-29 11:37:25,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +43: [2023-04-29 11:37:25,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +43: [2023-04-29 11:37:25,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +43: [2023-04-29 11:37:25,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. + 8: [2023-04-29 11:37:25,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +43: [2023-04-29 11:37:25,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. + 8: [2023-04-29 11:37:25,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +29: [2023-04-29 11:37:25,442] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +34: [2023-04-29 11:37:25,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +34: [2023-04-29 11:37:25,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +34: [2023-04-29 11:37:25,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +34: [2023-04-29 11:37:25,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +29: [2023-04-29 11:37:25,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +46: [2023-04-29 11:37:25,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +29: [2023-04-29 11:37:25,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +29: [2023-04-29 11:37:25,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +46: [2023-04-29 11:37:25,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +46: [2023-04-29 11:37:25,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +46: [2023-04-29 11:37:25,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +54: [2023-04-29 11:37:25,448] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +54: [2023-04-29 11:37:25,448] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +45: [2023-04-29 11:37:25,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +45: [2023-04-29 11:37:25,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +46: [2023-04-29 11:37:25,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +45: [2023-04-29 11:37:25,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +38: [2023-04-29 11:37:25,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +38: [2023-04-29 11:37:25,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +45: [2023-04-29 11:37:25,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +38: [2023-04-29 11:37:25,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +54: [2023-04-29 11:37:25,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +54: [2023-04-29 11:37:25,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +54: [2023-04-29 11:37:25,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +54: [2023-04-29 11:37:25,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +54: [2023-04-29 11:37:25,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +38: [2023-04-29 11:37:25,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +54: [2023-04-29 11:37:25,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +54: [2023-04-29 11:37:25,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +54: [2023-04-29 11:37:25,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +54: [2023-04-29 11:37:25,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +54: [2023-04-29 11:37:25,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +54: [2023-04-29 11:37:25,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +54: [2023-04-29 11:37:25,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +54: [2023-04-29 11:37:25,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +54: [2023-04-29 11:37:25,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +24: [2023-04-29 11:37:25,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +24: [2023-04-29 11:37:25,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +24: [2023-04-29 11:37:25,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +24: [2023-04-29 11:37:25,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +40: [2023-04-29 11:37:25,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +40: [2023-04-29 11:37:25,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +40: [2023-04-29 11:37:25,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +40: [2023-04-29 11:37:25,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +46: [2023-04-29 11:37:25,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 3: [2023-04-29 11:37:25,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 3: [2023-04-29 11:37:25,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 3: [2023-04-29 11:37:25,463] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 3: [2023-04-29 11:37:25,463] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +46: [2023-04-29 11:37:25,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +46: [2023-04-29 11:37:25,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... + 8: [2023-04-29 11:37:25,466] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +33: [2023-04-29 11:37:25,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +33: [2023-04-29 11:37:25,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +33: [2023-04-29 11:37:25,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +33: [2023-04-29 11:37:25,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +33: [2023-04-29 11:37:25,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +33: [2023-04-29 11:37:25,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +33: [2023-04-29 11:37:25,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +33: [2023-04-29 11:37:25,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +34: [2023-04-29 11:37:25,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +43: [2023-04-29 11:37:25,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +34: [2023-04-29 11:37:25,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +43: [2023-04-29 11:37:25,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +43: [2023-04-29 11:37:25,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +43: [2023-04-29 11:37:25,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +48: [2023-04-29 11:37:25,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +34: [2023-04-29 11:37:25,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +34: [2023-04-29 11:37:25,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +33: [2023-04-29 11:37:25,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... + 8: [2023-04-29 11:37:25,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +33: [2023-04-29 11:37:25,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +33: [2023-04-29 11:37:25,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +33: [2023-04-29 11:37:25,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... + 8: [2023-04-29 11:37:25,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +33: [2023-04-29 11:37:25,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +33: [2023-04-29 11:37:25,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +33: [2023-04-29 11:37:25,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +46: [2023-04-29 11:37:25,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +33: [2023-04-29 11:37:25,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +48: [2023-04-29 11:37:25,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... + 8: [2023-04-29 11:37:25,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +62: [2023-04-29 11:37:25,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +62: [2023-04-29 11:37:25,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +62: [2023-04-29 11:37:25,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +37: [2023-04-29 11:37:25,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +45: [2023-04-29 11:37:25,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +46: [2023-04-29 11:37:25,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +37: [2023-04-29 11:37:25,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +37: [2023-04-29 11:37:25,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +62: [2023-04-29 11:37:25,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +37: [2023-04-29 11:37:25,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +45: [2023-04-29 11:37:25,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +46: [2023-04-29 11:37:25,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +45: [2023-04-29 11:37:25,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +20: [2023-04-29 11:37:25,479] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +20: [2023-04-29 11:37:25,479] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +45: [2023-04-29 11:37:25,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +48: [2023-04-29 11:37:25,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +48: [2023-04-29 11:37:25,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +46: [2023-04-29 11:37:25,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +20: [2023-04-29 11:37:25,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +20: [2023-04-29 11:37:25,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +24: [2023-04-29 11:37:25,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +48: [2023-04-29 11:37:25,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +48: [2023-04-29 11:37:25,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +24: [2023-04-29 11:37:25,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +24: [2023-04-29 11:37:25,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +48: [2023-04-29 11:37:25,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +48: [2023-04-29 11:37:25,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +24: [2023-04-29 11:37:25,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +48: [2023-04-29 11:37:25,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +60: [2023-04-29 11:37:25,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +60: [2023-04-29 11:37:25,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +60: [2023-04-29 11:37:25,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +60: [2023-04-29 11:37:25,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +52: [2023-04-29 11:37:25,495] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +52: [2023-04-29 11:37:25,495] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +52: [2023-04-29 11:37:25,495] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +52: [2023-04-29 11:37:25,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +48: [2023-04-29 11:37:25,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +48: [2023-04-29 11:37:25,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +37: [2023-04-29 11:37:25,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +48: [2023-04-29 11:37:25,505] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +37: [2023-04-29 11:37:25,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +37: [2023-04-29 11:37:25,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +37: [2023-04-29 11:37:25,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +54: [2023-04-29 11:37:25,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +20: [2023-04-29 11:37:25,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +48: [2023-04-29 11:37:25,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +20: [2023-04-29 11:37:25,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +20: [2023-04-29 11:37:25,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +20: [2023-04-29 11:37:25,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +62: [2023-04-29 11:37:25,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +62: [2023-04-29 11:37:25,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +62: [2023-04-29 11:37:25,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +54: [2023-04-29 11:37:25,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +62: [2023-04-29 11:37:25,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +52: [2023-04-29 11:37:25,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +48: [2023-04-29 11:37:25,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +59: [2023-04-29 11:37:25,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +59: [2023-04-29 11:37:25,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +48: [2023-04-29 11:37:25,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +59: [2023-04-29 11:37:25,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +59: [2023-04-29 11:37:25,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +60: [2023-04-29 11:37:25,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +60: [2023-04-29 11:37:25,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +33: [2023-04-29 11:37:25,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +52: [2023-04-29 11:37:25,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +54: [2023-04-29 11:37:25,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +46: [2023-04-29 11:37:25,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +52: [2023-04-29 11:37:25,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +60: [2023-04-29 11:37:25,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +60: [2023-04-29 11:37:25,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +52: [2023-04-29 11:37:25,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +46: [2023-04-29 11:37:25,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +54: [2023-04-29 11:37:25,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +46: [2023-04-29 11:37:25,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +33: [2023-04-29 11:37:25,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +48: [2023-04-29 11:37:25,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +46: [2023-04-29 11:37:25,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +54: [2023-04-29 11:37:25,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +44: [2023-04-29 11:37:25,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +44: [2023-04-29 11:37:25,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +44: [2023-04-29 11:37:25,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +44: [2023-04-29 11:37:25,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +44: [2023-04-29 11:37:25,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +44: [2023-04-29 11:37:25,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +44: [2023-04-29 11:37:25,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +44: [2023-04-29 11:37:25,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +37: [2023-04-29 11:37:25,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +37: [2023-04-29 11:37:25,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +37: [2023-04-29 11:37:25,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +37: [2023-04-29 11:37:25,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +58: [2023-04-29 11:37:25,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +58: [2023-04-29 11:37:25,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +58: [2023-04-29 11:37:25,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +58: [2023-04-29 11:37:25,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +58: [2023-04-29 11:37:25,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +58: [2023-04-29 11:37:25,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +58: [2023-04-29 11:37:25,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +58: [2023-04-29 11:37:25,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +46: [2023-04-29 11:37:25,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +35: [2023-04-29 11:37:25,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +35: [2023-04-29 11:37:25,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +35: [2023-04-29 11:37:25,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +35: [2023-04-29 11:37:25,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +35: [2023-04-29 11:37:25,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +35: [2023-04-29 11:37:25,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +35: [2023-04-29 11:37:25,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +35: [2023-04-29 11:37:25,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +44: [2023-04-29 11:37:25,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +44: [2023-04-29 11:37:25,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +44: [2023-04-29 11:37:25,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +44: [2023-04-29 11:37:25,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +44: [2023-04-29 11:37:25,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +44: [2023-04-29 11:37:25,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +44: [2023-04-29 11:37:25,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +44: [2023-04-29 11:37:25,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 5: [2023-04-29 11:37:25,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 5: [2023-04-29 11:37:25,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 5: [2023-04-29 11:37:25,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +50: [2023-04-29 11:37:25,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +50: [2023-04-29 11:37:25,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +50: [2023-04-29 11:37:25,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. + 5: [2023-04-29 11:37:25,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +50: [2023-04-29 11:37:25,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +33: [2023-04-29 11:37:25,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +33: [2023-04-29 11:37:25,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +37: [2023-04-29 11:37:25,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +59: [2023-04-29 11:37:25,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +46: [2023-04-29 11:37:25,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +35: [2023-04-29 11:37:25,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +37: [2023-04-29 11:37:25,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +37: [2023-04-29 11:37:25,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +37: [2023-04-29 11:37:25,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +46: [2023-04-29 11:37:25,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +54: [2023-04-29 11:37:25,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +58: [2023-04-29 11:37:25,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +58: [2023-04-29 11:37:25,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +58: [2023-04-29 11:37:25,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +58: [2023-04-29 11:37:25,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +59: [2023-04-29 11:37:25,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +58: [2023-04-29 11:37:25,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +58: [2023-04-29 11:37:25,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +59: [2023-04-29 11:37:25,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +58: [2023-04-29 11:37:25,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +58: [2023-04-29 11:37:25,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +33: [2023-04-29 11:37:25,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +35: [2023-04-29 11:37:25,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +35: [2023-04-29 11:37:25,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +35: [2023-04-29 11:37:25,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +35: [2023-04-29 11:37:25,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +35: [2023-04-29 11:37:25,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +35: [2023-04-29 11:37:25,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +59: [2023-04-29 11:37:25,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +39: [2023-04-29 11:37:25,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +39: [2023-04-29 11:37:25,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +49: [2023-04-29 11:37:25,551] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +49: [2023-04-29 11:37:25,551] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +49: [2023-04-29 11:37:25,551] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +49: [2023-04-29 11:37:25,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +49: [2023-04-29 11:37:25,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +49: [2023-04-29 11:37:25,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +49: [2023-04-29 11:37:25,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +49: [2023-04-29 11:37:25,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +39: [2023-04-29 11:37:25,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +35: [2023-04-29 11:37:25,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +46: [2023-04-29 11:37:25,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +39: [2023-04-29 11:37:25,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +54: [2023-04-29 11:37:25,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +21: [2023-04-29 11:37:25,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +21: [2023-04-29 11:37:25,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +21: [2023-04-29 11:37:25,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +21: [2023-04-29 11:37:25,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +45: [2023-04-29 11:37:25,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +45: [2023-04-29 11:37:25,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +45: [2023-04-29 11:37:25,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +45: [2023-04-29 11:37:25,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +49: [2023-04-29 11:37:25,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +20: [2023-04-29 11:37:25,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +20: [2023-04-29 11:37:25,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +20: [2023-04-29 11:37:25,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +45: [2023-04-29 11:37:25,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +45: [2023-04-29 11:37:25,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +45: [2023-04-29 11:37:25,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +20: [2023-04-29 11:37:25,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +45: [2023-04-29 11:37:25,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +49: [2023-04-29 11:37:25,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +49: [2023-04-29 11:37:25,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +49: [2023-04-29 11:37:25,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +49: [2023-04-29 11:37:25,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +49: [2023-04-29 11:37:25,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +49: [2023-04-29 11:37:25,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +54: [2023-04-29 11:37:25,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +49: [2023-04-29 11:37:25,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +47: [2023-04-29 11:37:25,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +47: [2023-04-29 11:37:25,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +47: [2023-04-29 11:37:25,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +47: [2023-04-29 11:37:25,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +21: [2023-04-29 11:37:25,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +33: [2023-04-29 11:37:25,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +20: [2023-04-29 11:37:25,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +47: [2023-04-29 11:37:25,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +47: [2023-04-29 11:37:25,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +47: [2023-04-29 11:37:25,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +47: [2023-04-29 11:37:25,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +45: [2023-04-29 11:37:25,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +45: [2023-04-29 11:37:25,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +45: [2023-04-29 11:37:25,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +45: [2023-04-29 11:37:25,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +20: [2023-04-29 11:37:25,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +21: [2023-04-29 11:37:25,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +21: [2023-04-29 11:37:25,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +21: [2023-04-29 11:37:25,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +20: [2023-04-29 11:37:25,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +20: [2023-04-29 11:37:25,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +45: [2023-04-29 11:37:25,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +45: [2023-04-29 11:37:25,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +45: [2023-04-29 11:37:25,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +45: [2023-04-29 11:37:25,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +47: [2023-04-29 11:37:25,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +37: [2023-04-29 11:37:25,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. + 7: [2023-04-29 11:37:25,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 7: [2023-04-29 11:37:25,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 7: [2023-04-29 11:37:25,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 7: [2023-04-29 11:37:25,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +47: [2023-04-29 11:37:25,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +47: [2023-04-29 11:37:25,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +47: [2023-04-29 11:37:25,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... + 2: [2023-04-29 11:37:25,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 2: [2023-04-29 11:37:25,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 2: [2023-04-29 11:37:25,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +37: [2023-04-29 11:37:25,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +47: [2023-04-29 11:37:25,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 2: [2023-04-29 11:37:25,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +33: [2023-04-29 11:37:25,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +30: [2023-04-29 11:37:25,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +30: [2023-04-29 11:37:25,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 5: [2023-04-29 11:37:25,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +30: [2023-04-29 11:37:25,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +47: [2023-04-29 11:37:25,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +30: [2023-04-29 11:37:25,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +47: [2023-04-29 11:37:25,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +33: [2023-04-29 11:37:25,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +47: [2023-04-29 11:37:25,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... + 5: [2023-04-29 11:37:25,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +27: [2023-04-29 11:37:25,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +27: [2023-04-29 11:37:25,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +27: [2023-04-29 11:37:25,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 7: [2023-04-29 11:37:25,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +27: [2023-04-29 11:37:25,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 7: [2023-04-29 11:37:25,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 7: [2023-04-29 11:37:25,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 7: [2023-04-29 11:37:25,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 5: [2023-04-29 11:37:25,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 5: [2023-04-29 11:37:25,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +50: [2023-04-29 11:37:25,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +50: [2023-04-29 11:37:25,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +50: [2023-04-29 11:37:25,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +50: [2023-04-29 11:37:25,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 7: [2023-04-29 11:37:25,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +20: [2023-04-29 11:37:25,579] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +20: [2023-04-29 11:37:25,579] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +51: [2023-04-29 11:37:25,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +51: [2023-04-29 11:37:25,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +51: [2023-04-29 11:37:25,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +39: [2023-04-29 11:37:25,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +51: [2023-04-29 11:37:25,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +51: [2023-04-29 11:37:25,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +51: [2023-04-29 11:37:25,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +51: [2023-04-29 11:37:25,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +21: [2023-04-29 11:37:25,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +51: [2023-04-29 11:37:25,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +21: [2023-04-29 11:37:25,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +21: [2023-04-29 11:37:25,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +21: [2023-04-29 11:37:25,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 7: [2023-04-29 11:37:25,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 7: [2023-04-29 11:37:25,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 7: [2023-04-29 11:37:25,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +39: [2023-04-29 11:37:25,584] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +39: [2023-04-29 11:37:25,584] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +39: [2023-04-29 11:37:25,584] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +20: [2023-04-29 11:37:25,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +51: [2023-04-29 11:37:25,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +51: [2023-04-29 11:37:25,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +20: [2023-04-29 11:37:25,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +20: [2023-04-29 11:37:25,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +20: [2023-04-29 11:37:25,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 0: [2023-04-29 11:37:25,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 0: [2023-04-29 11:37:25,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 0: [2023-04-29 11:37:25,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 0: [2023-04-29 11:37:25,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 7: [2023-04-29 11:37:25,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +20: [2023-04-29 11:37:25,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 0: [2023-04-29 11:37:25,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +51: [2023-04-29 11:37:25,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +51: [2023-04-29 11:37:25,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +51: [2023-04-29 11:37:25,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +51: [2023-04-29 11:37:25,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +51: [2023-04-29 11:37:25,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... + 0: [2023-04-29 11:37:25,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 0: [2023-04-29 11:37:25,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 0: [2023-04-29 11:37:25,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +51: [2023-04-29 11:37:25,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 7: [2023-04-29 11:37:25,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 7: [2023-04-29 11:37:25,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +37: [2023-04-29 11:37:25,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +37: [2023-04-29 11:37:25,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +37: [2023-04-29 11:37:25,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. + 7: [2023-04-29 11:37:25,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +20: [2023-04-29 11:37:25,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 2: [2023-04-29 11:37:25,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +30: [2023-04-29 11:37:25,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 2: [2023-04-29 11:37:25,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 2: [2023-04-29 11:37:25,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 2: [2023-04-29 11:37:25,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +30: [2023-04-29 11:37:25,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +30: [2023-04-29 11:37:25,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +30: [2023-04-29 11:37:25,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +27: [2023-04-29 11:37:25,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +37: [2023-04-29 11:37:25,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +37: [2023-04-29 11:37:25,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +37: [2023-04-29 11:37:25,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +27: [2023-04-29 11:37:25,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +27: [2023-04-29 11:37:25,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +27: [2023-04-29 11:37:25,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +44: [2023-04-29 11:37:25,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +21: [2023-04-29 11:37:25,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +35: [2023-04-29 11:37:25,610] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +44: [2023-04-29 11:37:25,611] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +37: [2023-04-29 11:37:25,611] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +21: [2023-04-29 11:37:25,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +44: [2023-04-29 11:37:25,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +58: [2023-04-29 11:37:25,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +44: [2023-04-29 11:37:25,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +21: [2023-04-29 11:37:25,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +21: [2023-04-29 11:37:25,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 8: [2023-04-29 11:37:25,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 8: [2023-04-29 11:37:25,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 8: [2023-04-29 11:37:25,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 8: [2023-04-29 11:37:25,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 8: [2023-04-29 11:37:25,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 8: [2023-04-29 11:37:25,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 8: [2023-04-29 11:37:25,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 8: [2023-04-29 11:37:25,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +58: [2023-04-29 11:37:25,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +49: [2023-04-29 11:37:25,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +58: [2023-04-29 11:37:25,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +58: [2023-04-29 11:37:25,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +45: [2023-04-29 11:37:25,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +20: [2023-04-29 11:37:25,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +35: [2023-04-29 11:37:25,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +30: [2023-04-29 11:37:25,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +30: [2023-04-29 11:37:25,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 8: [2023-04-29 11:37:25,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 8: [2023-04-29 11:37:25,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 8: [2023-04-29 11:37:25,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +30: [2023-04-29 11:37:25,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +30: [2023-04-29 11:37:25,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +12: [2023-04-29 11:37:25,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +12: [2023-04-29 11:37:25,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +12: [2023-04-29 11:37:25,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +45: [2023-04-29 11:37:25,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +12: [2023-04-29 11:37:25,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +35: [2023-04-29 11:37:25,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +35: [2023-04-29 11:37:25,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. + 8: [2023-04-29 11:37:25,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 8: [2023-04-29 11:37:25,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 8: [2023-04-29 11:37:25,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 8: [2023-04-29 11:37:25,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +20: [2023-04-29 11:37:25,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +47: [2023-04-29 11:37:25,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +30: [2023-04-29 11:37:25,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +30: [2023-04-29 11:37:25,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +30: [2023-04-29 11:37:25,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 8: [2023-04-29 11:37:25,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +49: [2023-04-29 11:37:25,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +49: [2023-04-29 11:37:25,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +49: [2023-04-29 11:37:25,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +21: [2023-04-29 11:37:25,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +37: [2023-04-29 11:37:25,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +37: [2023-04-29 11:37:25,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +30: [2023-04-29 11:37:25,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +37: [2023-04-29 11:37:25,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +57: [2023-04-29 11:37:25,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +57: [2023-04-29 11:37:25,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +57: [2023-04-29 11:37:25,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +57: [2023-04-29 11:37:25,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +57: [2023-04-29 11:37:25,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +57: [2023-04-29 11:37:25,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +57: [2023-04-29 11:37:25,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +57: [2023-04-29 11:37:25,633] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +20: [2023-04-29 11:37:25,633] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +47: [2023-04-29 11:37:25,633] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +20: [2023-04-29 11:37:25,633] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +35: [2023-04-29 11:37:25,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +44: [2023-04-29 11:37:25,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +45: [2023-04-29 11:37:25,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +45: [2023-04-29 11:37:25,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +37: [2023-04-29 11:37:25,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +44: [2023-04-29 11:37:25,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +57: [2023-04-29 11:37:25,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +57: [2023-04-29 11:37:25,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +24: [2023-04-29 11:37:25,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +24: [2023-04-29 11:37:25,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +24: [2023-04-29 11:37:25,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +24: [2023-04-29 11:37:25,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +24: [2023-04-29 11:37:25,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +24: [2023-04-29 11:37:25,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +24: [2023-04-29 11:37:25,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +57: [2023-04-29 11:37:25,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 2: [2023-04-29 11:37:25,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 2: [2023-04-29 11:37:25,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +24: [2023-04-29 11:37:25,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 2: [2023-04-29 11:37:25,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +57: [2023-04-29 11:37:25,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... + 2: [2023-04-29 11:37:25,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +57: [2023-04-29 11:37:25,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +58: [2023-04-29 11:37:25,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +57: [2023-04-29 11:37:25,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +57: [2023-04-29 11:37:25,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +47: [2023-04-29 11:37:25,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +47: [2023-04-29 11:37:25,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +57: [2023-04-29 11:37:25,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +44: [2023-04-29 11:37:25,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +24: [2023-04-29 11:37:25,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +24: [2023-04-29 11:37:25,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +24: [2023-04-29 11:37:25,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +24: [2023-04-29 11:37:25,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 2: [2023-04-29 11:37:25,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +44: [2023-04-29 11:37:25,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +24: [2023-04-29 11:37:25,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 2: [2023-04-29 11:37:25,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 2: [2023-04-29 11:37:25,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +24: [2023-04-29 11:37:25,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 2: [2023-04-29 11:37:25,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +24: [2023-04-29 11:37:25,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +24: [2023-04-29 11:37:25,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +20: [2023-04-29 11:37:25,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +40: [2023-04-29 11:37:25,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +40: [2023-04-29 11:37:25,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +40: [2023-04-29 11:37:25,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +40: [2023-04-29 11:37:25,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +40: [2023-04-29 11:37:25,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +40: [2023-04-29 11:37:25,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +40: [2023-04-29 11:37:25,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +40: [2023-04-29 11:37:25,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +49: [2023-04-29 11:37:25,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +58: [2023-04-29 11:37:25,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +58: [2023-04-29 11:37:25,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +58: [2023-04-29 11:37:25,650] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +45: [2023-04-29 11:37:25,650] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... + 0: [2023-04-29 11:37:25,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +35: [2023-04-29 11:37:25,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +40: [2023-04-29 11:37:25,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +40: [2023-04-29 11:37:25,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +40: [2023-04-29 11:37:25,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +45: [2023-04-29 11:37:25,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +28: [2023-04-29 11:37:25,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +28: [2023-04-29 11:37:25,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +28: [2023-04-29 11:37:25,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +28: [2023-04-29 11:37:25,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 7: [2023-04-29 11:37:25,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +12: [2023-04-29 11:37:25,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +40: [2023-04-29 11:37:25,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +20: [2023-04-29 11:37:25,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 7: [2023-04-29 11:37:25,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +40: [2023-04-29 11:37:25,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 2: [2023-04-29 11:37:25,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +40: [2023-04-29 11:37:25,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +40: [2023-04-29 11:37:25,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +40: [2023-04-29 11:37:25,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +12: [2023-04-29 11:37:25,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +21: [2023-04-29 11:37:25,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +21: [2023-04-29 11:37:25,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +21: [2023-04-29 11:37:25,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +21: [2023-04-29 11:37:25,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +47: [2023-04-29 11:37:25,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +12: [2023-04-29 11:37:25,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +17: [2023-04-29 11:37:25,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +17: [2023-04-29 11:37:25,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +17: [2023-04-29 11:37:25,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +47: [2023-04-29 11:37:25,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +17: [2023-04-29 11:37:25,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +35: [2023-04-29 11:37:25,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +12: [2023-04-29 11:37:25,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +35: [2023-04-29 11:37:25,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +20: [2023-04-29 11:37:25,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +20: [2023-04-29 11:37:25,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +37: [2023-04-29 11:37:25,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... + 0: [2023-04-29 11:37:25,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 0: [2023-04-29 11:37:25,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 0: [2023-04-29 11:37:25,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 7: [2023-04-29 11:37:25,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 7: [2023-04-29 11:37:25,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 7: [2023-04-29 11:37:25,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 7: [2023-04-29 11:37:25,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 2: [2023-04-29 11:37:25,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +37: [2023-04-29 11:37:25,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +37: [2023-04-29 11:37:25,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +49: [2023-04-29 11:37:25,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... + 4: [2023-04-29 11:37:25,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +45: [2023-04-29 11:37:25,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +49: [2023-04-29 11:37:25,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... + 4: [2023-04-29 11:37:25,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 4: [2023-04-29 11:37:25,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +49: [2023-04-29 11:37:25,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... + 4: [2023-04-29 11:37:25,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +45: [2023-04-29 11:37:25,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +47: [2023-04-29 11:37:25,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +47: [2023-04-29 11:37:25,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... + 7: [2023-04-29 11:37:25,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +51: [2023-04-29 11:37:25,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +63: [2023-04-29 11:37:25,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +63: [2023-04-29 11:37:25,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +63: [2023-04-29 11:37:25,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +63: [2023-04-29 11:37:25,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +63: [2023-04-29 11:37:25,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +63: [2023-04-29 11:37:25,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +63: [2023-04-29 11:37:25,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +63: [2023-04-29 11:37:25,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +30: [2023-04-29 11:37:25,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 9: [2023-04-29 11:37:25,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 9: [2023-04-29 11:37:25,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +51: [2023-04-29 11:37:25,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +51: [2023-04-29 11:37:25,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +51: [2023-04-29 11:37:25,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. + 2: [2023-04-29 11:37:25,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 2: [2023-04-29 11:37:25,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 9: [2023-04-29 11:37:25,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +30: [2023-04-29 11:37:25,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +63: [2023-04-29 11:37:25,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 9: [2023-04-29 11:37:25,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +63: [2023-04-29 11:37:25,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +63: [2023-04-29 11:37:25,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +63: [2023-04-29 11:37:25,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... + 7: [2023-04-29 11:37:25,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +23: [2023-04-29 11:37:25,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +23: [2023-04-29 11:37:25,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 2: [2023-04-29 11:37:25,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +63: [2023-04-29 11:37:25,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 0: [2023-04-29 11:37:25,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +63: [2023-04-29 11:37:25,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +63: [2023-04-29 11:37:25,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +55: [2023-04-29 11:37:25,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +55: [2023-04-29 11:37:25,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +55: [2023-04-29 11:37:25,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +63: [2023-04-29 11:37:25,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +55: [2023-04-29 11:37:25,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +30: [2023-04-29 11:37:25,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 6: [2023-04-29 11:37:25,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 6: [2023-04-29 11:37:25,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 7: [2023-04-29 11:37:25,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 2: [2023-04-29 11:37:25,677] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +23: [2023-04-29 11:37:25,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +23: [2023-04-29 11:37:25,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 2: [2023-04-29 11:37:25,677] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +30: [2023-04-29 11:37:25,677] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +14: [2023-04-29 11:37:25,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +14: [2023-04-29 11:37:25,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +21: [2023-04-29 11:37:25,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 6: [2023-04-29 11:37:25,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 6: [2023-04-29 11:37:25,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +14: [2023-04-29 11:37:25,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +28: [2023-04-29 11:37:25,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +14: [2023-04-29 11:37:25,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 2: [2023-04-29 11:37:25,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 7: [2023-04-29 11:37:25,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +30: [2023-04-29 11:37:25,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +30: [2023-04-29 11:37:25,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +17: [2023-04-29 11:37:25,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 7: [2023-04-29 11:37:25,683] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +17: [2023-04-29 11:37:25,683] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +28: [2023-04-29 11:37:25,683] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +21: [2023-04-29 11:37:25,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +17: [2023-04-29 11:37:25,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 8: [2023-04-29 11:37:25,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 7: [2023-04-29 11:37:25,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +28: [2023-04-29 11:37:25,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +28: [2023-04-29 11:37:25,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +30: [2023-04-29 11:37:25,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +30: [2023-04-29 11:37:25,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +22: [2023-04-29 11:37:25,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +22: [2023-04-29 11:37:25,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 0: [2023-04-29 11:37:25,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +22: [2023-04-29 11:37:25,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +22: [2023-04-29 11:37:25,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 0: [2023-04-29 11:37:25,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +17: [2023-04-29 11:37:25,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +21: [2023-04-29 11:37:25,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +50: [2023-04-29 11:37:25,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +50: [2023-04-29 11:37:25,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. + 8: [2023-04-29 11:37:25,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +50: [2023-04-29 11:37:25,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +21: [2023-04-29 11:37:25,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +50: [2023-04-29 11:37:25,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +50: [2023-04-29 11:37:25,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +50: [2023-04-29 11:37:25,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +50: [2023-04-29 11:37:25,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +21: [2023-04-29 11:37:25,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +50: [2023-04-29 11:37:25,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. + 0: [2023-04-29 11:37:25,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 4: [2023-04-29 11:37:25,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +21: [2023-04-29 11:37:25,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 4: [2023-04-29 11:37:25,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 4: [2023-04-29 11:37:25,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 4: [2023-04-29 11:37:25,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +22: [2023-04-29 11:37:25,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 7: [2023-04-29 11:37:25,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +32: [2023-04-29 11:37:25,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +32: [2023-04-29 11:37:25,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +50: [2023-04-29 11:37:25,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +22: [2023-04-29 11:37:25,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +11: [2023-04-29 11:37:25,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +11: [2023-04-29 11:37:25,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +22: [2023-04-29 11:37:25,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +50: [2023-04-29 11:37:25,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +50: [2023-04-29 11:37:25,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +11: [2023-04-29 11:37:25,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +32: [2023-04-29 11:37:25,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. + 7: [2023-04-29 11:37:25,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +22: [2023-04-29 11:37:25,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +11: [2023-04-29 11:37:25,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +32: [2023-04-29 11:37:25,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +21: [2023-04-29 11:37:25,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +36: [2023-04-29 11:37:25,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +36: [2023-04-29 11:37:25,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. + 8: [2023-04-29 11:37:25,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 8: [2023-04-29 11:37:25,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +42: [2023-04-29 11:37:25,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +42: [2023-04-29 11:37:25,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +30: [2023-04-29 11:37:25,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +36: [2023-04-29 11:37:25,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +36: [2023-04-29 11:37:25,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +42: [2023-04-29 11:37:25,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +36: [2023-04-29 11:37:25,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +36: [2023-04-29 11:37:25,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +36: [2023-04-29 11:37:25,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +36: [2023-04-29 11:37:25,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +42: [2023-04-29 11:37:25,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. + 7: [2023-04-29 11:37:25,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 7: [2023-04-29 11:37:25,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +50: [2023-04-29 11:37:25,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +50: [2023-04-29 11:37:25,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +32: [2023-04-29 11:37:25,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +32: [2023-04-29 11:37:25,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +50: [2023-04-29 11:37:25,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +55: [2023-04-29 11:37:25,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +50: [2023-04-29 11:37:25,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +55: [2023-04-29 11:37:25,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +50: [2023-04-29 11:37:25,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +23: [2023-04-29 11:37:25,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +23: [2023-04-29 11:37:25,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +36: [2023-04-29 11:37:25,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +36: [2023-04-29 11:37:25,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +55: [2023-04-29 11:37:25,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +55: [2023-04-29 11:37:25,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +42: [2023-04-29 11:37:25,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +30: [2023-04-29 11:37:25,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +42: [2023-04-29 11:37:25,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 9: [2023-04-29 11:37:25,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +36: [2023-04-29 11:37:25,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +32: [2023-04-29 11:37:25,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +57: [2023-04-29 11:37:25,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +36: [2023-04-29 11:37:25,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +51: [2023-04-29 11:37:25,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +42: [2023-04-29 11:37:25,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +32: [2023-04-29 11:37:25,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 9: [2023-04-29 11:37:25,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +19: [2023-04-29 11:37:25,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +19: [2023-04-29 11:37:25,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +42: [2023-04-29 11:37:25,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +24: [2023-04-29 11:37:25,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +24: [2023-04-29 11:37:25,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +24: [2023-04-29 11:37:25,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 9: [2023-04-29 11:37:25,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +30: [2023-04-29 11:37:25,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 6: [2023-04-29 11:37:25,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +14: [2023-04-29 11:37:25,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +23: [2023-04-29 11:37:25,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +23: [2023-04-29 11:37:25,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +30: [2023-04-29 11:37:25,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +57: [2023-04-29 11:37:25,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +24: [2023-04-29 11:37:25,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 9: [2023-04-29 11:37:25,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 6: [2023-04-29 11:37:25,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +51: [2023-04-29 11:37:25,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +36: [2023-04-29 11:37:25,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +36: [2023-04-29 11:37:25,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +57: [2023-04-29 11:37:25,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +21: [2023-04-29 11:37:25,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +19: [2023-04-29 11:37:25,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +36: [2023-04-29 11:37:25,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +19: [2023-04-29 11:37:25,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 6: [2023-04-29 11:37:25,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 8: [2023-04-29 11:37:25,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +36: [2023-04-29 11:37:25,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +57: [2023-04-29 11:37:25,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +14: [2023-04-29 11:37:25,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 2: [2023-04-29 11:37:25,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +51: [2023-04-29 11:37:25,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +14: [2023-04-29 11:37:25,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +21: [2023-04-29 11:37:25,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +14: [2023-04-29 11:37:25,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 6: [2023-04-29 11:37:25,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +51: [2023-04-29 11:37:25,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +53: [2023-04-29 11:37:25,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +53: [2023-04-29 11:37:25,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +53: [2023-04-29 11:37:25,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +53: [2023-04-29 11:37:25,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +21: [2023-04-29 11:37:25,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 2: [2023-04-29 11:37:25,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 2: [2023-04-29 11:37:25,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 2: [2023-04-29 11:37:25,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +53: [2023-04-29 11:37:25,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 8: [2023-04-29 11:37:25,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +40: [2023-04-29 11:37:25,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +10: [2023-04-29 11:37:25,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +10: [2023-04-29 11:37:25,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +10: [2023-04-29 11:37:25,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +32: [2023-04-29 11:37:25,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +32: [2023-04-29 11:37:25,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +52: [2023-04-29 11:37:25,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +32: [2023-04-29 11:37:25,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +10: [2023-04-29 11:37:25,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +52: [2023-04-29 11:37:25,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +52: [2023-04-29 11:37:25,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +32: [2023-04-29 11:37:25,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +52: [2023-04-29 11:37:25,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +52: [2023-04-29 11:37:25,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +52: [2023-04-29 11:37:25,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +52: [2023-04-29 11:37:25,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +53: [2023-04-29 11:37:25,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +53: [2023-04-29 11:37:25,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +52: [2023-04-29 11:37:25,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +21: [2023-04-29 11:37:25,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +53: [2023-04-29 11:37:25,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +62: [2023-04-29 11:37:25,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +62: [2023-04-29 11:37:25,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +62: [2023-04-29 11:37:25,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +30: [2023-04-29 11:37:25,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +62: [2023-04-29 11:37:25,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +62: [2023-04-29 11:37:25,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +62: [2023-04-29 11:37:25,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +62: [2023-04-29 11:37:25,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +62: [2023-04-29 11:37:25,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +52: [2023-04-29 11:37:25,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +10: [2023-04-29 11:37:25,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 8: [2023-04-29 11:37:25,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 8: [2023-04-29 11:37:25,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +11: [2023-04-29 11:37:25,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +11: [2023-04-29 11:37:25,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +10: [2023-04-29 11:37:25,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +11: [2023-04-29 11:37:25,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +11: [2023-04-29 11:37:25,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +10: [2023-04-29 11:37:25,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +52: [2023-04-29 11:37:25,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +52: [2023-04-29 11:37:25,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +52: [2023-04-29 11:37:25,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +10: [2023-04-29 11:37:25,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +62: [2023-04-29 11:37:25,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +62: [2023-04-29 11:37:25,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +52: [2023-04-29 11:37:25,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +52: [2023-04-29 11:37:25,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +52: [2023-04-29 11:37:25,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +24: [2023-04-29 11:37:25,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +52: [2023-04-29 11:37:25,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +25: [2023-04-29 11:37:25,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +25: [2023-04-29 11:37:25,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +25: [2023-04-29 11:37:25,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +25: [2023-04-29 11:37:25,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +30: [2023-04-29 11:37:25,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +24: [2023-04-29 11:37:25,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +62: [2023-04-29 11:37:25,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +62: [2023-04-29 11:37:25,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +24: [2023-04-29 11:37:25,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +24: [2023-04-29 11:37:25,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +62: [2023-04-29 11:37:25,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +62: [2023-04-29 11:37:25,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +62: [2023-04-29 11:37:25,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +19: [2023-04-29 11:37:25,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +62: [2023-04-29 11:37:25,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +30: [2023-04-29 11:37:25,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +30: [2023-04-29 11:37:25,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +25: [2023-04-29 11:37:25,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +40: [2023-04-29 11:37:25,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +57: [2023-04-29 11:37:25,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +40: [2023-04-29 11:37:25,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +40: [2023-04-29 11:37:25,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. + 2: [2023-04-29 11:37:25,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +25: [2023-04-29 11:37:25,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +63: [2023-04-29 11:37:25,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +19: [2023-04-29 11:37:25,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +19: [2023-04-29 11:37:25,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +63: [2023-04-29 11:37:25,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +25: [2023-04-29 11:37:25,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +57: [2023-04-29 11:37:25,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +57: [2023-04-29 11:37:25,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +25: [2023-04-29 11:37:25,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +19: [2023-04-29 11:37:25,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +60: [2023-04-29 11:37:25,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +60: [2023-04-29 11:37:25,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +60: [2023-04-29 11:37:25,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +60: [2023-04-29 11:37:25,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +60: [2023-04-29 11:37:25,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +60: [2023-04-29 11:37:25,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +60: [2023-04-29 11:37:25,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +40: [2023-04-29 11:37:25,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +60: [2023-04-29 11:37:25,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +57: [2023-04-29 11:37:25,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +63: [2023-04-29 11:37:25,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +63: [2023-04-29 11:37:25,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. + 2: [2023-04-29 11:37:25,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 2: [2023-04-29 11:37:25,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +42: [2023-04-29 11:37:25,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +42: [2023-04-29 11:37:25,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +14: [2023-04-29 11:37:25,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +14: [2023-04-29 11:37:25,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +60: [2023-04-29 11:37:25,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +60: [2023-04-29 11:37:25,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 2: [2023-04-29 11:37:25,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +60: [2023-04-29 11:37:25,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +42: [2023-04-29 11:37:25,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +42: [2023-04-29 11:37:25,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +60: [2023-04-29 11:37:25,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +14: [2023-04-29 11:37:25,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +14: [2023-04-29 11:37:25,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +41: [2023-04-29 11:37:25,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +41: [2023-04-29 11:37:25,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +60: [2023-04-29 11:37:25,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +60: [2023-04-29 11:37:25,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +60: [2023-04-29 11:37:25,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +25: [2023-04-29 11:37:25,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +25: [2023-04-29 11:37:25,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +27: [2023-04-29 11:37:25,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +27: [2023-04-29 11:37:25,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +27: [2023-04-29 11:37:25,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +27: [2023-04-29 11:37:25,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +27: [2023-04-29 11:37:25,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +27: [2023-04-29 11:37:25,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +27: [2023-04-29 11:37:25,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +27: [2023-04-29 11:37:25,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +60: [2023-04-29 11:37:25,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... + 6: [2023-04-29 11:37:25,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 6: [2023-04-29 11:37:25,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +41: [2023-04-29 11:37:25,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. + 6: [2023-04-29 11:37:25,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 6: [2023-04-29 11:37:25,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +32: [2023-04-29 11:37:25,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +41: [2023-04-29 11:37:25,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +13: [2023-04-29 11:37:25,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +13: [2023-04-29 11:37:25,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +13: [2023-04-29 11:37:25,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +19: [2023-04-29 11:37:25,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +19: [2023-04-29 11:37:25,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +13: [2023-04-29 11:37:25,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +14: [2023-04-29 11:37:25,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +19: [2023-04-29 11:37:25,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +19: [2023-04-29 11:37:25,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +14: [2023-04-29 11:37:25,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 4: [2023-04-29 11:37:25,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 4: [2023-04-29 11:37:25,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 4: [2023-04-29 11:37:25,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 4: [2023-04-29 11:37:25,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 4: [2023-04-29 11:37:25,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +14: [2023-04-29 11:37:25,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +25: [2023-04-29 11:37:25,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +22: [2023-04-29 11:37:25,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +25: [2023-04-29 11:37:25,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +27: [2023-04-29 11:37:25,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 6: [2023-04-29 11:37:25,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 6: [2023-04-29 11:37:25,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 6: [2023-04-29 11:37:25,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 6: [2023-04-29 11:37:25,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +27: [2023-04-29 11:37:25,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +27: [2023-04-29 11:37:25,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +32: [2023-04-29 11:37:25,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +32: [2023-04-29 11:37:25,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 4: [2023-04-29 11:37:25,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +27: [2023-04-29 11:37:25,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +27: [2023-04-29 11:37:25,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +27: [2023-04-29 11:37:25,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +14: [2023-04-29 11:37:25,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +27: [2023-04-29 11:37:25,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +13: [2023-04-29 11:37:25,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +27: [2023-04-29 11:37:25,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +13: [2023-04-29 11:37:25,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +13: [2023-04-29 11:37:25,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +19: [2023-04-29 11:37:25,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +19: [2023-04-29 11:37:25,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +13: [2023-04-29 11:37:25,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +19: [2023-04-29 11:37:25,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 4: [2023-04-29 11:37:25,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +50: [2023-04-29 11:37:25,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +43: [2023-04-29 11:37:25,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +43: [2023-04-29 11:37:25,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +43: [2023-04-29 11:37:25,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +43: [2023-04-29 11:37:25,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +43: [2023-04-29 11:37:25,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +43: [2023-04-29 11:37:25,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +43: [2023-04-29 11:37:25,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. + 4: [2023-04-29 11:37:25,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +43: [2023-04-29 11:37:25,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +19: [2023-04-29 11:37:25,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 4: [2023-04-29 11:37:25,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 4: [2023-04-29 11:37:25,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 4: [2023-04-29 11:37:25,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +63: [2023-04-29 11:37:25,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +32: [2023-04-29 11:37:25,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +40: [2023-04-29 11:37:25,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... + 4: [2023-04-29 11:37:25,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +41: [2023-04-29 11:37:25,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +40: [2023-04-29 11:37:25,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +41: [2023-04-29 11:37:25,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +41: [2023-04-29 11:37:25,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +15: [2023-04-29 11:37:25,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +15: [2023-04-29 11:37:25,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +15: [2023-04-29 11:37:25,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +34: [2023-04-29 11:37:25,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +34: [2023-04-29 11:37:25,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +11: [2023-04-29 11:37:25,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +15: [2023-04-29 11:37:25,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +11: [2023-04-29 11:37:25,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +17: [2023-04-29 11:37:25,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +17: [2023-04-29 11:37:25,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +11: [2023-04-29 11:37:25,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +11: [2023-04-29 11:37:25,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +17: [2023-04-29 11:37:25,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +40: [2023-04-29 11:37:25,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +17: [2023-04-29 11:37:25,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +17: [2023-04-29 11:37:25,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 4: [2023-04-29 11:37:25,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +17: [2023-04-29 11:37:25,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +17: [2023-04-29 11:37:25,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +41: [2023-04-29 11:37:25,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +17: [2023-04-29 11:37:25,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +38: [2023-04-29 11:37:25,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +38: [2023-04-29 11:37:25,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +22: [2023-04-29 11:37:25,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +22: [2023-04-29 11:37:25,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +22: [2023-04-29 11:37:25,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +43: [2023-04-29 11:37:25,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +34: [2023-04-29 11:37:25,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +34: [2023-04-29 11:37:25,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +63: [2023-04-29 11:37:25,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +34: [2023-04-29 11:37:25,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +34: [2023-04-29 11:37:25,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +61: [2023-04-29 11:37:25,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +61: [2023-04-29 11:37:25,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +61: [2023-04-29 11:37:25,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +34: [2023-04-29 11:37:25,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +34: [2023-04-29 11:37:25,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +61: [2023-04-29 11:37:25,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +43: [2023-04-29 11:37:25,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +38: [2023-04-29 11:37:25,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +38: [2023-04-29 11:37:25,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +29: [2023-04-29 11:37:25,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +29: [2023-04-29 11:37:25,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +29: [2023-04-29 11:37:25,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +29: [2023-04-29 11:37:25,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +29: [2023-04-29 11:37:25,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +29: [2023-04-29 11:37:25,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +29: [2023-04-29 11:37:25,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +29: [2023-04-29 11:37:25,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +43: [2023-04-29 11:37:25,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +38: [2023-04-29 11:37:25,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +38: [2023-04-29 11:37:25,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +38: [2023-04-29 11:37:25,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +38: [2023-04-29 11:37:25,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +43: [2023-04-29 11:37:25,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +43: [2023-04-29 11:37:25,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +15: [2023-04-29 11:37:25,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +43: [2023-04-29 11:37:25,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +15: [2023-04-29 11:37:25,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +11: [2023-04-29 11:37:25,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +11: [2023-04-29 11:37:25,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +36: [2023-04-29 11:37:25,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +36: [2023-04-29 11:37:25,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. + 4: [2023-04-29 11:37:25,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +43: [2023-04-29 11:37:25,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +43: [2023-04-29 11:37:25,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +17: [2023-04-29 11:37:25,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +15: [2023-04-29 11:37:25,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +11: [2023-04-29 11:37:25,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +34: [2023-04-29 11:37:25,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +34: [2023-04-29 11:37:25,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +15: [2023-04-29 11:37:25,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +11: [2023-04-29 11:37:25,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +41: [2023-04-29 11:37:25,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +17: [2023-04-29 11:37:25,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +17: [2023-04-29 11:37:25,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 4: [2023-04-29 11:37:25,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +17: [2023-04-29 11:37:25,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +63: [2023-04-29 11:37:25,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +63: [2023-04-29 11:37:25,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +17: [2023-04-29 11:37:25,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +17: [2023-04-29 11:37:25,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +34: [2023-04-29 11:37:25,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +34: [2023-04-29 11:37:25,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +17: [2023-04-29 11:37:25,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +41: [2023-04-29 11:37:25,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +29: [2023-04-29 11:37:25,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +29: [2023-04-29 11:37:25,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +38: [2023-04-29 11:37:25,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +38: [2023-04-29 11:37:25,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +56: [2023-04-29 11:37:25,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +56: [2023-04-29 11:37:25,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +61: [2023-04-29 11:37:25,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 9: [2023-04-29 11:37:25,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 9: [2023-04-29 11:37:25,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +56: [2023-04-29 11:37:25,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +38: [2023-04-29 11:37:25,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +61: [2023-04-29 11:37:25,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +56: [2023-04-29 11:37:25,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +56: [2023-04-29 11:37:25,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +56: [2023-04-29 11:37:25,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +56: [2023-04-29 11:37:25,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +38: [2023-04-29 11:37:25,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +31: [2023-04-29 11:37:25,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +56: [2023-04-29 11:37:25,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +31: [2023-04-29 11:37:25,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +31: [2023-04-29 11:37:25,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 9: [2023-04-29 11:37:25,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +29: [2023-04-29 11:37:25,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 9: [2023-04-29 11:37:25,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +17: [2023-04-29 11:37:25,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +29: [2023-04-29 11:37:25,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +29: [2023-04-29 11:37:25,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +31: [2023-04-29 11:37:25,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +61: [2023-04-29 11:37:25,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +26: [2023-04-29 11:37:25,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +26: [2023-04-29 11:37:25,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +29: [2023-04-29 11:37:25,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +29: [2023-04-29 11:37:25,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +29: [2023-04-29 11:37:25,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +41: [2023-04-29 11:37:25,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +42: [2023-04-29 11:37:25,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +42: [2023-04-29 11:37:25,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +41: [2023-04-29 11:37:25,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +42: [2023-04-29 11:37:25,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. + 9: [2023-04-29 11:37:25,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +34: [2023-04-29 11:37:25,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... + 4: [2023-04-29 11:37:25,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 9: [2023-04-29 11:37:25,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 9: [2023-04-29 11:37:25,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +34: [2023-04-29 11:37:25,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +38: [2023-04-29 11:37:25,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +34: [2023-04-29 11:37:25,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +61: [2023-04-29 11:37:25,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +42: [2023-04-29 11:37:25,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +14: [2023-04-29 11:37:25,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +50: [2023-04-29 11:37:25,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +32: [2023-04-29 11:37:25,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +32: [2023-04-29 11:37:25,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +41: [2023-04-29 11:37:25,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +34: [2023-04-29 11:37:25,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +38: [2023-04-29 11:37:25,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +38: [2023-04-29 11:37:25,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +38: [2023-04-29 11:37:25,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +36: [2023-04-29 11:37:25,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +42: [2023-04-29 11:37:25,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +36: [2023-04-29 11:37:25,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +26: [2023-04-29 11:37:25,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +26: [2023-04-29 11:37:25,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +56: [2023-04-29 11:37:25,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +56: [2023-04-29 11:37:25,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +56: [2023-04-29 11:37:25,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +56: [2023-04-29 11:37:25,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +56: [2023-04-29 11:37:25,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +22: [2023-04-29 11:37:25,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 9: [2023-04-29 11:37:25,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +53: [2023-04-29 11:37:25,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +31: [2023-04-29 11:37:25,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +56: [2023-04-29 11:37:25,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +56: [2023-04-29 11:37:25,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +56: [2023-04-29 11:37:25,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +31: [2023-04-29 11:37:25,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 9: [2023-04-29 11:37:25,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +41: [2023-04-29 11:37:25,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +31: [2023-04-29 11:37:25,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 6: [2023-04-29 11:37:25,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 9: [2023-04-29 11:37:25,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +31: [2023-04-29 11:37:25,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +25: [2023-04-29 11:37:25,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +25: [2023-04-29 11:37:25,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 9: [2023-04-29 11:37:25,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +50: [2023-04-29 11:37:25,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +42: [2023-04-29 11:37:25,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 6: [2023-04-29 11:37:25,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +41: [2023-04-29 11:37:25,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 6: [2023-04-29 11:37:25,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 6: [2023-04-29 11:37:25,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +14: [2023-04-29 11:37:25,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 9: [2023-04-29 11:37:25,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +50: [2023-04-29 11:37:25,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. + 9: [2023-04-29 11:37:25,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +50: [2023-04-29 11:37:25,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... + 9: [2023-04-29 11:37:25,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +22: [2023-04-29 11:37:25,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +22: [2023-04-29 11:37:25,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +22: [2023-04-29 11:37:25,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 9: [2023-04-29 11:37:25,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +25: [2023-04-29 11:37:25,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +42: [2023-04-29 11:37:25,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +41: [2023-04-29 11:37:25,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +10: [2023-04-29 11:37:25,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +22: [2023-04-29 11:37:25,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 9: [2023-04-29 11:37:25,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 6: [2023-04-29 11:37:25,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +25: [2023-04-29 11:37:25,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +52: [2023-04-29 11:37:25,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +14: [2023-04-29 11:37:25,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +14: [2023-04-29 11:37:25,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +14: [2023-04-29 11:37:25,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +54: [2023-04-29 11:37:25,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +54: [2023-04-29 11:37:25,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +48: [2023-04-29 11:37:25,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +48: [2023-04-29 11:37:25,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +48: [2023-04-29 11:37:25,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +42: [2023-04-29 11:37:25,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +54: [2023-04-29 11:37:25,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +48: [2023-04-29 11:37:25,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. + 6: [2023-04-29 11:37:25,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +54: [2023-04-29 11:37:25,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. + 6: [2023-04-29 11:37:25,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 6: [2023-04-29 11:37:25,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +53: [2023-04-29 11:37:25,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +53: [2023-04-29 11:37:25,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +53: [2023-04-29 11:37:25,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +32: [2023-04-29 11:37:25,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +32: [2023-04-29 11:37:25,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +62: [2023-04-29 11:37:25,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +11: [2023-04-29 11:37:25,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +11: [2023-04-29 11:37:25,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +10: [2023-04-29 11:37:25,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +10: [2023-04-29 11:37:25,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +10: [2023-04-29 11:37:25,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +52: [2023-04-29 11:37:25,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +52: [2023-04-29 11:37:25,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +22: [2023-04-29 11:37:25,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +14: [2023-04-29 11:37:25,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +14: [2023-04-29 11:37:25,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +14: [2023-04-29 11:37:25,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +36: [2023-04-29 11:37:25,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +62: [2023-04-29 11:37:25,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +52: [2023-04-29 11:37:25,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +44: [2023-04-29 11:37:25,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +44: [2023-04-29 11:37:25,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +44: [2023-04-29 11:37:25,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +44: [2023-04-29 11:37:25,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +36: [2023-04-29 11:37:25,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +22: [2023-04-29 11:37:25,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +11: [2023-04-29 11:37:25,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +11: [2023-04-29 11:37:25,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +22: [2023-04-29 11:37:25,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 1: [2023-04-29 11:37:25,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 1: [2023-04-29 11:37:25,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 1: [2023-04-29 11:37:25,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +11: [2023-04-29 11:37:25,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 1: [2023-04-29 11:37:25,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +46: [2023-04-29 11:37:25,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +46: [2023-04-29 11:37:25,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +53: [2023-04-29 11:37:25,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +46: [2023-04-29 11:37:25,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +59: [2023-04-29 11:37:25,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +59: [2023-04-29 11:37:25,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +13: [2023-04-29 11:37:25,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +46: [2023-04-29 11:37:25,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +13: [2023-04-29 11:37:25,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +42: [2023-04-29 11:37:25,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +11: [2023-04-29 11:37:25,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +26: [2023-04-29 11:37:25,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +16: [2023-04-29 11:37:25,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +16: [2023-04-29 11:37:25,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +26: [2023-04-29 11:37:25,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +32: [2023-04-29 11:37:25,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +62: [2023-04-29 11:37:25,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +62: [2023-04-29 11:37:25,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. + 1: [2023-04-29 11:37:25,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +32: [2023-04-29 11:37:25,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +26: [2023-04-29 11:37:25,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 1: [2023-04-29 11:37:25,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +25: [2023-04-29 11:37:25,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +59: [2023-04-29 11:37:25,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +59: [2023-04-29 11:37:25,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +59: [2023-04-29 11:37:25,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +59: [2023-04-29 11:37:25,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +59: [2023-04-29 11:37:25,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +59: [2023-04-29 11:37:25,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +46: [2023-04-29 11:37:25,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +50: [2023-04-29 11:37:25,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +36: [2023-04-29 11:37:25,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +42: [2023-04-29 11:37:25,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +42: [2023-04-29 11:37:25,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +11: [2023-04-29 11:37:25,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 1: [2023-04-29 11:37:25,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +13: [2023-04-29 11:37:25,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +13: [2023-04-29 11:37:25,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +46: [2023-04-29 11:37:25,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +19: [2023-04-29 11:37:25,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +26: [2023-04-29 11:37:25,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +46: [2023-04-29 11:37:25,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 1: [2023-04-29 11:37:25,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +22: [2023-04-29 11:37:25,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +46: [2023-04-29 11:37:25,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +36: [2023-04-29 11:37:25,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +10: [2023-04-29 11:37:25,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +11: [2023-04-29 11:37:25,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +59: [2023-04-29 11:37:25,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +16: [2023-04-29 11:37:25,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +52: [2023-04-29 11:37:25,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +59: [2023-04-29 11:37:25,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +10: [2023-04-29 11:37:25,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +59: [2023-04-29 11:37:25,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +22: [2023-04-29 11:37:25,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +22: [2023-04-29 11:37:25,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +10: [2023-04-29 11:37:25,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +16: [2023-04-29 11:37:25,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +59: [2023-04-29 11:37:25,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +59: [2023-04-29 11:37:25,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +10: [2023-04-29 11:37:25,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +50: [2023-04-29 11:37:25,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +22: [2023-04-29 11:37:25,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +60: [2023-04-29 11:37:25,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +60: [2023-04-29 11:37:25,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +25: [2023-04-29 11:37:25,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +19: [2023-04-29 11:37:25,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +15: [2023-04-29 11:37:25,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +15: [2023-04-29 11:37:25,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +15: [2023-04-29 11:37:25,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +59: [2023-04-29 11:37:25,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +15: [2023-04-29 11:37:25,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +19: [2023-04-29 11:37:25,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +59: [2023-04-29 11:37:25,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +59: [2023-04-29 11:37:25,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +19: [2023-04-29 11:37:25,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +10: [2023-04-29 11:37:25,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +50: [2023-04-29 11:37:25,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +54: [2023-04-29 11:37:25,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +54: [2023-04-29 11:37:25,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +25: [2023-04-29 11:37:25,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +19: [2023-04-29 11:37:25,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +42: [2023-04-29 11:37:25,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +25: [2023-04-29 11:37:25,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +27: [2023-04-29 11:37:25,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 4: [2023-04-29 11:37:25,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +23: [2023-04-29 11:37:25,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +23: [2023-04-29 11:37:25,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +54: [2023-04-29 11:37:25,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +55: [2023-04-29 11:37:25,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +55: [2023-04-29 11:37:25,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +52: [2023-04-29 11:37:25,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +60: [2023-04-29 11:37:25,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +52: [2023-04-29 11:37:25,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +60: [2023-04-29 11:37:25,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +58: [2023-04-29 11:37:25,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +58: [2023-04-29 11:37:25,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +23: [2023-04-29 11:37:25,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +19: [2023-04-29 11:37:25,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +19: [2023-04-29 11:37:25,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +23: [2023-04-29 11:37:25,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +23: [2023-04-29 11:37:25,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 6: [2023-04-29 11:37:25,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +62: [2023-04-29 11:37:25,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +62: [2023-04-29 11:37:25,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +23: [2023-04-29 11:37:25,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +23: [2023-04-29 11:37:25,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +23: [2023-04-29 11:37:25,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +58: [2023-04-29 11:37:25,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +58: [2023-04-29 11:37:25,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +14: [2023-04-29 11:37:25,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +14: [2023-04-29 11:37:25,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +55: [2023-04-29 11:37:25,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +55: [2023-04-29 11:37:25,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +10: [2023-04-29 11:37:25,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +19: [2023-04-29 11:37:25,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +19: [2023-04-29 11:37:25,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +48: [2023-04-29 11:37:25,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +55: [2023-04-29 11:37:25,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +55: [2023-04-29 11:37:25,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +55: [2023-04-29 11:37:25,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +44: [2023-04-29 11:37:25,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +52: [2023-04-29 11:37:25,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +27: [2023-04-29 11:37:25,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +44: [2023-04-29 11:37:25,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +55: [2023-04-29 11:37:25,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +54: [2023-04-29 11:37:25,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +10: [2023-04-29 11:37:25,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +44: [2023-04-29 11:37:25,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +53: [2023-04-29 11:37:25,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +53: [2023-04-29 11:37:25,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +53: [2023-04-29 11:37:25,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +32: [2023-04-29 11:37:25,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +44: [2023-04-29 11:37:25,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +10: [2023-04-29 11:37:25,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +14: [2023-04-29 11:37:25,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +27: [2023-04-29 11:37:25,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +27: [2023-04-29 11:37:25,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +43: [2023-04-29 11:37:25,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. + 6: [2023-04-29 11:37:25,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +19: [2023-04-29 11:37:25,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 6: [2023-04-29 11:37:25,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 6: [2023-04-29 11:37:25,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +19: [2023-04-29 11:37:25,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +23: [2023-04-29 11:37:25,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +23: [2023-04-29 11:37:25,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +23: [2023-04-29 11:37:25,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +48: [2023-04-29 11:37:25,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 3: [2023-04-29 11:37:25,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 3: [2023-04-29 11:37:25,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +23: [2023-04-29 11:37:25,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +32: [2023-04-29 11:37:25,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +33: [2023-04-29 11:37:25,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +33: [2023-04-29 11:37:25,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. + 3: [2023-04-29 11:37:25,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +31: [2023-04-29 11:37:25,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +31: [2023-04-29 11:37:25,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +31: [2023-04-29 11:37:25,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 3: [2023-04-29 11:37:25,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +55: [2023-04-29 11:37:25,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 3: [2023-04-29 11:37:25,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +55: [2023-04-29 11:37:25,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 3: [2023-04-29 11:37:25,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 3: [2023-04-29 11:37:25,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +55: [2023-04-29 11:37:25,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +33: [2023-04-29 11:37:25,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. + 3: [2023-04-29 11:37:25,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +14: [2023-04-29 11:37:25,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +31: [2023-04-29 11:37:25,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +33: [2023-04-29 11:37:25,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +55: [2023-04-29 11:37:25,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +55: [2023-04-29 11:37:25,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +11: [2023-04-29 11:37:25,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +25: [2023-04-29 11:37:25,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +55: [2023-04-29 11:37:25,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... + 4: [2023-04-29 11:37:25,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 4: [2023-04-29 11:37:25,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 4: [2023-04-29 11:37:25,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +55: [2023-04-29 11:37:25,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +23: [2023-04-29 11:37:25,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +23: [2023-04-29 11:37:25,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +48: [2023-04-29 11:37:25,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +55: [2023-04-29 11:37:25,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +48: [2023-04-29 11:37:25,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +23: [2023-04-29 11:37:25,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +23: [2023-04-29 11:37:25,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +38: [2023-04-29 11:37:25,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +29: [2023-04-29 11:37:25,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +16: [2023-04-29 11:37:25,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +45: [2023-04-29 11:37:25,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +45: [2023-04-29 11:37:25,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +16: [2023-04-29 11:37:25,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 3: [2023-04-29 11:37:25,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 3: [2023-04-29 11:37:25,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +34: [2023-04-29 11:37:25,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +61: [2023-04-29 11:37:25,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +61: [2023-04-29 11:37:25,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. + 3: [2023-04-29 11:37:25,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +32: [2023-04-29 11:37:25,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +13: [2023-04-29 11:37:25,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +13: [2023-04-29 11:37:25,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +43: [2023-04-29 11:37:25,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +62: [2023-04-29 11:37:25,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... + 3: [2023-04-29 11:37:25,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +32: [2023-04-29 11:37:25,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. + 3: [2023-04-29 11:37:25,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +62: [2023-04-29 11:37:25,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +43: [2023-04-29 11:37:25,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. + 3: [2023-04-29 11:37:25,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 3: [2023-04-29 11:37:25,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +28: [2023-04-29 11:37:25,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +28: [2023-04-29 11:37:25,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +11: [2023-04-29 11:37:25,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 3: [2023-04-29 11:37:25,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +17: [2023-04-29 11:37:25,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +38: [2023-04-29 11:37:25,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +45: [2023-04-29 11:37:25,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +45: [2023-04-29 11:37:25,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +28: [2023-04-29 11:37:25,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +28: [2023-04-29 11:37:25,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +28: [2023-04-29 11:37:25,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +43: [2023-04-29 11:37:25,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. + 5: [2023-04-29 11:37:25,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 5: [2023-04-29 11:37:25,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +28: [2023-04-29 11:37:25,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +28: [2023-04-29 11:37:25,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +34: [2023-04-29 11:37:25,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +28: [2023-04-29 11:37:25,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +19: [2023-04-29 11:37:25,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +61: [2023-04-29 11:37:25,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +61: [2023-04-29 11:37:25,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +61: [2023-04-29 11:37:25,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +17: [2023-04-29 11:37:25,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +17: [2023-04-29 11:37:25,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +17: [2023-04-29 11:37:25,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 9: [2023-04-29 11:37:25,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 5: [2023-04-29 11:37:25,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +10: [2023-04-29 11:37:25,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 5: [2023-04-29 11:37:25,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 5: [2023-04-29 11:37:25,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 5: [2023-04-29 11:37:25,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 5: [2023-04-29 11:37:25,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +60: [2023-04-29 11:37:25,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +60: [2023-04-29 11:37:25,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... + 1: [2023-04-29 11:37:25,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 1: [2023-04-29 11:37:25,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 5: [2023-04-29 11:37:25,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +56: [2023-04-29 11:37:25,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +32: [2023-04-29 11:37:25,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +32: [2023-04-29 11:37:25,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +10: [2023-04-29 11:37:25,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +11: [2023-04-29 11:37:25,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +15: [2023-04-29 11:37:25,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +12: [2023-04-29 11:37:25,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +11: [2023-04-29 11:37:25,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +12: [2023-04-29 11:37:25,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +61: [2023-04-29 11:37:25,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +61: [2023-04-29 11:37:25,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +15: [2023-04-29 11:37:25,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +10: [2023-04-29 11:37:25,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +28: [2023-04-29 11:37:25,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +28: [2023-04-29 11:37:25,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +10: [2023-04-29 11:37:25,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +25: [2023-04-29 11:37:25,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +28: [2023-04-29 11:37:25,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +28: [2023-04-29 11:37:25,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +25: [2023-04-29 11:37:25,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +28: [2023-04-29 11:37:25,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +32: [2023-04-29 11:37:25,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +32: [2023-04-29 11:37:25,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +18: [2023-04-29 11:37:25,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +18: [2023-04-29 11:37:25,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +28: [2023-04-29 11:37:25,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +29: [2023-04-29 11:37:25,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +29: [2023-04-29 11:37:25,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +29: [2023-04-29 11:37:25,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +28: [2023-04-29 11:37:25,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +18: [2023-04-29 11:37:25,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +18: [2023-04-29 11:37:25,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 4: [2023-04-29 11:37:25,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +28: [2023-04-29 11:37:25,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +12: [2023-04-29 11:37:25,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +12: [2023-04-29 11:37:25,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +18: [2023-04-29 11:37:25,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +18: [2023-04-29 11:37:25,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 1: [2023-04-29 11:37:25,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +12: [2023-04-29 11:37:25,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +12: [2023-04-29 11:37:25,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +12: [2023-04-29 11:37:25,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 5: [2023-04-29 11:37:25,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 5: [2023-04-29 11:37:25,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 1: [2023-04-29 11:37:25,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +38: [2023-04-29 11:37:25,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +15: [2023-04-29 11:37:25,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +12: [2023-04-29 11:37:25,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 5: [2023-04-29 11:37:25,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +56: [2023-04-29 11:37:25,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. + 0: [2023-04-29 11:37:25,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 0: [2023-04-29 11:37:25,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +16: [2023-04-29 11:37:25,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +13: [2023-04-29 11:37:25,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 5: [2023-04-29 11:37:25,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 0: [2023-04-29 11:37:25,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. + 6: [2023-04-29 11:37:25,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +15: [2023-04-29 11:37:25,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 0: [2023-04-29 11:37:25,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_03-model_01-model_states.pt. +46: [2023-04-29 11:37:25,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +46: [2023-04-29 11:37:25,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +27: [2023-04-29 11:37:25,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +15: [2023-04-29 11:37:25,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +41: [2023-04-29 11:37:25,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +60: [2023-04-29 11:37:25,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +15: [2023-04-29 11:37:25,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +15: [2023-04-29 11:37:25,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +38: [2023-04-29 11:37:25,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. + 5: [2023-04-29 11:37:25,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 9: [2023-04-29 11:37:25,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 9: [2023-04-29 11:37:25,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +19: [2023-04-29 11:37:25,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +34: [2023-04-29 11:37:25,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +34: [2023-04-29 11:37:25,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. + 5: [2023-04-29 11:37:25,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +18: [2023-04-29 11:37:25,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 5: [2023-04-29 11:37:25,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +13: [2023-04-29 11:37:25,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 5: [2023-04-29 11:37:25,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +16: [2023-04-29 11:37:25,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +18: [2023-04-29 11:37:25,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +12: [2023-04-29 11:37:25,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +42: [2023-04-29 11:37:25,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +12: [2023-04-29 11:37:25,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +56: [2023-04-29 11:37:25,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +56: [2023-04-29 11:37:25,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +32: [2023-04-29 11:37:25,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +32: [2023-04-29 11:37:25,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... + 9: [2023-04-29 11:37:25,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +19: [2023-04-29 11:37:25,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +58: [2023-04-29 11:37:25,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +58: [2023-04-29 11:37:25,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +12: [2023-04-29 11:37:25,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +61: [2023-04-29 11:37:25,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +58: [2023-04-29 11:37:25,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +58: [2023-04-29 11:37:25,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +15: [2023-04-29 11:37:25,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +25: [2023-04-29 11:37:25,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +60: [2023-04-29 11:37:25,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +43: [2023-04-29 11:37:25,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +41: [2023-04-29 11:37:25,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +41: [2023-04-29 11:37:25,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. + 6: [2023-04-29 11:37:25,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +27: [2023-04-29 11:37:25,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 6: [2023-04-29 11:37:25,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 6: [2023-04-29 11:37:25,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +14: [2023-04-29 11:37:25,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +14: [2023-04-29 11:37:25,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +46: [2023-04-29 11:37:25,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +27: [2023-04-29 11:37:25,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +46: [2023-04-29 11:37:25,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +26: [2023-04-29 11:37:25,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +26: [2023-04-29 11:37:25,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +19: [2023-04-29 11:37:25,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +12: [2023-04-29 11:37:25,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +14: [2023-04-29 11:37:25,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +18: [2023-04-29 11:37:25,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +11: [2023-04-29 11:37:25,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +27: [2023-04-29 11:37:25,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +18: [2023-04-29 11:37:25,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +18: [2023-04-29 11:37:25,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +42: [2023-04-29 11:37:25,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +38: [2023-04-29 11:37:25,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +26: [2023-04-29 11:37:25,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +13: [2023-04-29 11:37:25,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +13: [2023-04-29 11:37:25,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +26: [2023-04-29 11:37:25,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +13: [2023-04-29 11:37:25,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +13: [2023-04-29 11:37:25,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +33: [2023-04-29 11:37:25,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +12: [2023-04-29 11:37:25,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +12: [2023-04-29 11:37:25,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +31: [2023-04-29 11:37:25,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +41: [2023-04-29 11:37:25,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +41: [2023-04-29 11:37:25,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +41: [2023-04-29 11:37:25,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +12: [2023-04-29 11:37:25,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +41: [2023-04-29 11:37:25,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +12: [2023-04-29 11:37:25,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +34: [2023-04-29 11:37:25,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +31: [2023-04-29 11:37:25,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +31: [2023-04-29 11:37:25,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +31: [2023-04-29 11:37:25,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +43: [2023-04-29 11:37:25,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +31: [2023-04-29 11:37:25,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +18: [2023-04-29 11:37:25,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +41: [2023-04-29 11:37:25,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +41: [2023-04-29 11:37:25,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +45: [2023-04-29 11:37:25,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +45: [2023-04-29 11:37:25,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +29: [2023-04-29 11:37:25,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +34: [2023-04-29 11:37:25,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +11: [2023-04-29 11:37:25,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +25: [2023-04-29 11:37:25,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +25: [2023-04-29 11:37:25,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +25: [2023-04-29 11:37:25,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +42: [2023-04-29 11:37:25,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +42: [2023-04-29 11:37:25,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +31: [2023-04-29 11:37:25,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +31: [2023-04-29 11:37:25,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +31: [2023-04-29 11:37:25,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +33: [2023-04-29 11:37:25,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +33: [2023-04-29 11:37:25,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +33: [2023-04-29 11:37:25,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +17: [2023-04-29 11:37:25,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +43: [2023-04-29 11:37:25,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +14: [2023-04-29 11:37:25,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +43: [2023-04-29 11:37:25,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +26: [2023-04-29 11:37:25,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +26: [2023-04-29 11:37:25,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +45: [2023-04-29 11:37:25,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +45: [2023-04-29 11:37:25,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +19: [2023-04-29 11:37:25,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +38: [2023-04-29 11:37:25,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... + 4: [2023-04-29 11:37:25,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 9: [2023-04-29 11:37:25,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +26: [2023-04-29 11:37:25,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 4: [2023-04-29 11:37:25,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 4: [2023-04-29 11:37:25,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +25: [2023-04-29 11:37:25,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +25: [2023-04-29 11:37:25,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +17: [2023-04-29 11:37:25,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +26: [2023-04-29 11:37:25,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +25: [2023-04-29 11:37:25,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +61: [2023-04-29 11:37:25,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +56: [2023-04-29 11:37:25,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +17: [2023-04-29 11:37:25,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +17: [2023-04-29 11:37:25,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +61: [2023-04-29 11:37:25,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +41: [2023-04-29 11:37:25,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +11: [2023-04-29 11:37:25,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +42: [2023-04-29 11:37:25,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +42: [2023-04-29 11:37:25,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +11: [2023-04-29 11:37:25,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +25: [2023-04-29 11:37:25,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +42: [2023-04-29 11:37:25,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +18: [2023-04-29 11:37:25,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +18: [2023-04-29 11:37:25,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 1: [2023-04-29 11:37:25,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 1: [2023-04-29 11:37:25,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... + 1: [2023-04-29 11:37:25,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +22: [2023-04-29 11:37:25,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +29: [2023-04-29 11:37:25,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 1: [2023-04-29 11:37:25,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +35: [2023-04-29 11:37:25,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +35: [2023-04-29 11:37:25,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +46: [2023-04-29 11:37:25,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +29: [2023-04-29 11:37:25,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +29: [2023-04-29 11:37:25,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 0: [2023-04-29 11:37:25,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +15: [2023-04-29 11:37:25,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 0: [2023-04-29 11:37:25,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +49: [2023-04-29 11:37:25,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +49: [2023-04-29 11:37:25,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +38: [2023-04-29 11:37:25,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +53: [2023-04-29 11:37:25,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +53: [2023-04-29 11:37:25,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. + 0: [2023-04-29 11:37:25,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +18: [2023-04-29 11:37:25,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +35: [2023-04-29 11:37:25,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +46: [2023-04-29 11:37:25,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 0: [2023-04-29 11:37:25,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +53: [2023-04-29 11:37:25,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +18: [2023-04-29 11:37:25,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +35: [2023-04-29 11:37:25,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +25: [2023-04-29 11:37:25,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +41: [2023-04-29 11:37:25,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +61: [2023-04-29 11:37:25,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +53: [2023-04-29 11:37:25,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_25-model_01-model_states.pt. +61: [2023-04-29 11:37:25,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +61: [2023-04-29 11:37:25,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +49: [2023-04-29 11:37:25,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +22: [2023-04-29 11:37:25,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +49: [2023-04-29 11:37:25,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +38: [2023-04-29 11:37:25,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +15: [2023-04-29 11:37:25,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +46: [2023-04-29 11:37:25,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +26: [2023-04-29 11:37:25,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +61: [2023-04-29 11:37:25,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +34: [2023-04-29 11:37:25,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +56: [2023-04-29 11:37:25,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +15: [2023-04-29 11:37:25,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +59: [2023-04-29 11:37:25,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +59: [2023-04-29 11:37:25,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +42: [2023-04-29 11:37:25,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +34: [2023-04-29 11:37:25,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +13: [2023-04-29 11:37:25,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +13: [2023-04-29 11:37:25,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +46: [2023-04-29 11:37:25,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +41: [2023-04-29 11:37:25,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +15: [2023-04-29 11:37:25,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +22: [2023-04-29 11:37:25,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 1: [2023-04-29 11:37:25,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 9: [2023-04-29 11:37:25,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 9: [2023-04-29 11:37:25,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +22: [2023-04-29 11:37:25,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +22: [2023-04-29 11:37:25,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +56: [2023-04-29 11:37:25,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +59: [2023-04-29 11:37:25,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +59: [2023-04-29 11:37:25,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +61: [2023-04-29 11:37:25,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +56: [2023-04-29 11:37:25,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... + 9: [2023-04-29 11:37:25,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 1: [2023-04-29 11:37:25,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 1: [2023-04-29 11:37:25,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +46: [2023-04-29 11:37:25,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +26: [2023-04-29 11:37:25,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +26: [2023-04-29 11:37:25,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +46: [2023-04-29 11:37:25,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +26: [2023-04-29 11:37:25,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +22: [2023-04-29 11:37:25,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 1: [2023-04-29 11:37:25,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +22: [2023-04-29 11:37:25,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +22: [2023-04-29 11:37:25,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +61: [2023-04-29 11:37:25,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +31: [2023-04-29 11:37:25,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +41: [2023-04-29 11:37:25,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +41: [2023-04-29 11:37:25,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +23: [2023-04-29 11:37:25,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +54: [2023-04-29 11:37:25,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +54: [2023-04-29 11:37:25,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +23: [2023-04-29 11:37:25,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +54: [2023-04-29 11:37:25,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +54: [2023-04-29 11:37:25,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +54: [2023-04-29 11:37:25,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +54: [2023-04-29 11:37:25,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +26: [2023-04-29 11:37:25,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +41: [2023-04-29 11:37:25,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +39: [2023-04-29 11:37:25,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +39: [2023-04-29 11:37:25,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +31: [2023-04-29 11:37:25,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +55: [2023-04-29 11:37:25,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +31: [2023-04-29 11:37:25,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +48: [2023-04-29 11:37:25,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +48: [2023-04-29 11:37:25,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +26: [2023-04-29 11:37:25,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +26: [2023-04-29 11:37:25,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 3: [2023-04-29 11:37:25,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +54: [2023-04-29 11:37:25,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +41: [2023-04-29 11:37:25,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +54: [2023-04-29 11:37:25,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +54: [2023-04-29 11:37:25,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +54: [2023-04-29 11:37:25,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +31: [2023-04-29 11:37:25,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +13: [2023-04-29 11:37:25,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +13: [2023-04-29 11:37:25,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +54: [2023-04-29 11:37:25,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +54: [2023-04-29 11:37:25,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +39: [2023-04-29 11:37:25,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +39: [2023-04-29 11:37:25,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +39: [2023-04-29 11:37:25,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +39: [2023-04-29 11:37:25,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +39: [2023-04-29 11:37:25,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +55: [2023-04-29 11:37:25,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +39: [2023-04-29 11:37:25,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. + 3: [2023-04-29 11:37:25,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +54: [2023-04-29 11:37:25,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +48: [2023-04-29 11:37:25,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +48: [2023-04-29 11:37:25,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +48: [2023-04-29 11:37:25,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +26: [2023-04-29 11:37:25,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +55: [2023-04-29 11:37:25,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +23: [2023-04-29 11:37:25,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +23: [2023-04-29 11:37:25,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +49: [2023-04-29 11:37:25,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +35: [2023-04-29 11:37:25,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +46: [2023-04-29 11:37:25,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +49: [2023-04-29 11:37:25,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +39: [2023-04-29 11:37:25,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +46: [2023-04-29 11:37:25,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +39: [2023-04-29 11:37:25,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +48: [2023-04-29 11:37:25,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +49: [2023-04-29 11:37:25,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +39: [2023-04-29 11:37:25,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +10: [2023-04-29 11:37:25,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +48: [2023-04-29 11:37:25,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +48: [2023-04-29 11:37:25,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +35: [2023-04-29 11:37:25,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +53: [2023-04-29 11:37:25,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +59: [2023-04-29 11:37:25,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +48: [2023-04-29 11:37:25,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +59: [2023-04-29 11:37:25,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +39: [2023-04-29 11:37:25,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +39: [2023-04-29 11:37:25,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +54: [2023-04-29 11:37:25,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +49: [2023-04-29 11:37:25,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +39: [2023-04-29 11:37:25,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +48: [2023-04-29 11:37:25,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +53: [2023-04-29 11:37:25,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +54: [2023-04-29 11:37:25,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... + 3: [2023-04-29 11:37:25,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 3: [2023-04-29 11:37:25,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +53: [2023-04-29 11:37:25,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... +55: [2023-04-29 11:37:25,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +39: [2023-04-29 11:37:25,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +53: [2023-04-29 11:37:25,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt... + 1: [2023-04-29 11:37:25,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +39: [2023-04-29 11:37:25,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +48: [2023-04-29 11:37:25,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +48: [2023-04-29 11:37:25,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +48: [2023-04-29 11:37:25,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +47: [2023-04-29 11:37:25,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +47: [2023-04-29 11:37:25,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +28: [2023-04-29 11:37:25,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +10: [2023-04-29 11:37:25,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +35: [2023-04-29 11:37:25,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +47: [2023-04-29 11:37:25,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +46: [2023-04-29 11:37:25,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +10: [2023-04-29 11:37:25,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +35: [2023-04-29 11:37:25,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +47: [2023-04-29 11:37:25,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. + 1: [2023-04-29 11:37:25,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +59: [2023-04-29 11:37:25,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +59: [2023-04-29 11:37:25,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +28: [2023-04-29 11:37:25,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +54: [2023-04-29 11:37:25,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +46: [2023-04-29 11:37:25,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +10: [2023-04-29 11:37:25,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +10: [2023-04-29 11:37:25,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 1: [2023-04-29 11:37:25,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +23: [2023-04-29 11:37:25,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +16: [2023-04-29 11:37:25,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +16: [2023-04-29 11:37:25,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +12: [2023-04-29 11:37:25,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +48: [2023-04-29 11:37:25,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +48: [2023-04-29 11:37:25,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +48: [2023-04-29 11:37:25,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +28: [2023-04-29 11:37:25,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +16: [2023-04-29 11:37:25,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +16: [2023-04-29 11:37:25,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +16: [2023-04-29 11:37:25,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +16: [2023-04-29 11:37:25,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +28: [2023-04-29 11:37:25,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 1: [2023-04-29 11:37:25,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +23: [2023-04-29 11:37:25,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +10: [2023-04-29 11:37:25,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +12: [2023-04-29 11:37:25,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 3: [2023-04-29 11:37:25,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +10: [2023-04-29 11:37:25,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +18: [2023-04-29 11:37:25,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +16: [2023-04-29 11:37:25,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +16: [2023-04-29 11:37:25,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +57: [2023-04-29 11:37:25,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +57: [2023-04-29 11:37:25,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +57: [2023-04-29 11:37:25,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. + 5: [2023-04-29 11:37:25,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 5: [2023-04-29 11:37:25,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +57: [2023-04-29 11:37:25,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. + 5: [2023-04-29 11:37:25,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +15: [2023-04-29 11:37:25,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 3: [2023-04-29 11:37:25,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +55: [2023-04-29 11:37:25,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +12: [2023-04-29 11:37:25,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +12: [2023-04-29 11:37:25,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +16: [2023-04-29 11:37:25,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +33: [2023-04-29 11:37:25,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +33: [2023-04-29 11:37:25,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +33: [2023-04-29 11:37:25,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +58: [2023-04-29 11:37:25,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +58: [2023-04-29 11:37:25,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +58: [2023-04-29 11:37:25,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +58: [2023-04-29 11:37:25,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +58: [2023-04-29 11:37:25,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +58: [2023-04-29 11:37:25,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +58: [2023-04-29 11:37:25,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. + 5: [2023-04-29 11:37:25,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +58: [2023-04-29 11:37:25,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +10: [2023-04-29 11:37:25,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +15: [2023-04-29 11:37:25,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +15: [2023-04-29 11:37:25,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +33: [2023-04-29 11:37:25,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +55: [2023-04-29 11:37:25,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +55: [2023-04-29 11:37:25,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +23: [2023-04-29 11:37:25,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +23: [2023-04-29 11:37:25,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +15: [2023-04-29 11:37:25,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +13: [2023-04-29 11:37:25,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +15: [2023-04-29 11:37:25,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +33: [2023-04-29 11:37:25,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +16: [2023-04-29 11:37:25,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +58: [2023-04-29 11:37:25,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +58: [2023-04-29 11:37:25,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +58: [2023-04-29 11:37:25,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +46: [2023-04-29 11:37:25,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +16: [2023-04-29 11:37:25,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +58: [2023-04-29 11:37:25,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +26: [2023-04-29 11:37:25,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +58: [2023-04-29 11:37:25,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +16: [2023-04-29 11:37:25,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +33: [2023-04-29 11:37:25,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +33: [2023-04-29 11:37:25,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +33: [2023-04-29 11:37:25,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +15: [2023-04-29 11:37:25,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +46: [2023-04-29 11:37:25,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +58: [2023-04-29 11:37:25,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +16: [2023-04-29 11:37:25,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +15: [2023-04-29 11:37:25,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +16: [2023-04-29 11:37:25,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt... +33: [2023-04-29 11:37:25,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +58: [2023-04-29 11:37:25,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +58: [2023-04-29 11:37:25,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +28: [2023-04-29 11:37:25,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +33: [2023-04-29 11:37:25,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +55: [2023-04-29 11:37:25,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +47: [2023-04-29 11:37:25,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +28: [2023-04-29 11:37:25,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 3: [2023-04-29 11:37:25,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +26: [2023-04-29 11:37:25,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +26: [2023-04-29 11:37:25,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +33: [2023-04-29 11:37:25,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +15: [2023-04-29 11:37:25,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +16: [2023-04-29 11:37:25,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +61: [2023-04-29 11:37:25,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +13: [2023-04-29 11:37:25,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +26: [2023-04-29 11:37:25,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +47: [2023-04-29 11:37:25,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +33: [2023-04-29 11:37:25,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... + 3: [2023-04-29 11:37:25,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +31: [2023-04-29 11:37:25,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +47: [2023-04-29 11:37:25,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +18: [2023-04-29 11:37:25,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +16: [2023-04-29 11:37:25,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +28: [2023-04-29 11:37:25,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +31: [2023-04-29 11:37:25,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +31: [2023-04-29 11:37:25,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +13: [2023-04-29 11:37:25,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +13: [2023-04-29 11:37:25,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +49: [2023-04-29 11:37:25,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +49: [2023-04-29 11:37:25,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +47: [2023-04-29 11:37:25,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +18: [2023-04-29 11:37:25,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 0: [2023-04-29 11:37:25,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 0: [2023-04-29 11:37:25,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 0: [2023-04-29 11:37:25,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +49: [2023-04-29 11:37:25,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +49: [2023-04-29 11:37:25,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +33: [2023-04-29 11:37:25,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +12: [2023-04-29 11:37:25,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +61: [2023-04-29 11:37:25,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... + 0: [2023-04-29 11:37:25,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +33: [2023-04-29 11:37:25,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +18: [2023-04-29 11:37:25,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +18: [2023-04-29 11:37:25,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +13: [2023-04-29 11:37:25,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +31: [2023-04-29 11:37:25,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +18: [2023-04-29 11:37:25,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +46: [2023-04-29 11:37:25,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +18: [2023-04-29 11:37:25,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 1: [2023-04-29 11:37:25,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +57: [2023-04-29 11:37:25,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +28: [2023-04-29 11:37:25,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +49: [2023-04-29 11:37:25,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +49: [2023-04-29 11:37:25,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +31: [2023-04-29 11:37:25,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +54: [2023-04-29 11:37:25,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +31: [2023-04-29 11:37:25,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +31: [2023-04-29 11:37:25,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +49: [2023-04-29 11:37:25,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +46: [2023-04-29 11:37:25,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +49: [2023-04-29 11:37:25,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +12: [2023-04-29 11:37:25,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +57: [2023-04-29 11:37:25,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +13: [2023-04-29 11:37:25,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +13: [2023-04-29 11:37:25,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 0: [2023-04-29 11:37:25,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 0: [2023-04-29 11:37:25,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 0: [2023-04-29 11:37:25,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +33: [2023-04-29 11:37:25,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... + 0: [2023-04-29 11:37:25,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +18: [2023-04-29 11:37:25,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +18: [2023-04-29 11:37:25,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 1: [2023-04-29 11:37:25,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +31: [2023-04-29 11:37:25,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +33: [2023-04-29 11:37:25,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +61: [2023-04-29 11:37:25,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +61: [2023-04-29 11:37:25,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +61: [2023-04-29 11:37:25,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +12: [2023-04-29 11:37:25,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +46: [2023-04-29 11:37:25,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +57: [2023-04-29 11:37:25,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +57: [2023-04-29 11:37:25,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +13: [2023-04-29 11:37:25,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +12: [2023-04-29 11:37:25,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +46: [2023-04-29 11:37:25,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... + 1: [2023-04-29 11:37:25,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 1: [2023-04-29 11:37:25,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. + 1: [2023-04-29 11:37:25,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 5: [2023-04-29 11:37:25,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 5: [2023-04-29 11:37:25,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 5: [2023-04-29 11:37:25,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 1: [2023-04-29 11:37:25,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +46: [2023-04-29 11:37:25,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +48: [2023-04-29 11:37:25,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +61: [2023-04-29 11:37:25,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +61: [2023-04-29 11:37:25,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +61: [2023-04-29 11:37:25,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... + 1: [2023-04-29 11:37:25,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... + 1: [2023-04-29 11:37:25,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +54: [2023-04-29 11:37:25,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. + 5: [2023-04-29 11:37:25,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +46: [2023-04-29 11:37:25,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +26: [2023-04-29 11:37:25,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +53: [2023-04-29 11:37:25,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +37: [2023-04-29 11:37:25,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +54: [2023-04-29 11:37:25,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +54: [2023-04-29 11:37:25,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +37: [2023-04-29 11:37:25,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +37: [2023-04-29 11:37:25,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +39: [2023-04-29 11:37:25,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +37: [2023-04-29 11:37:25,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +26: [2023-04-29 11:37:25,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +26: [2023-04-29 11:37:25,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +48: [2023-04-29 11:37:25,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +49: [2023-04-29 11:37:25,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +48: [2023-04-29 11:37:25,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +48: [2023-04-29 11:37:25,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +54: [2023-04-29 11:37:25,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +53: [2023-04-29 11:37:25,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +46: [2023-04-29 11:37:25,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +53: [2023-04-29 11:37:25,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +53: [2023-04-29 11:37:25,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +53: [2023-04-29 11:37:25,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +18: [2023-04-29 11:37:25,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +18: [2023-04-29 11:37:25,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +39: [2023-04-29 11:37:25,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +26: [2023-04-29 11:37:25,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +49: [2023-04-29 11:37:25,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +39: [2023-04-29 11:37:25,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +18: [2023-04-29 11:37:25,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +49: [2023-04-29 11:37:25,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +46: [2023-04-29 11:37:25,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +39: [2023-04-29 11:37:25,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_00-model_states.pt. +53: [2023-04-29 11:37:25,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +53: [2023-04-29 11:37:25,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +53: [2023-04-29 11:37:25,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt... +49: [2023-04-29 11:37:25,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +40: [2023-04-29 11:37:25,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +40: [2023-04-29 11:37:25,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +40: [2023-04-29 11:37:25,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +40: [2023-04-29 11:37:25,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +18: [2023-04-29 11:37:25,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +49: [2023-04-29 11:37:25,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +18: [2023-04-29 11:37:25,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +18: [2023-04-29 11:37:25,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt... +48: [2023-04-29 11:37:25,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +49: [2023-04-29 11:37:25,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +18: [2023-04-29 11:37:25,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +54: [2023-04-29 11:37:25,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +58: [2023-04-29 11:37:25,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +49: [2023-04-29 11:37:25,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +58: [2023-04-29 11:37:25,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +39: [2023-04-29 11:37:25,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +49: [2023-04-29 11:37:25,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +37: [2023-04-29 11:37:25,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +54: [2023-04-29 11:37:25,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +54: [2023-04-29 11:37:25,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +48: [2023-04-29 11:37:25,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +33: [2023-04-29 11:37:25,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +37: [2023-04-29 11:37:25,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +37: [2023-04-29 11:37:25,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +33: [2023-04-29 11:37:25,998] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +33: [2023-04-29 11:37:25,998] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +63: [2023-04-29 11:37:25,998] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +63: [2023-04-29 11:37:25,998] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +48: [2023-04-29 11:37:25,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +63: [2023-04-29 11:37:25,998] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +63: [2023-04-29 11:37:25,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +48: [2023-04-29 11:37:25,999] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +37: [2023-04-29 11:37:26,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +16: [2023-04-29 11:37:26,000] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +58: [2023-04-29 11:37:26,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +16: [2023-04-29 11:37:26,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +16: [2023-04-29 11:37:26,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +39: [2023-04-29 11:37:26,001] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +49: [2023-04-29 11:37:26,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +39: [2023-04-29 11:37:26,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +33: [2023-04-29 11:37:26,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +39: [2023-04-29 11:37:26,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +16: [2023-04-29 11:37:26,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_00-model_states.pt. +40: [2023-04-29 11:37:26,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +51: [2023-04-29 11:37:26,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +40: [2023-04-29 11:37:26,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +51: [2023-04-29 11:37:26,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +51: [2023-04-29 11:37:26,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +51: [2023-04-29 11:37:26,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +40: [2023-04-29 11:37:26,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +40: [2023-04-29 11:37:26,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +58: [2023-04-29 11:37:26,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +58: [2023-04-29 11:37:26,012] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +58: [2023-04-29 11:37:26,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +49: [2023-04-29 11:37:26,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +33: [2023-04-29 11:37:26,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +33: [2023-04-29 11:37:26,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +33: [2023-04-29 11:37:26,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +49: [2023-04-29 11:37:26,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +63: [2023-04-29 11:37:26,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +63: [2023-04-29 11:37:26,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +63: [2023-04-29 11:37:26,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +33: [2023-04-29 11:37:26,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +63: [2023-04-29 11:37:26,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +49: [2023-04-29 11:37:26,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +58: [2023-04-29 11:37:26,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +16: [2023-04-29 11:37:26,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +51: [2023-04-29 11:37:26,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +16: [2023-04-29 11:37:26,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +49: [2023-04-29 11:37:26,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +51: [2023-04-29 11:37:26,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +44: [2023-04-29 11:37:26,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +44: [2023-04-29 11:37:26,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +44: [2023-04-29 11:37:26,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +44: [2023-04-29 11:37:26,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +44: [2023-04-29 11:37:26,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +44: [2023-04-29 11:37:26,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +44: [2023-04-29 11:37:26,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +51: [2023-04-29 11:37:26,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +51: [2023-04-29 11:37:26,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +44: [2023-04-29 11:37:26,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +16: [2023-04-29 11:37:26,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +58: [2023-04-29 11:37:26,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +44: [2023-04-29 11:37:26,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +44: [2023-04-29 11:37:26,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +44: [2023-04-29 11:37:26,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +44: [2023-04-29 11:37:26,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +44: [2023-04-29 11:37:26,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +44: [2023-04-29 11:37:26,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +44: [2023-04-29 11:37:26,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +44: [2023-04-29 11:37:26,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +16: [2023-04-29 11:37:26,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +49: [2023-04-29 11:37:26,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +62: [2023-04-29 11:37:26,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +49: [2023-04-29 11:37:26,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +62: [2023-04-29 11:37:26,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +62: [2023-04-29 11:37:26,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +62: [2023-04-29 11:37:26,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +49: [2023-04-29 11:37:26,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +37: [2023-04-29 11:37:26,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +37: [2023-04-29 11:37:26,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +37: [2023-04-29 11:37:26,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +37: [2023-04-29 11:37:26,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +37: [2023-04-29 11:37:26,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +37: [2023-04-29 11:37:26,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +37: [2023-04-29 11:37:26,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +37: [2023-04-29 11:37:26,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +37: [2023-04-29 11:37:26,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +37: [2023-04-29 11:37:26,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +37: [2023-04-29 11:37:26,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +37: [2023-04-29 11:37:26,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +37: [2023-04-29 11:37:26,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +37: [2023-04-29 11:37:26,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +37: [2023-04-29 11:37:26,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +37: [2023-04-29 11:37:26,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +44: [2023-04-29 11:37:26,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +62: [2023-04-29 11:37:26,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +62: [2023-04-29 11:37:26,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +62: [2023-04-29 11:37:26,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +62: [2023-04-29 11:37:26,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +44: [2023-04-29 11:37:26,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +44: [2023-04-29 11:37:26,112] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +57: [2023-04-29 11:37:26,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +57: [2023-04-29 11:37:26,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +36: [2023-04-29 11:37:26,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +36: [2023-04-29 11:37:26,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +57: [2023-04-29 11:37:26,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +57: [2023-04-29 11:37:26,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +57: [2023-04-29 11:37:26,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +57: [2023-04-29 11:37:26,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +57: [2023-04-29 11:37:26,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +36: [2023-04-29 11:37:26,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +57: [2023-04-29 11:37:26,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +36: [2023-04-29 11:37:26,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +44: [2023-04-29 11:37:26,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +50: [2023-04-29 11:37:26,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +50: [2023-04-29 11:37:26,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +50: [2023-04-29 11:37:26,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +50: [2023-04-29 11:37:26,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +44: [2023-04-29 11:37:26,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +57: [2023-04-29 11:37:26,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +57: [2023-04-29 11:37:26,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +57: [2023-04-29 11:37:26,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +57: [2023-04-29 11:37:26,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +57: [2023-04-29 11:37:26,123] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +57: [2023-04-29 11:37:26,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +57: [2023-04-29 11:37:26,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +57: [2023-04-29 11:37:26,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +44: [2023-04-29 11:37:26,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +52: [2023-04-29 11:37:26,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +52: [2023-04-29 11:37:26,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +52: [2023-04-29 11:37:26,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +52: [2023-04-29 11:37:26,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +37: [2023-04-29 11:37:26,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +44: [2023-04-29 11:37:26,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +36: [2023-04-29 11:37:26,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +36: [2023-04-29 11:37:26,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +44: [2023-04-29 11:37:26,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +36: [2023-04-29 11:37:26,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +36: [2023-04-29 11:37:26,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +50: [2023-04-29 11:37:26,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +50: [2023-04-29 11:37:26,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +43: [2023-04-29 11:37:26,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +43: [2023-04-29 11:37:26,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +43: [2023-04-29 11:37:26,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +43: [2023-04-29 11:37:26,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +35: [2023-04-29 11:37:26,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +35: [2023-04-29 11:37:26,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +50: [2023-04-29 11:37:26,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +50: [2023-04-29 11:37:26,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +35: [2023-04-29 11:37:26,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +35: [2023-04-29 11:37:26,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +35: [2023-04-29 11:37:26,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +35: [2023-04-29 11:37:26,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +35: [2023-04-29 11:37:26,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +35: [2023-04-29 11:37:26,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +56: [2023-04-29 11:37:26,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +56: [2023-04-29 11:37:26,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +56: [2023-04-29 11:37:26,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +56: [2023-04-29 11:37:26,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +35: [2023-04-29 11:37:26,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +35: [2023-04-29 11:37:26,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +35: [2023-04-29 11:37:26,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +35: [2023-04-29 11:37:26,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +32: [2023-04-29 11:37:26,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +32: [2023-04-29 11:37:26,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +35: [2023-04-29 11:37:26,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +38: [2023-04-29 11:37:26,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +38: [2023-04-29 11:37:26,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +35: [2023-04-29 11:37:26,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +50: [2023-04-29 11:37:26,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +59: [2023-04-29 11:37:26,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +59: [2023-04-29 11:37:26,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +35: [2023-04-29 11:37:26,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +50: [2023-04-29 11:37:26,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +50: [2023-04-29 11:37:26,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +50: [2023-04-29 11:37:26,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +32: [2023-04-29 11:37:26,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +35: [2023-04-29 11:37:26,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +32: [2023-04-29 11:37:26,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +37: [2023-04-29 11:37:26,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +55: [2023-04-29 11:37:26,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +55: [2023-04-29 11:37:26,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +55: [2023-04-29 11:37:26,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +50: [2023-04-29 11:37:26,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +55: [2023-04-29 11:37:26,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +52: [2023-04-29 11:37:26,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +59: [2023-04-29 11:37:26,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +59: [2023-04-29 11:37:26,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +38: [2023-04-29 11:37:26,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +38: [2023-04-29 11:37:26,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +52: [2023-04-29 11:37:26,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +52: [2023-04-29 11:37:26,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +34: [2023-04-29 11:37:26,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +34: [2023-04-29 11:37:26,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +34: [2023-04-29 11:37:26,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +37: [2023-04-29 11:37:26,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +37: [2023-04-29 11:37:26,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +37: [2023-04-29 11:37:26,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +34: [2023-04-29 11:37:26,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +50: [2023-04-29 11:37:26,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +50: [2023-04-29 11:37:26,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +41: [2023-04-29 11:37:26,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +41: [2023-04-29 11:37:26,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +52: [2023-04-29 11:37:26,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +50: [2023-04-29 11:37:26,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +57: [2023-04-29 11:37:26,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +41: [2023-04-29 11:37:26,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +41: [2023-04-29 11:37:26,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +42: [2023-04-29 11:37:26,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +42: [2023-04-29 11:37:26,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +51: [2023-04-29 11:37:26,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +51: [2023-04-29 11:37:26,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +51: [2023-04-29 11:37:26,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +51: [2023-04-29 11:37:26,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +51: [2023-04-29 11:37:26,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +51: [2023-04-29 11:37:26,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +51: [2023-04-29 11:37:26,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +51: [2023-04-29 11:37:26,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +40: [2023-04-29 11:37:26,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +40: [2023-04-29 11:37:26,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +40: [2023-04-29 11:37:26,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +40: [2023-04-29 11:37:26,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +40: [2023-04-29 11:37:26,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +40: [2023-04-29 11:37:26,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +40: [2023-04-29 11:37:26,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +40: [2023-04-29 11:37:26,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +47: [2023-04-29 11:37:26,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +47: [2023-04-29 11:37:26,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +47: [2023-04-29 11:37:26,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +47: [2023-04-29 11:37:26,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +47: [2023-04-29 11:37:26,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +47: [2023-04-29 11:37:26,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +47: [2023-04-29 11:37:26,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +43: [2023-04-29 11:37:26,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +43: [2023-04-29 11:37:26,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +47: [2023-04-29 11:37:26,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +42: [2023-04-29 11:37:26,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +42: [2023-04-29 11:37:26,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +42: [2023-04-29 11:37:26,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +42: [2023-04-29 11:37:26,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +42: [2023-04-29 11:37:26,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +32: [2023-04-29 11:37:26,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +32: [2023-04-29 11:37:26,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +32: [2023-04-29 11:37:26,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +42: [2023-04-29 11:37:26,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +40: [2023-04-29 11:37:26,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +51: [2023-04-29 11:37:26,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +43: [2023-04-29 11:37:26,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +51: [2023-04-29 11:37:26,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +56: [2023-04-29 11:37:26,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +43: [2023-04-29 11:37:26,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +56: [2023-04-29 11:37:26,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +56: [2023-04-29 11:37:26,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +40: [2023-04-29 11:37:26,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +40: [2023-04-29 11:37:26,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +56: [2023-04-29 11:37:26,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +32: [2023-04-29 11:37:26,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +47: [2023-04-29 11:37:26,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +40: [2023-04-29 11:37:26,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +40: [2023-04-29 11:37:26,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +63: [2023-04-29 11:37:26,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +63: [2023-04-29 11:37:26,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +63: [2023-04-29 11:37:26,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +63: [2023-04-29 11:37:26,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +63: [2023-04-29 11:37:26,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +63: [2023-04-29 11:37:26,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +63: [2023-04-29 11:37:26,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +47: [2023-04-29 11:37:26,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +63: [2023-04-29 11:37:26,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +47: [2023-04-29 11:37:26,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +51: [2023-04-29 11:37:26,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +40: [2023-04-29 11:37:26,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +40: [2023-04-29 11:37:26,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +40: [2023-04-29 11:37:26,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +47: [2023-04-29 11:37:26,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +42: [2023-04-29 11:37:26,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +42: [2023-04-29 11:37:26,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +57: [2023-04-29 11:37:26,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +57: [2023-04-29 11:37:26,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +42: [2023-04-29 11:37:26,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +51: [2023-04-29 11:37:26,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +47: [2023-04-29 11:37:26,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +47: [2023-04-29 11:37:26,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +47: [2023-04-29 11:37:26,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +51: [2023-04-29 11:37:26,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +63: [2023-04-29 11:37:26,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +47: [2023-04-29 11:37:26,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +51: [2023-04-29 11:37:26,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +51: [2023-04-29 11:37:26,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +51: [2023-04-29 11:37:26,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +45: [2023-04-29 11:37:26,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +45: [2023-04-29 11:37:26,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +32: [2023-04-29 11:37:26,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +45: [2023-04-29 11:37:26,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +45: [2023-04-29 11:37:26,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +32: [2023-04-29 11:37:26,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +45: [2023-04-29 11:37:26,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +45: [2023-04-29 11:37:26,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +45: [2023-04-29 11:37:26,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +32: [2023-04-29 11:37:26,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +45: [2023-04-29 11:37:26,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +59: [2023-04-29 11:37:26,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +59: [2023-04-29 11:37:26,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +63: [2023-04-29 11:37:26,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +32: [2023-04-29 11:37:26,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +63: [2023-04-29 11:37:26,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +42: [2023-04-29 11:37:26,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +63: [2023-04-29 11:37:26,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +63: [2023-04-29 11:37:26,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +63: [2023-04-29 11:37:26,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +38: [2023-04-29 11:37:26,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +38: [2023-04-29 11:37:26,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +63: [2023-04-29 11:37:26,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +59: [2023-04-29 11:37:26,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +63: [2023-04-29 11:37:26,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +32: [2023-04-29 11:37:26,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +32: [2023-04-29 11:37:26,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +60: [2023-04-29 11:37:26,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +60: [2023-04-29 11:37:26,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +55: [2023-04-29 11:37:26,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +55: [2023-04-29 11:37:26,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +60: [2023-04-29 11:37:26,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +41: [2023-04-29 11:37:26,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +41: [2023-04-29 11:37:26,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +45: [2023-04-29 11:37:26,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +45: [2023-04-29 11:37:26,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +55: [2023-04-29 11:37:26,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +34: [2023-04-29 11:37:26,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +34: [2023-04-29 11:37:26,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +45: [2023-04-29 11:37:26,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +45: [2023-04-29 11:37:26,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +45: [2023-04-29 11:37:26,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +55: [2023-04-29 11:37:26,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +45: [2023-04-29 11:37:26,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +60: [2023-04-29 11:37:26,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +45: [2023-04-29 11:37:26,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +32: [2023-04-29 11:37:26,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +59: [2023-04-29 11:37:26,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +57: [2023-04-29 11:37:26,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +45: [2023-04-29 11:37:26,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +34: [2023-04-29 11:37:26,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +32: [2023-04-29 11:37:26,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +20: [2023-04-29 11:37:26,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +20: [2023-04-29 11:37:26,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +20: [2023-04-29 11:37:26,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +38: [2023-04-29 11:37:26,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +20: [2023-04-29 11:37:26,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +38: [2023-04-29 11:37:26,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +34: [2023-04-29 11:37:26,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +37: [2023-04-29 11:37:26,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +57: [2023-04-29 11:37:26,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +37: [2023-04-29 11:37:26,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +37: [2023-04-29 11:37:26,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +41: [2023-04-29 11:37:26,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +41: [2023-04-29 11:37:26,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +42: [2023-04-29 11:37:26,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +42: [2023-04-29 11:37:26,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +53: [2023-04-29 11:37:26,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +53: [2023-04-29 11:37:26,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +53: [2023-04-29 11:37:26,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +42: [2023-04-29 11:37:26,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +53: [2023-04-29 11:37:26,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +52: [2023-04-29 11:37:26,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +52: [2023-04-29 11:37:26,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +52: [2023-04-29 11:37:26,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +52: [2023-04-29 11:37:26,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +62: [2023-04-29 11:37:26,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +62: [2023-04-29 11:37:26,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +42: [2023-04-29 11:37:26,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +57: [2023-04-29 11:37:26,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +57: [2023-04-29 11:37:26,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +50: [2023-04-29 11:37:26,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +50: [2023-04-29 11:37:26,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +62: [2023-04-29 11:37:26,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +61: [2023-04-29 11:37:26,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +62: [2023-04-29 11:37:26,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +62: [2023-04-29 11:37:26,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +62: [2023-04-29 11:37:26,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +62: [2023-04-29 11:37:26,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +61: [2023-04-29 11:37:26,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +61: [2023-04-29 11:37:26,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +62: [2023-04-29 11:37:26,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +61: [2023-04-29 11:37:26,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +52: [2023-04-29 11:37:26,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +52: [2023-04-29 11:37:26,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +52: [2023-04-29 11:37:26,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +62: [2023-04-29 11:37:26,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +62: [2023-04-29 11:37:26,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +50: [2023-04-29 11:37:26,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +52: [2023-04-29 11:37:26,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +57: [2023-04-29 11:37:26,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +60: [2023-04-29 11:37:26,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +50: [2023-04-29 11:37:26,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +50: [2023-04-29 11:37:26,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +35: [2023-04-29 11:37:26,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +60: [2023-04-29 11:37:26,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +60: [2023-04-29 11:37:26,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +35: [2023-04-29 11:37:26,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +20: [2023-04-29 11:37:26,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +20: [2023-04-29 11:37:26,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +60: [2023-04-29 11:37:26,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +62: [2023-04-29 11:37:26,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +62: [2023-04-29 11:37:26,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +62: [2023-04-29 11:37:26,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +62: [2023-04-29 11:37:26,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +58: [2023-04-29 11:37:26,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +58: [2023-04-29 11:37:26,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +62: [2023-04-29 11:37:26,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +58: [2023-04-29 11:37:26,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +62: [2023-04-29 11:37:26,229] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +58: [2023-04-29 11:37:26,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +20: [2023-04-29 11:37:26,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +35: [2023-04-29 11:37:26,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +52: [2023-04-29 11:37:26,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +53: [2023-04-29 11:37:26,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +20: [2023-04-29 11:37:26,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +52: [2023-04-29 11:37:26,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +50: [2023-04-29 11:37:26,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +53: [2023-04-29 11:37:26,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +47: [2023-04-29 11:37:26,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +52: [2023-04-29 11:37:26,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +53: [2023-04-29 11:37:26,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +53: [2023-04-29 11:37:26,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +39: [2023-04-29 11:37:26,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +39: [2023-04-29 11:37:26,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +39: [2023-04-29 11:37:26,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +39: [2023-04-29 11:37:26,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_26-model_01-model_states.pt. +61: [2023-04-29 11:37:26,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +35: [2023-04-29 11:37:26,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +50: [2023-04-29 11:37:26,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +52: [2023-04-29 11:37:26,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +52: [2023-04-29 11:37:26,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +50: [2023-04-29 11:37:26,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +50: [2023-04-29 11:37:26,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +50: [2023-04-29 11:37:26,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +50: [2023-04-29 11:37:26,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +61: [2023-04-29 11:37:26,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +52: [2023-04-29 11:37:26,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +61: [2023-04-29 11:37:26,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +52: [2023-04-29 11:37:26,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +40: [2023-04-29 11:37:26,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +63: [2023-04-29 11:37:26,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +61: [2023-04-29 11:37:26,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +47: [2023-04-29 11:37:26,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +51: [2023-04-29 11:37:26,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +40: [2023-04-29 11:37:26,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +50: [2023-04-29 11:37:26,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +42: [2023-04-29 11:37:26,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +35: [2023-04-29 11:37:26,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +45: [2023-04-29 11:37:26,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +45: [2023-04-29 11:37:26,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +32: [2023-04-29 11:37:26,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +63: [2023-04-29 11:37:26,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +58: [2023-04-29 11:37:26,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +58: [2023-04-29 11:37:26,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +52: [2023-04-29 11:37:26,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +58: [2023-04-29 11:37:26,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +51: [2023-04-29 11:37:26,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +35: [2023-04-29 11:37:26,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +36: [2023-04-29 11:37:26,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +47: [2023-04-29 11:37:26,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +36: [2023-04-29 11:37:26,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +32: [2023-04-29 11:37:26,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +36: [2023-04-29 11:37:26,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +36: [2023-04-29 11:37:26,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +36: [2023-04-29 11:37:26,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +36: [2023-04-29 11:37:26,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +36: [2023-04-29 11:37:26,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +58: [2023-04-29 11:37:26,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +36: [2023-04-29 11:37:26,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +56: [2023-04-29 11:37:26,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +56: [2023-04-29 11:37:26,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +56: [2023-04-29 11:37:26,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +56: [2023-04-29 11:37:26,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +56: [2023-04-29 11:37:26,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +56: [2023-04-29 11:37:26,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +56: [2023-04-29 11:37:26,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +56: [2023-04-29 11:37:26,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +54: [2023-04-29 11:37:26,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +54: [2023-04-29 11:37:26,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +35: [2023-04-29 11:37:26,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +45: [2023-04-29 11:37:26,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +49: [2023-04-29 11:37:26,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +49: [2023-04-29 11:37:26,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +45: [2023-04-29 11:37:26,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +47: [2023-04-29 11:37:26,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +32: [2023-04-29 11:37:26,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +49: [2023-04-29 11:37:26,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +49: [2023-04-29 11:37:26,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +42: [2023-04-29 11:37:26,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +42: [2023-04-29 11:37:26,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +47: [2023-04-29 11:37:26,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +63: [2023-04-29 11:37:26,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +63: [2023-04-29 11:37:26,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +54: [2023-04-29 11:37:26,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +54: [2023-04-29 11:37:26,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +36: [2023-04-29 11:37:26,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +56: [2023-04-29 11:37:26,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +56: [2023-04-29 11:37:26,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +38: [2023-04-29 11:37:26,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +38: [2023-04-29 11:37:26,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +38: [2023-04-29 11:37:26,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +38: [2023-04-29 11:37:26,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +38: [2023-04-29 11:37:26,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +38: [2023-04-29 11:37:26,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +38: [2023-04-29 11:37:26,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +56: [2023-04-29 11:37:26,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +56: [2023-04-29 11:37:26,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +27: [2023-04-29 11:37:26,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +27: [2023-04-29 11:37:26,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +27: [2023-04-29 11:37:26,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +50: [2023-04-29 11:37:26,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +32: [2023-04-29 11:37:26,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +32: [2023-04-29 11:37:26,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +36: [2023-04-29 11:37:26,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +27: [2023-04-29 11:37:26,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +56: [2023-04-29 11:37:26,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +56: [2023-04-29 11:37:26,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +32: [2023-04-29 11:37:26,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +49: [2023-04-29 11:37:26,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +36: [2023-04-29 11:37:26,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +56: [2023-04-29 11:37:26,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +49: [2023-04-29 11:37:26,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +36: [2023-04-29 11:37:26,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +36: [2023-04-29 11:37:26,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +56: [2023-04-29 11:37:26,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +42: [2023-04-29 11:37:26,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +39: [2023-04-29 11:37:26,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +36: [2023-04-29 11:37:26,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +39: [2023-04-29 11:37:26,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +49: [2023-04-29 11:37:26,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +49: [2023-04-29 11:37:26,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +36: [2023-04-29 11:37:26,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +52: [2023-04-29 11:37:26,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +38: [2023-04-29 11:37:26,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +36: [2023-04-29 11:37:26,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +49: [2023-04-29 11:37:26,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +49: [2023-04-29 11:37:26,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +54: [2023-04-29 11:37:26,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +54: [2023-04-29 11:37:26,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +48: [2023-04-29 11:37:26,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +48: [2023-04-29 11:37:26,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +48: [2023-04-29 11:37:26,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +48: [2023-04-29 11:37:26,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +54: [2023-04-29 11:37:26,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +38: [2023-04-29 11:37:26,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +39: [2023-04-29 11:37:26,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +54: [2023-04-29 11:37:26,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +42: [2023-04-29 11:37:26,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +38: [2023-04-29 11:37:26,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +38: [2023-04-29 11:37:26,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +49: [2023-04-29 11:37:26,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +38: [2023-04-29 11:37:26,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +38: [2023-04-29 11:37:26,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +38: [2023-04-29 11:37:26,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +62: [2023-04-29 11:37:26,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +40: [2023-04-29 11:37:26,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +38: [2023-04-29 11:37:26,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +40: [2023-04-29 11:37:26,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +39: [2023-04-29 11:37:26,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +33: [2023-04-29 11:37:26,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +33: [2023-04-29 11:37:26,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +35: [2023-04-29 11:37:26,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +32: [2023-04-29 11:37:26,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +32: [2023-04-29 11:37:26,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +49: [2023-04-29 11:37:26,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +54: [2023-04-29 11:37:26,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +33: [2023-04-29 11:37:26,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +54: [2023-04-29 11:37:26,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +50: [2023-04-29 11:37:26,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +50: [2023-04-29 11:37:26,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +33: [2023-04-29 11:37:26,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +48: [2023-04-29 11:37:26,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +40: [2023-04-29 11:37:26,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +48: [2023-04-29 11:37:26,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +48: [2023-04-29 11:37:26,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +48: [2023-04-29 11:37:26,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +63: [2023-04-29 11:37:26,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +32: [2023-04-29 11:37:26,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +32: [2023-04-29 11:37:26,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +40: [2023-04-29 11:37:26,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +54: [2023-04-29 11:37:26,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +42: [2023-04-29 11:37:26,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +54: [2023-04-29 11:37:26,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +42: [2023-04-29 11:37:26,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +42: [2023-04-29 11:37:26,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +51: [2023-04-29 11:37:26,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +38: [2023-04-29 11:37:26,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +51: [2023-04-29 11:37:26,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +47: [2023-04-29 11:37:26,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +63: [2023-04-29 11:37:26,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +42: [2023-04-29 11:37:26,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +51: [2023-04-29 11:37:26,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +45: [2023-04-29 11:37:26,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +45: [2023-04-29 11:37:26,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +42: [2023-04-29 11:37:26,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +42: [2023-04-29 11:37:26,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +52: [2023-04-29 11:37:26,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +52: [2023-04-29 11:37:26,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +32: [2023-04-29 11:37:26,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +45: [2023-04-29 11:37:26,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +32: [2023-04-29 11:37:26,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +62: [2023-04-29 11:37:26,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +48: [2023-04-29 11:37:26,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +48: [2023-04-29 11:37:26,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +47: [2023-04-29 11:37:26,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +32: [2023-04-29 11:37:26,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +48: [2023-04-29 11:37:26,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +48: [2023-04-29 11:37:26,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +42: [2023-04-29 11:37:26,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +58: [2023-04-29 11:37:26,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +58: [2023-04-29 11:37:26,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +58: [2023-04-29 11:37:26,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +58: [2023-04-29 11:37:26,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +47: [2023-04-29 11:37:26,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +45: [2023-04-29 11:37:26,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +27: [2023-04-29 11:37:26,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +51: [2023-04-29 11:37:26,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +63: [2023-04-29 11:37:26,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +52: [2023-04-29 11:37:26,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +54: [2023-04-29 11:37:26,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +63: [2023-04-29 11:37:26,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +32: [2023-04-29 11:37:26,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +42: [2023-04-29 11:37:26,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +32: [2023-04-29 11:37:26,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +50: [2023-04-29 11:37:26,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +49: [2023-04-29 11:37:26,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +27: [2023-04-29 11:37:26,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +54: [2023-04-29 11:37:26,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +54: [2023-04-29 11:37:26,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +53: [2023-04-29 11:37:26,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +32: [2023-04-29 11:37:26,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +53: [2023-04-29 11:37:26,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +53: [2023-04-29 11:37:26,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +53: [2023-04-29 11:37:26,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +54: [2023-04-29 11:37:26,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +49: [2023-04-29 11:37:26,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +58: [2023-04-29 11:37:26,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +58: [2023-04-29 11:37:26,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +58: [2023-04-29 11:37:26,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +58: [2023-04-29 11:37:26,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +62: [2023-04-29 11:37:26,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +27: [2023-04-29 11:37:26,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +27: [2023-04-29 11:37:26,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +49: [2023-04-29 11:37:26,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +42: [2023-04-29 11:37:26,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +49: [2023-04-29 11:37:26,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +52: [2023-04-29 11:37:26,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +41: [2023-04-29 11:37:26,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +41: [2023-04-29 11:37:26,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +41: [2023-04-29 11:37:26,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +41: [2023-04-29 11:37:26,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +41: [2023-04-29 11:37:26,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +41: [2023-04-29 11:37:26,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +41: [2023-04-29 11:37:26,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +41: [2023-04-29 11:37:26,301] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +53: [2023-04-29 11:37:26,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +40: [2023-04-29 11:37:26,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +53: [2023-04-29 11:37:26,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +53: [2023-04-29 11:37:26,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +53: [2023-04-29 11:37:26,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +34: [2023-04-29 11:37:26,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +34: [2023-04-29 11:37:26,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +53: [2023-04-29 11:37:26,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +33: [2023-04-29 11:37:26,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +33: [2023-04-29 11:37:26,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +34: [2023-04-29 11:37:26,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +34: [2023-04-29 11:37:26,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +34: [2023-04-29 11:37:26,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +34: [2023-04-29 11:37:26,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +34: [2023-04-29 11:37:26,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +34: [2023-04-29 11:37:26,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +62: [2023-04-29 11:37:26,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +62: [2023-04-29 11:37:26,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +59: [2023-04-29 11:37:26,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +59: [2023-04-29 11:37:26,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +41: [2023-04-29 11:37:26,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +41: [2023-04-29 11:37:26,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +40: [2023-04-29 11:37:26,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +41: [2023-04-29 11:37:26,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +33: [2023-04-29 11:37:26,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +59: [2023-04-29 11:37:26,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +59: [2023-04-29 11:37:26,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +59: [2023-04-29 11:37:26,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +59: [2023-04-29 11:37:26,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +59: [2023-04-29 11:37:26,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +59: [2023-04-29 11:37:26,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +41: [2023-04-29 11:37:26,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +34: [2023-04-29 11:37:26,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +42: [2023-04-29 11:37:26,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +53: [2023-04-29 11:37:26,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +53: [2023-04-29 11:37:26,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +53: [2023-04-29 11:37:26,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +41: [2023-04-29 11:37:26,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +34: [2023-04-29 11:37:26,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +34: [2023-04-29 11:37:26,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +34: [2023-04-29 11:37:26,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +46: [2023-04-29 11:37:26,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +46: [2023-04-29 11:37:26,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +33: [2023-04-29 11:37:26,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +42: [2023-04-29 11:37:26,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +41: [2023-04-29 11:37:26,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +55: [2023-04-29 11:37:26,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +55: [2023-04-29 11:37:26,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +53: [2023-04-29 11:37:26,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +41: [2023-04-29 11:37:26,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +61: [2023-04-29 11:37:26,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +61: [2023-04-29 11:37:26,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +46: [2023-04-29 11:37:26,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +46: [2023-04-29 11:37:26,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +43: [2023-04-29 11:37:26,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +34: [2023-04-29 11:37:26,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +43: [2023-04-29 11:37:26,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +59: [2023-04-29 11:37:26,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +59: [2023-04-29 11:37:26,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +59: [2023-04-29 11:37:26,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +41: [2023-04-29 11:37:26,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +34: [2023-04-29 11:37:26,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +59: [2023-04-29 11:37:26,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +59: [2023-04-29 11:37:26,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +59: [2023-04-29 11:37:26,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +59: [2023-04-29 11:37:26,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +43: [2023-04-29 11:37:26,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +60: [2023-04-29 11:37:26,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +60: [2023-04-29 11:37:26,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +60: [2023-04-29 11:37:26,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +60: [2023-04-29 11:37:26,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +60: [2023-04-29 11:37:26,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +43: [2023-04-29 11:37:26,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +60: [2023-04-29 11:37:26,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +60: [2023-04-29 11:37:26,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +43: [2023-04-29 11:37:26,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +43: [2023-04-29 11:37:26,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +55: [2023-04-29 11:37:26,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +60: [2023-04-29 11:37:26,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +43: [2023-04-29 11:37:26,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +55: [2023-04-29 11:37:26,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +43: [2023-04-29 11:37:26,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +55: [2023-04-29 11:37:26,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +55: [2023-04-29 11:37:26,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +55: [2023-04-29 11:37:26,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +52: [2023-04-29 11:37:26,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +55: [2023-04-29 11:37:26,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +61: [2023-04-29 11:37:26,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +61: [2023-04-29 11:37:26,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +34: [2023-04-29 11:37:26,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +59: [2023-04-29 11:37:26,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +61: [2023-04-29 11:37:26,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +51: [2023-04-29 11:37:26,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +51: [2023-04-29 11:37:26,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +53: [2023-04-29 11:37:26,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +34: [2023-04-29 11:37:26,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +53: [2023-04-29 11:37:26,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +62: [2023-04-29 11:37:26,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +53: [2023-04-29 11:37:26,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +52: [2023-04-29 11:37:26,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +55: [2023-04-29 11:37:26,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +48: [2023-04-29 11:37:26,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +55: [2023-04-29 11:37:26,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +55: [2023-04-29 11:37:26,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +61: [2023-04-29 11:37:26,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +43: [2023-04-29 11:37:26,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +48: [2023-04-29 11:37:26,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +43: [2023-04-29 11:37:26,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +43: [2023-04-29 11:37:26,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +60: [2023-04-29 11:37:26,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +43: [2023-04-29 11:37:26,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +44: [2023-04-29 11:37:26,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +44: [2023-04-29 11:37:26,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +44: [2023-04-29 11:37:26,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +61: [2023-04-29 11:37:26,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +60: [2023-04-29 11:37:26,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +43: [2023-04-29 11:37:26,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +60: [2023-04-29 11:37:26,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +44: [2023-04-29 11:37:26,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +60: [2023-04-29 11:37:26,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +60: [2023-04-29 11:37:26,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +60: [2023-04-29 11:37:26,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +60: [2023-04-29 11:37:26,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +61: [2023-04-29 11:37:26,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +55: [2023-04-29 11:37:26,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +55: [2023-04-29 11:37:26,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +55: [2023-04-29 11:37:26,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +43: [2023-04-29 11:37:26,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +61: [2023-04-29 11:37:26,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +61: [2023-04-29 11:37:26,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +61: [2023-04-29 11:37:26,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +43: [2023-04-29 11:37:26,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +60: [2023-04-29 11:37:26,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +61: [2023-04-29 11:37:26,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +55: [2023-04-29 11:37:26,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +43: [2023-04-29 11:37:26,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +55: [2023-04-29 11:37:26,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +61: [2023-04-29 11:37:26,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +48: [2023-04-29 11:37:26,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +48: [2023-04-29 11:37:26,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 8: [2023-04-29 11:37:26,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. + 8: [2023-04-29 11:37:26,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. + 8: [2023-04-29 11:37:26,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. + 8: [2023-04-29 11:37:26,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +61: [2023-04-29 11:37:26,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +61: [2023-04-29 11:37:26,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +61: [2023-04-29 11:37:26,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +58: [2023-04-29 11:37:26,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +56: [2023-04-29 11:37:26,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +56: [2023-04-29 11:37:26,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +52: [2023-04-29 11:37:26,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +38: [2023-04-29 11:37:26,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +36: [2023-04-29 11:37:26,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +36: [2023-04-29 11:37:26,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +62: [2023-04-29 11:37:26,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +62: [2023-04-29 11:37:26,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +56: [2023-04-29 11:37:26,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +58: [2023-04-29 11:37:26,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +58: [2023-04-29 11:37:26,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +46: [2023-04-29 11:37:26,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +46: [2023-04-29 11:37:26,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +46: [2023-04-29 11:37:26,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +46: [2023-04-29 11:37:26,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 4: [2023-04-29 11:37:26,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. + 4: [2023-04-29 11:37:26,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. + 4: [2023-04-29 11:37:26,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +46: [2023-04-29 11:37:26,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 4: [2023-04-29 11:37:26,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +46: [2023-04-29 11:37:26,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +58: [2023-04-29 11:37:26,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +46: [2023-04-29 11:37:26,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +46: [2023-04-29 11:37:26,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +38: [2023-04-29 11:37:26,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +36: [2023-04-29 11:37:26,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +36: [2023-04-29 11:37:26,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +46: [2023-04-29 11:37:26,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +58: [2023-04-29 11:37:26,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +58: [2023-04-29 11:37:26,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +38: [2023-04-29 11:37:26,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +46: [2023-04-29 11:37:26,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +46: [2023-04-29 11:37:26,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +46: [2023-04-29 11:37:26,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +58: [2023-04-29 11:37:26,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +48: [2023-04-29 11:37:26,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +49: [2023-04-29 11:37:26,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +38: [2023-04-29 11:37:26,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +44: [2023-04-29 11:37:26,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +44: [2023-04-29 11:37:26,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +44: [2023-04-29 11:37:26,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +44: [2023-04-29 11:37:26,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +58: [2023-04-29 11:37:26,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +54: [2023-04-29 11:37:26,349] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +24: [2023-04-29 11:37:26,349] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +24: [2023-04-29 11:37:26,349] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +24: [2023-04-29 11:37:26,349] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +56: [2023-04-29 11:37:26,349] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +24: [2023-04-29 11:37:26,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. + 8: [2023-04-29 11:37:26,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 8: [2023-04-29 11:37:26,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +38: [2023-04-29 11:37:26,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +54: [2023-04-29 11:37:26,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. + 3: [2023-04-29 11:37:26,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. + 3: [2023-04-29 11:37:26,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. + 3: [2023-04-29 11:37:26,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. + 3: [2023-04-29 11:37:26,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +56: [2023-04-29 11:37:26,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +56: [2023-04-29 11:37:26,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 8: [2023-04-29 11:37:26,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +48: [2023-04-29 11:37:26,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +48: [2023-04-29 11:37:26,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +49: [2023-04-29 11:37:26,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +36: [2023-04-29 11:37:26,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +36: [2023-04-29 11:37:26,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +56: [2023-04-29 11:37:26,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +53: [2023-04-29 11:37:26,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +30: [2023-04-29 11:37:26,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +30: [2023-04-29 11:37:26,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +30: [2023-04-29 11:37:26,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +54: [2023-04-29 11:37:26,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +30: [2023-04-29 11:37:26,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +34: [2023-04-29 11:37:26,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. + 8: [2023-04-29 11:37:26,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +41: [2023-04-29 11:37:26,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. + 4: [2023-04-29 11:37:26,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 4: [2023-04-29 11:37:26,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +49: [2023-04-29 11:37:26,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +54: [2023-04-29 11:37:26,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +54: [2023-04-29 11:37:26,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +53: [2023-04-29 11:37:26,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +54: [2023-04-29 11:37:26,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. + 4: [2023-04-29 11:37:26,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 4: [2023-04-29 11:37:26,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +54: [2023-04-29 11:37:26,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +38: [2023-04-29 11:37:26,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +59: [2023-04-29 11:37:26,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +59: [2023-04-29 11:37:26,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +49: [2023-04-29 11:37:26,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +49: [2023-04-29 11:37:26,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +55: [2023-04-29 11:37:26,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +58: [2023-04-29 11:37:26,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +58: [2023-04-29 11:37:26,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +54: [2023-04-29 11:37:26,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +49: [2023-04-29 11:37:26,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +33: [2023-04-29 11:37:26,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +33: [2023-04-29 11:37:26,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +48: [2023-04-29 11:37:26,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +48: [2023-04-29 11:37:26,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +54: [2023-04-29 11:37:26,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +11: [2023-04-29 11:37:26,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +11: [2023-04-29 11:37:26,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +41: [2023-04-29 11:37:26,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +11: [2023-04-29 11:37:26,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +38: [2023-04-29 11:37:26,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +11: [2023-04-29 11:37:26,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +36: [2023-04-29 11:37:26,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +37: [2023-04-29 11:37:26,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +37: [2023-04-29 11:37:26,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +37: [2023-04-29 11:37:26,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +37: [2023-04-29 11:37:26,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +58: [2023-04-29 11:37:26,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +58: [2023-04-29 11:37:26,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +36: [2023-04-29 11:37:26,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +55: [2023-04-29 11:37:26,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +33: [2023-04-29 11:37:26,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +33: [2023-04-29 11:37:26,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +33: [2023-04-29 11:37:26,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +38: [2023-04-29 11:37:26,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +54: [2023-04-29 11:37:26,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +55: [2023-04-29 11:37:26,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +49: [2023-04-29 11:37:26,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +54: [2023-04-29 11:37:26,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +61: [2023-04-29 11:37:26,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +24: [2023-04-29 11:37:26,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +24: [2023-04-29 11:37:26,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +33: [2023-04-29 11:37:26,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +33: [2023-04-29 11:37:26,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +24: [2023-04-29 11:37:26,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +24: [2023-04-29 11:37:26,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +33: [2023-04-29 11:37:26,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +44: [2023-04-29 11:37:26,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +44: [2023-04-29 11:37:26,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +56: [2023-04-29 11:37:26,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +44: [2023-04-29 11:37:26,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +44: [2023-04-29 11:37:26,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +49: [2023-04-29 11:37:26,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +43: [2023-04-29 11:37:26,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +33: [2023-04-29 11:37:26,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +33: [2023-04-29 11:37:26,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +59: [2023-04-29 11:37:26,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +59: [2023-04-29 11:37:26,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +33: [2023-04-29 11:37:26,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +49: [2023-04-29 11:37:26,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. + 3: [2023-04-29 11:37:26,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +33: [2023-04-29 11:37:26,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +33: [2023-04-29 11:37:26,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +34: [2023-04-29 11:37:26,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +53: [2023-04-29 11:37:26,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +61: [2023-04-29 11:37:26,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. + 3: [2023-04-29 11:37:26,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +53: [2023-04-29 11:37:26,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. + 3: [2023-04-29 11:37:26,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 3: [2023-04-29 11:37:26,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +61: [2023-04-29 11:37:26,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +44: [2023-04-29 11:37:26,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +44: [2023-04-29 11:37:26,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +44: [2023-04-29 11:37:26,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +54: [2023-04-29 11:37:26,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +44: [2023-04-29 11:37:26,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +43: [2023-04-29 11:37:26,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +34: [2023-04-29 11:37:26,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +54: [2023-04-29 11:37:26,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +60: [2023-04-29 11:37:26,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +60: [2023-04-29 11:37:26,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +34: [2023-04-29 11:37:26,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +34: [2023-04-29 11:37:26,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +43: [2023-04-29 11:37:26,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +33: [2023-04-29 11:37:26,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +48: [2023-04-29 11:37:26,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +33: [2023-04-29 11:37:26,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +43: [2023-04-29 11:37:26,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +48: [2023-04-29 11:37:26,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +33: [2023-04-29 11:37:26,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +41: [2023-04-29 11:37:26,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +49: [2023-04-29 11:37:26,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +53: [2023-04-29 11:37:26,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +53: [2023-04-29 11:37:26,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +48: [2023-04-29 11:37:26,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +61: [2023-04-29 11:37:26,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +57: [2023-04-29 11:37:26,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +57: [2023-04-29 11:37:26,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +41: [2023-04-29 11:37:26,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +41: [2023-04-29 11:37:26,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +60: [2023-04-29 11:37:26,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +60: [2023-04-29 11:37:26,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +46: [2023-04-29 11:37:26,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +48: [2023-04-29 11:37:26,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +57: [2023-04-29 11:37:26,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +55: [2023-04-29 11:37:26,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +57: [2023-04-29 11:37:26,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +30: [2023-04-29 11:37:26,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +48: [2023-04-29 11:37:26,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +30: [2023-04-29 11:37:26,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +30: [2023-04-29 11:37:26,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +54: [2023-04-29 11:37:26,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +54: [2023-04-29 11:37:26,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +46: [2023-04-29 11:37:26,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +59: [2023-04-29 11:37:26,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +59: [2023-04-29 11:37:26,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +54: [2023-04-29 11:37:26,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +55: [2023-04-29 11:37:26,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +30: [2023-04-29 11:37:26,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +17: [2023-04-29 11:37:26,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +17: [2023-04-29 11:37:26,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +17: [2023-04-29 11:37:26,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +11: [2023-04-29 11:37:26,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +17: [2023-04-29 11:37:26,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +11: [2023-04-29 11:37:26,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +41: [2023-04-29 11:37:26,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +11: [2023-04-29 11:37:26,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +11: [2023-04-29 11:37:26,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +58: [2023-04-29 11:37:26,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +58: [2023-04-29 11:37:26,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +46: [2023-04-29 11:37:26,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +37: [2023-04-29 11:37:26,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +55: [2023-04-29 11:37:26,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +61: [2023-04-29 11:37:26,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +48: [2023-04-29 11:37:26,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +49: [2023-04-29 11:37:26,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +48: [2023-04-29 11:37:26,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +55: [2023-04-29 11:37:26,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +46: [2023-04-29 11:37:26,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +14: [2023-04-29 11:37:26,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +14: [2023-04-29 11:37:26,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +14: [2023-04-29 11:37:26,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +49: [2023-04-29 11:37:26,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +43: [2023-04-29 11:37:26,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +14: [2023-04-29 11:37:26,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +37: [2023-04-29 11:37:26,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +37: [2023-04-29 11:37:26,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +37: [2023-04-29 11:37:26,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +46: [2023-04-29 11:37:26,405] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +58: [2023-04-29 11:37:26,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +34: [2023-04-29 11:37:26,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +61: [2023-04-29 11:37:26,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +58: [2023-04-29 11:37:26,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +19: [2023-04-29 11:37:26,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +19: [2023-04-29 11:37:26,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +19: [2023-04-29 11:37:26,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +19: [2023-04-29 11:37:26,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +46: [2023-04-29 11:37:26,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +49: [2023-04-29 11:37:26,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +48: [2023-04-29 11:37:26,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +48: [2023-04-29 11:37:26,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +53: [2023-04-29 11:37:26,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +59: [2023-04-29 11:37:26,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +59: [2023-04-29 11:37:26,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +46: [2023-04-29 11:37:26,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +61: [2023-04-29 11:37:26,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +49: [2023-04-29 11:37:26,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +49: [2023-04-29 11:37:26,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +46: [2023-04-29 11:37:26,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +28: [2023-04-29 11:37:26,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +28: [2023-04-29 11:37:26,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +28: [2023-04-29 11:37:26,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +43: [2023-04-29 11:37:26,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 6: [2023-04-29 11:37:26,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. + 6: [2023-04-29 11:37:26,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +28: [2023-04-29 11:37:26,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. + 7: [2023-04-29 11:37:26,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. + 7: [2023-04-29 11:37:26,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +60: [2023-04-29 11:37:26,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +49: [2023-04-29 11:37:26,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... + 7: [2023-04-29 11:37:26,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. + 7: [2023-04-29 11:37:26,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +53: [2023-04-29 11:37:26,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +43: [2023-04-29 11:37:26,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +43: [2023-04-29 11:37:26,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +34: [2023-04-29 11:37:26,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +60: [2023-04-29 11:37:26,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 6: [2023-04-29 11:37:26,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +48: [2023-04-29 11:37:26,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +48: [2023-04-29 11:37:26,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +34: [2023-04-29 11:37:26,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +44: [2023-04-29 11:37:26,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +55: [2023-04-29 11:37:26,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +57: [2023-04-29 11:37:26,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +44: [2023-04-29 11:37:26,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +61: [2023-04-29 11:37:26,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +57: [2023-04-29 11:37:26,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +44: [2023-04-29 11:37:26,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. + 6: [2023-04-29 11:37:26,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +60: [2023-04-29 11:37:26,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +60: [2023-04-29 11:37:26,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +57: [2023-04-29 11:37:26,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +17: [2023-04-29 11:37:26,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +57: [2023-04-29 11:37:26,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +41: [2023-04-29 11:37:26,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +46: [2023-04-29 11:37:26,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +41: [2023-04-29 11:37:26,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +44: [2023-04-29 11:37:26,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +46: [2023-04-29 11:37:26,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +46: [2023-04-29 11:37:26,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +17: [2023-04-29 11:37:26,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +17: [2023-04-29 11:37:26,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +44: [2023-04-29 11:37:26,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +44: [2023-04-29 11:37:26,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +44: [2023-04-29 11:37:26,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +17: [2023-04-29 11:37:26,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +14: [2023-04-29 11:37:26,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +37: [2023-04-29 11:37:26,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +39: [2023-04-29 11:37:26,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +46: [2023-04-29 11:37:26,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +39: [2023-04-29 11:37:26,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +33: [2023-04-29 11:37:26,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +37: [2023-04-29 11:37:26,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +37: [2023-04-29 11:37:26,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +37: [2023-04-29 11:37:26,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +14: [2023-04-29 11:37:26,432] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +19: [2023-04-29 11:37:26,432] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +44: [2023-04-29 11:37:26,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +39: [2023-04-29 11:37:26,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +39: [2023-04-29 11:37:26,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +39: [2023-04-29 11:37:26,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +39: [2023-04-29 11:37:26,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +39: [2023-04-29 11:37:26,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +14: [2023-04-29 11:37:26,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +14: [2023-04-29 11:37:26,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +39: [2023-04-29 11:37:26,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +37: [2023-04-29 11:37:26,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +40: [2023-04-29 11:37:26,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +40: [2023-04-29 11:37:26,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +40: [2023-04-29 11:37:26,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +40: [2023-04-29 11:37:26,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +19: [2023-04-29 11:37:26,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +39: [2023-04-29 11:37:26,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +21: [2023-04-29 11:37:26,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +21: [2023-04-29 11:37:26,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +21: [2023-04-29 11:37:26,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +39: [2023-04-29 11:37:26,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +21: [2023-04-29 11:37:26,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +19: [2023-04-29 11:37:26,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +39: [2023-04-29 11:37:26,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +19: [2023-04-29 11:37:26,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 7: [2023-04-29 11:37:26,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +23: [2023-04-29 11:37:26,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +23: [2023-04-29 11:37:26,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +29: [2023-04-29 11:37:26,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +23: [2023-04-29 11:37:26,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +29: [2023-04-29 11:37:26,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +30: [2023-04-29 11:37:26,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +30: [2023-04-29 11:37:26,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +30: [2023-04-29 11:37:26,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +29: [2023-04-29 11:37:26,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +30: [2023-04-29 11:37:26,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +23: [2023-04-29 11:37:26,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +37: [2023-04-29 11:37:26,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +37: [2023-04-29 11:37:26,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +39: [2023-04-29 11:37:26,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +46: [2023-04-29 11:37:26,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +29: [2023-04-29 11:37:26,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +37: [2023-04-29 11:37:26,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 6: [2023-04-29 11:37:26,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +39: [2023-04-29 11:37:26,442] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... +39: [2023-04-29 11:37:26,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... + 6: [2023-04-29 11:37:26,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +28: [2023-04-29 11:37:26,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +28: [2023-04-29 11:37:26,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +28: [2023-04-29 11:37:26,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +39: [2023-04-29 11:37:26,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt... +21: [2023-04-29 11:37:26,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +39: [2023-04-29 11:37:26,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt... + 7: [2023-04-29 11:37:26,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 6: [2023-04-29 11:37:26,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 7: [2023-04-29 11:37:26,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +46: [2023-04-29 11:37:26,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 7: [2023-04-29 11:37:26,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +21: [2023-04-29 11:37:26,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +21: [2023-04-29 11:37:26,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +21: [2023-04-29 11:37:26,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +33: [2023-04-29 11:37:26,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +33: [2023-04-29 11:37:26,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +28: [2023-04-29 11:37:26,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +33: [2023-04-29 11:37:26,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +30: [2023-04-29 11:37:26,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +30: [2023-04-29 11:37:26,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +30: [2023-04-29 11:37:26,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +30: [2023-04-29 11:37:26,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +10: [2023-04-29 11:37:26,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +10: [2023-04-29 11:37:26,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +10: [2023-04-29 11:37:26,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +10: [2023-04-29 11:37:26,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +46: [2023-04-29 11:37:26,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 6: [2023-04-29 11:37:26,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 8: [2023-04-29 11:37:26,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +10: [2023-04-29 11:37:26,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 8: [2023-04-29 11:37:26,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 8: [2023-04-29 11:37:26,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 8: [2023-04-29 11:37:26,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 8: [2023-04-29 11:37:26,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 8: [2023-04-29 11:37:26,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 8: [2023-04-29 11:37:26,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +46: [2023-04-29 11:37:26,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 8: [2023-04-29 11:37:26,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +10: [2023-04-29 11:37:26,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +44: [2023-04-29 11:37:26,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +44: [2023-04-29 11:37:26,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +10: [2023-04-29 11:37:26,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +10: [2023-04-29 11:37:26,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +44: [2023-04-29 11:37:26,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +30: [2023-04-29 11:37:26,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 8: [2023-04-29 11:37:26,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 8: [2023-04-29 11:37:26,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +33: [2023-04-29 11:37:26,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 8: [2023-04-29 11:37:26,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +40: [2023-04-29 11:37:26,463] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +40: [2023-04-29 11:37:26,463] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +30: [2023-04-29 11:37:26,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 8: [2023-04-29 11:37:26,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 8: [2023-04-29 11:37:26,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 8: [2023-04-29 11:37:26,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +40: [2023-04-29 11:37:26,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +40: [2023-04-29 11:37:26,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 8: [2023-04-29 11:37:26,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +44: [2023-04-29 11:37:26,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +23: [2023-04-29 11:37:26,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +37: [2023-04-29 11:37:26,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +30: [2023-04-29 11:37:26,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +30: [2023-04-29 11:37:26,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 8: [2023-04-29 11:37:26,466] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +23: [2023-04-29 11:37:26,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +29: [2023-04-29 11:37:26,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +29: [2023-04-29 11:37:26,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +23: [2023-04-29 11:37:26,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +30: [2023-04-29 11:37:26,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +27: [2023-04-29 11:37:26,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +27: [2023-04-29 11:37:26,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +27: [2023-04-29 11:37:26,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +27: [2023-04-29 11:37:26,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +27: [2023-04-29 11:37:26,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +27: [2023-04-29 11:37:26,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +27: [2023-04-29 11:37:26,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +27: [2023-04-29 11:37:26,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +23: [2023-04-29 11:37:26,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +29: [2023-04-29 11:37:26,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +37: [2023-04-29 11:37:26,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... + 5: [2023-04-29 11:37:26,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. + 5: [2023-04-29 11:37:26,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. + 5: [2023-04-29 11:37:26,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. + 5: [2023-04-29 11:37:26,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +29: [2023-04-29 11:37:26,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +27: [2023-04-29 11:37:26,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +27: [2023-04-29 11:37:26,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +27: [2023-04-29 11:37:26,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +33: [2023-04-29 11:37:26,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +30: [2023-04-29 11:37:26,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +30: [2023-04-29 11:37:26,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +30: [2023-04-29 11:37:26,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +27: [2023-04-29 11:37:26,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +27: [2023-04-29 11:37:26,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +27: [2023-04-29 11:37:26,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +27: [2023-04-29 11:37:26,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +27: [2023-04-29 11:37:26,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +33: [2023-04-29 11:37:26,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +33: [2023-04-29 11:37:26,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +62: [2023-04-29 11:37:26,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +62: [2023-04-29 11:37:26,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +62: [2023-04-29 11:37:26,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +62: [2023-04-29 11:37:26,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +35: [2023-04-29 11:37:26,479] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +35: [2023-04-29 11:37:26,479] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +44: [2023-04-29 11:37:26,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +35: [2023-04-29 11:37:26,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +35: [2023-04-29 11:37:26,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +44: [2023-04-29 11:37:26,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +44: [2023-04-29 11:37:26,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +39: [2023-04-29 11:37:26,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +44: [2023-04-29 11:37:26,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +47: [2023-04-29 11:37:26,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +47: [2023-04-29 11:37:26,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +10: [2023-04-29 11:37:26,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +10: [2023-04-29 11:37:26,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +10: [2023-04-29 11:37:26,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +10: [2023-04-29 11:37:26,497] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +37: [2023-04-29 11:37:26,497] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +47: [2023-04-29 11:37:26,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +47: [2023-04-29 11:37:26,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +39: [2023-04-29 11:37:26,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +37: [2023-04-29 11:37:26,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +37: [2023-04-29 11:37:26,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +24: [2023-04-29 11:37:26,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +24: [2023-04-29 11:37:26,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +24: [2023-04-29 11:37:26,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +24: [2023-04-29 11:37:26,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +24: [2023-04-29 11:37:26,499] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +24: [2023-04-29 11:37:26,499] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +24: [2023-04-29 11:37:26,499] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +24: [2023-04-29 11:37:26,499] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +37: [2023-04-29 11:37:26,502] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. + 5: [2023-04-29 11:37:26,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 5: [2023-04-29 11:37:26,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 5: [2023-04-29 11:37:26,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 5: [2023-04-29 11:37:26,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +24: [2023-04-29 11:37:26,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +24: [2023-04-29 11:37:26,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +24: [2023-04-29 11:37:26,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +24: [2023-04-29 11:37:26,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +37: [2023-04-29 11:37:26,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +24: [2023-04-29 11:37:26,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +24: [2023-04-29 11:37:26,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +24: [2023-04-29 11:37:26,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +39: [2023-04-29 11:37:26,505] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. +24: [2023-04-29 11:37:26,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +37: [2023-04-29 11:37:26,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... + 0: [2023-04-29 11:37:26,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 0: [2023-04-29 11:37:26,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 0: [2023-04-29 11:37:26,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +20: [2023-04-29 11:37:26,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +20: [2023-04-29 11:37:26,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +20: [2023-04-29 11:37:26,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +20: [2023-04-29 11:37:26,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +20: [2023-04-29 11:37:26,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +20: [2023-04-29 11:37:26,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +20: [2023-04-29 11:37:26,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 0: [2023-04-29 11:37:26,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +20: [2023-04-29 11:37:26,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +35: [2023-04-29 11:37:26,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +35: [2023-04-29 11:37:26,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +21: [2023-04-29 11:37:26,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +21: [2023-04-29 11:37:26,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +37: [2023-04-29 11:37:26,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +30: [2023-04-29 11:37:26,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +35: [2023-04-29 11:37:26,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +62: [2023-04-29 11:37:26,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +45: [2023-04-29 11:37:26,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +45: [2023-04-29 11:37:26,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +63: [2023-04-29 11:37:26,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +63: [2023-04-29 11:37:26,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +20: [2023-04-29 11:37:26,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +63: [2023-04-29 11:37:26,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. + 4: [2023-04-29 11:37:26,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 0: [2023-04-29 11:37:26,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +63: [2023-04-29 11:37:26,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +62: [2023-04-29 11:37:26,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 4: [2023-04-29 11:37:26,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 4: [2023-04-29 11:37:26,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 4: [2023-04-29 11:37:26,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 4: [2023-04-29 11:37:26,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 4: [2023-04-29 11:37:26,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 4: [2023-04-29 11:37:26,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 4: [2023-04-29 11:37:26,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 0: [2023-04-29 11:37:26,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +35: [2023-04-29 11:37:26,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 0: [2023-04-29 11:37:26,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 0: [2023-04-29 11:37:26,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +62: [2023-04-29 11:37:26,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +20: [2023-04-29 11:37:26,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +20: [2023-04-29 11:37:26,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +62: [2023-04-29 11:37:26,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 7: [2023-04-29 11:37:26,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 7: [2023-04-29 11:37:26,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +20: [2023-04-29 11:37:26,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +45: [2023-04-29 11:37:26,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +20: [2023-04-29 11:37:26,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +20: [2023-04-29 11:37:26,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +45: [2023-04-29 11:37:26,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +20: [2023-04-29 11:37:26,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +30: [2023-04-29 11:37:26,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +39: [2023-04-29 11:37:26,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 7: [2023-04-29 11:37:26,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 7: [2023-04-29 11:37:26,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 7: [2023-04-29 11:37:26,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 7: [2023-04-29 11:37:26,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 7: [2023-04-29 11:37:26,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 7: [2023-04-29 11:37:26,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +20: [2023-04-29 11:37:26,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +39: [2023-04-29 11:37:26,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_00-model_states.pt. + 4: [2023-04-29 11:37:26,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 4: [2023-04-29 11:37:26,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 4: [2023-04-29 11:37:26,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +30: [2023-04-29 11:37:26,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +21: [2023-04-29 11:37:26,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +56: [2023-04-29 11:37:26,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +56: [2023-04-29 11:37:26,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +56: [2023-04-29 11:37:26,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +56: [2023-04-29 11:37:26,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. + 8: [2023-04-29 11:37:26,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 4: [2023-04-29 11:37:26,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 4: [2023-04-29 11:37:26,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 7: [2023-04-29 11:37:26,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 4: [2023-04-29 11:37:26,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 4: [2023-04-29 11:37:26,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 4: [2023-04-29 11:37:26,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 7: [2023-04-29 11:37:26,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 8: [2023-04-29 11:37:26,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 7: [2023-04-29 11:37:26,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 7: [2023-04-29 11:37:26,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +21: [2023-04-29 11:37:26,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 7: [2023-04-29 11:37:26,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 7: [2023-04-29 11:37:26,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +18: [2023-04-29 11:37:26,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +18: [2023-04-29 11:37:26,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +39: [2023-04-29 11:37:26,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +30: [2023-04-29 11:37:26,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +18: [2023-04-29 11:37:26,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. + 7: [2023-04-29 11:37:26,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +18: [2023-04-29 11:37:26,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. + 7: [2023-04-29 11:37:26,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +47: [2023-04-29 11:37:26,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +47: [2023-04-29 11:37:26,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +37: [2023-04-29 11:37:26,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +47: [2023-04-29 11:37:26,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +47: [2023-04-29 11:37:26,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +10: [2023-04-29 11:37:26,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +10: [2023-04-29 11:37:26,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +37: [2023-04-29 11:37:26,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +37: [2023-04-29 11:37:26,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +10: [2023-04-29 11:37:26,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +37: [2023-04-29 11:37:26,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +27: [2023-04-29 11:37:26,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +10: [2023-04-29 11:37:26,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +21: [2023-04-29 11:37:26,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +10: [2023-04-29 11:37:26,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 8: [2023-04-29 11:37:26,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 8: [2023-04-29 11:37:26,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +39: [2023-04-29 11:37:26,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +21: [2023-04-29 11:37:26,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +30: [2023-04-29 11:37:26,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +63: [2023-04-29 11:37:26,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +63: [2023-04-29 11:37:26,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +63: [2023-04-29 11:37:26,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +51: [2023-04-29 11:37:26,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +51: [2023-04-29 11:37:26,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +51: [2023-04-29 11:37:26,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +45: [2023-04-29 11:37:26,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +51: [2023-04-29 11:37:26,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +27: [2023-04-29 11:37:26,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +10: [2023-04-29 11:37:26,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +10: [2023-04-29 11:37:26,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +10: [2023-04-29 11:37:26,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +45: [2023-04-29 11:37:26,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +45: [2023-04-29 11:37:26,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +63: [2023-04-29 11:37:26,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +15: [2023-04-29 11:37:26,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +15: [2023-04-29 11:37:26,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +45: [2023-04-29 11:37:26,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +27: [2023-04-29 11:37:26,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +13: [2023-04-29 11:37:26,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +13: [2023-04-29 11:37:26,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +13: [2023-04-29 11:37:26,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +15: [2023-04-29 11:37:26,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +15: [2023-04-29 11:37:26,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +13: [2023-04-29 11:37:26,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +39: [2023-04-29 11:37:26,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +15: [2023-04-29 11:37:26,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +15: [2023-04-29 11:37:26,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +15: [2023-04-29 11:37:26,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +15: [2023-04-29 11:37:26,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 8: [2023-04-29 11:37:26,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 8: [2023-04-29 11:37:26,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +27: [2023-04-29 11:37:26,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +56: [2023-04-29 11:37:26,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +26: [2023-04-29 11:37:26,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +26: [2023-04-29 11:37:26,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +26: [2023-04-29 11:37:26,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +15: [2023-04-29 11:37:26,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +25: [2023-04-29 11:37:26,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +25: [2023-04-29 11:37:26,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +26: [2023-04-29 11:37:26,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +25: [2023-04-29 11:37:26,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +15: [2023-04-29 11:37:26,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +56: [2023-04-29 11:37:26,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +56: [2023-04-29 11:37:26,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +25: [2023-04-29 11:37:26,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +56: [2023-04-29 11:37:26,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +21: [2023-04-29 11:37:26,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +30: [2023-04-29 11:37:26,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +30: [2023-04-29 11:37:26,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +15: [2023-04-29 11:37:26,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +15: [2023-04-29 11:37:26,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +18: [2023-04-29 11:37:26,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 6: [2023-04-29 11:37:26,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 6: [2023-04-29 11:37:26,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 6: [2023-04-29 11:37:26,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 6: [2023-04-29 11:37:26,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 6: [2023-04-29 11:37:26,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 6: [2023-04-29 11:37:26,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 6: [2023-04-29 11:37:26,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +18: [2023-04-29 11:37:26,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +21: [2023-04-29 11:37:26,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 6: [2023-04-29 11:37:26,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +18: [2023-04-29 11:37:26,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +18: [2023-04-29 11:37:26,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +21: [2023-04-29 11:37:26,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +21: [2023-04-29 11:37:26,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +21: [2023-04-29 11:37:26,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +21: [2023-04-29 11:37:26,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +30: [2023-04-29 11:37:26,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +52: [2023-04-29 11:37:26,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +52: [2023-04-29 11:37:26,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +52: [2023-04-29 11:37:26,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +52: [2023-04-29 11:37:26,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +27: [2023-04-29 11:37:26,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 6: [2023-04-29 11:37:26,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 6: [2023-04-29 11:37:26,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +37: [2023-04-29 11:37:26,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 6: [2023-04-29 11:37:26,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 6: [2023-04-29 11:37:26,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 6: [2023-04-29 11:37:26,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 6: [2023-04-29 11:37:26,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +37: [2023-04-29 11:37:26,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 6: [2023-04-29 11:37:26,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 6: [2023-04-29 11:37:26,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +10: [2023-04-29 11:37:26,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 8: [2023-04-29 11:37:26,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 8: [2023-04-29 11:37:26,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +37: [2023-04-29 11:37:26,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +24: [2023-04-29 11:37:26,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +24: [2023-04-29 11:37:26,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +51: [2023-04-29 11:37:26,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +51: [2023-04-29 11:37:26,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +24: [2023-04-29 11:37:26,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +27: [2023-04-29 11:37:26,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +10: [2023-04-29 11:37:26,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +51: [2023-04-29 11:37:26,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +51: [2023-04-29 11:37:26,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +24: [2023-04-29 11:37:26,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +27: [2023-04-29 11:37:26,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +27: [2023-04-29 11:37:26,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +10: [2023-04-29 11:37:26,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +10: [2023-04-29 11:37:26,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +20: [2023-04-29 11:37:26,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +15: [2023-04-29 11:37:26,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +15: [2023-04-29 11:37:26,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +13: [2023-04-29 11:37:26,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +26: [2023-04-29 11:37:26,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 4: [2023-04-29 11:37:26,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +20: [2023-04-29 11:37:26,577] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +13: [2023-04-29 11:37:26,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +15: [2023-04-29 11:37:26,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +15: [2023-04-29 11:37:26,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 0: [2023-04-29 11:37:26,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +26: [2023-04-29 11:37:26,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +13: [2023-04-29 11:37:26,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +13: [2023-04-29 11:37:26,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +26: [2023-04-29 11:37:26,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +26: [2023-04-29 11:37:26,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +20: [2023-04-29 11:37:26,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +20: [2023-04-29 11:37:26,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +25: [2023-04-29 11:37:26,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +35: [2023-04-29 11:37:26,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +35: [2023-04-29 11:37:26,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +35: [2023-04-29 11:37:26,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +35: [2023-04-29 11:37:26,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +35: [2023-04-29 11:37:26,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +35: [2023-04-29 11:37:26,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +25: [2023-04-29 11:37:26,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +52: [2023-04-29 11:37:26,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +21: [2023-04-29 11:37:26,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +21: [2023-04-29 11:37:26,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 0: [2023-04-29 11:37:26,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 0: [2023-04-29 11:37:26,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 0: [2023-04-29 11:37:26,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +35: [2023-04-29 11:37:26,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +25: [2023-04-29 11:37:26,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +25: [2023-04-29 11:37:26,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 7: [2023-04-29 11:37:26,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +21: [2023-04-29 11:37:26,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +21: [2023-04-29 11:37:26,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +35: [2023-04-29 11:37:26,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +35: [2023-04-29 11:37:26,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +52: [2023-04-29 11:37:26,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 4: [2023-04-29 11:37:26,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +50: [2023-04-29 11:37:26,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +50: [2023-04-29 11:37:26,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +24: [2023-04-29 11:37:26,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +52: [2023-04-29 11:37:26,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +52: [2023-04-29 11:37:26,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +35: [2023-04-29 11:37:26,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 7: [2023-04-29 11:37:26,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 7: [2023-04-29 11:37:26,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +35: [2023-04-29 11:37:26,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 4: [2023-04-29 11:37:26,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 4: [2023-04-29 11:37:26,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 7: [2023-04-29 11:37:26,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +35: [2023-04-29 11:37:26,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +35: [2023-04-29 11:37:26,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +50: [2023-04-29 11:37:26,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +35: [2023-04-29 11:37:26,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +50: [2023-04-29 11:37:26,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +24: [2023-04-29 11:37:26,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +24: [2023-04-29 11:37:26,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +35: [2023-04-29 11:37:26,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +20: [2023-04-29 11:37:26,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +42: [2023-04-29 11:37:26,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +42: [2023-04-29 11:37:26,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +35: [2023-04-29 11:37:26,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +10: [2023-04-29 11:37:26,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +24: [2023-04-29 11:37:26,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 2: [2023-04-29 11:37:26,597] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. + 2: [2023-04-29 11:37:26,597] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +42: [2023-04-29 11:37:26,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. + 2: [2023-04-29 11:37:26,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +42: [2023-04-29 11:37:26,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. + 2: [2023-04-29 11:37:26,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +10: [2023-04-29 11:37:26,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 4: [2023-04-29 11:37:26,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 1: [2023-04-29 11:37:26,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. + 1: [2023-04-29 11:37:26,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. + 0: [2023-04-29 11:37:26,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +57: [2023-04-29 11:37:26,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +57: [2023-04-29 11:37:26,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +57: [2023-04-29 11:37:26,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +57: [2023-04-29 11:37:26,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. + 1: [2023-04-29 11:37:26,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +57: [2023-04-29 11:37:26,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +57: [2023-04-29 11:37:26,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +57: [2023-04-29 11:37:26,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. + 1: [2023-04-29 11:37:26,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +57: [2023-04-29 11:37:26,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +20: [2023-04-29 11:37:26,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +10: [2023-04-29 11:37:26,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +58: [2023-04-29 11:37:26,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +58: [2023-04-29 11:37:26,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +58: [2023-04-29 11:37:26,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +58: [2023-04-29 11:37:26,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +31: [2023-04-29 11:37:26,606] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +31: [2023-04-29 11:37:26,606] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +20: [2023-04-29 11:37:26,607] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +20: [2023-04-29 11:37:26,607] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +31: [2023-04-29 11:37:26,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +31: [2023-04-29 11:37:26,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +36: [2023-04-29 11:37:26,608] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +36: [2023-04-29 11:37:26,608] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +36: [2023-04-29 11:37:26,608] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +36: [2023-04-29 11:37:26,608] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +57: [2023-04-29 11:37:26,609] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +57: [2023-04-29 11:37:26,609] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +57: [2023-04-29 11:37:26,609] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +57: [2023-04-29 11:37:26,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +57: [2023-04-29 11:37:26,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +57: [2023-04-29 11:37:26,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +22: [2023-04-29 11:37:26,610] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +22: [2023-04-29 11:37:26,610] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +57: [2023-04-29 11:37:26,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +57: [2023-04-29 11:37:26,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... + 0: [2023-04-29 11:37:26,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +10: [2023-04-29 11:37:26,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +22: [2023-04-29 11:37:26,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +38: [2023-04-29 11:37:26,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +38: [2023-04-29 11:37:26,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +22: [2023-04-29 11:37:26,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. + 7: [2023-04-29 11:37:26,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 0: [2023-04-29 11:37:26,614] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 0: [2023-04-29 11:37:26,614] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +38: [2023-04-29 11:37:26,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +38: [2023-04-29 11:37:26,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +10: [2023-04-29 11:37:26,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +41: [2023-04-29 11:37:26,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +41: [2023-04-29 11:37:26,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +10: [2023-04-29 11:37:26,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 4: [2023-04-29 11:37:26,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +50: [2023-04-29 11:37:26,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +50: [2023-04-29 11:37:26,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 4: [2023-04-29 11:37:26,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 4: [2023-04-29 11:37:26,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +41: [2023-04-29 11:37:26,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +41: [2023-04-29 11:37:26,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +10: [2023-04-29 11:37:26,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +49: [2023-04-29 11:37:26,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +49: [2023-04-29 11:37:26,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. + 7: [2023-04-29 11:37:26,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +10: [2023-04-29 11:37:26,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 7: [2023-04-29 11:37:26,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 6: [2023-04-29 11:37:26,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 6: [2023-04-29 11:37:26,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +49: [2023-04-29 11:37:26,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +49: [2023-04-29 11:37:26,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +50: [2023-04-29 11:37:26,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +42: [2023-04-29 11:37:26,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +50: [2023-04-29 11:37:26,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 6: [2023-04-29 11:37:26,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 7: [2023-04-29 11:37:26,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 2: [2023-04-29 11:37:26,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 2: [2023-04-29 11:37:26,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +42: [2023-04-29 11:37:26,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +18: [2023-04-29 11:37:26,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +18: [2023-04-29 11:37:26,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 2: [2023-04-29 11:37:26,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 2: [2023-04-29 11:37:26,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +18: [2023-04-29 11:37:26,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +18: [2023-04-29 11:37:26,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +18: [2023-04-29 11:37:26,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +18: [2023-04-29 11:37:26,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +18: [2023-04-29 11:37:26,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +18: [2023-04-29 11:37:26,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 6: [2023-04-29 11:37:26,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +49: [2023-04-29 11:37:26,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +49: [2023-04-29 11:37:26,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +42: [2023-04-29 11:37:26,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 1: [2023-04-29 11:37:26,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +15: [2023-04-29 11:37:26,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +15: [2023-04-29 11:37:26,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +15: [2023-04-29 11:37:26,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 1: [2023-04-29 11:37:26,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 1: [2023-04-29 11:37:26,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 1: [2023-04-29 11:37:26,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +31: [2023-04-29 11:37:26,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +18: [2023-04-29 11:37:26,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +58: [2023-04-29 11:37:26,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +49: [2023-04-29 11:37:26,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +18: [2023-04-29 11:37:26,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +18: [2023-04-29 11:37:26,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +42: [2023-04-29 11:37:26,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +49: [2023-04-29 11:37:26,634] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +18: [2023-04-29 11:37:26,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +18: [2023-04-29 11:37:26,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +22: [2023-04-29 11:37:26,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +49: [2023-04-29 11:37:26,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +22: [2023-04-29 11:37:26,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +49: [2023-04-29 11:37:26,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +18: [2023-04-29 11:37:26,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +18: [2023-04-29 11:37:26,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +58: [2023-04-29 11:37:26,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +31: [2023-04-29 11:37:26,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +58: [2023-04-29 11:37:26,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +22: [2023-04-29 11:37:26,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +22: [2023-04-29 11:37:26,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +36: [2023-04-29 11:37:26,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +36: [2023-04-29 11:37:26,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +49: [2023-04-29 11:37:26,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +18: [2023-04-29 11:37:26,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +16: [2023-04-29 11:37:26,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +16: [2023-04-29 11:37:26,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +31: [2023-04-29 11:37:26,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +31: [2023-04-29 11:37:26,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +36: [2023-04-29 11:37:26,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +36: [2023-04-29 11:37:26,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +15: [2023-04-29 11:37:26,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +21: [2023-04-29 11:37:26,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +12: [2023-04-29 11:37:26,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +12: [2023-04-29 11:37:26,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +58: [2023-04-29 11:37:26,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +16: [2023-04-29 11:37:26,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +12: [2023-04-29 11:37:26,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +38: [2023-04-29 11:37:26,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +16: [2023-04-29 11:37:26,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +12: [2023-04-29 11:37:26,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +49: [2023-04-29 11:37:26,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +41: [2023-04-29 11:37:26,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +38: [2023-04-29 11:37:26,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +38: [2023-04-29 11:37:26,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 9: [2023-04-29 11:37:26,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. + 9: [2023-04-29 11:37:26,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. + 9: [2023-04-29 11:37:26,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. + 9: [2023-04-29 11:37:26,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +41: [2023-04-29 11:37:26,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +21: [2023-04-29 11:37:26,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +38: [2023-04-29 11:37:26,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +21: [2023-04-29 11:37:26,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 6: [2023-04-29 11:37:26,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 6: [2023-04-29 11:37:26,650] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +50: [2023-04-29 11:37:26,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +50: [2023-04-29 11:37:26,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +50: [2023-04-29 11:37:26,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +50: [2023-04-29 11:37:26,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +25: [2023-04-29 11:37:26,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +25: [2023-04-29 11:37:26,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +25: [2023-04-29 11:37:26,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +25: [2023-04-29 11:37:26,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +25: [2023-04-29 11:37:26,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +25: [2023-04-29 11:37:26,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +25: [2023-04-29 11:37:26,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +49: [2023-04-29 11:37:26,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +49: [2023-04-29 11:37:26,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +25: [2023-04-29 11:37:26,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +21: [2023-04-29 11:37:26,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +35: [2023-04-29 11:37:26,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +41: [2023-04-29 11:37:26,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +41: [2023-04-29 11:37:26,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +14: [2023-04-29 11:37:26,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +14: [2023-04-29 11:37:26,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +32: [2023-04-29 11:37:26,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +32: [2023-04-29 11:37:26,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +32: [2023-04-29 11:37:26,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. + 6: [2023-04-29 11:37:26,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 6: [2023-04-29 11:37:26,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +32: [2023-04-29 11:37:26,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +49: [2023-04-29 11:37:26,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +49: [2023-04-29 11:37:26,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +14: [2023-04-29 11:37:26,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +50: [2023-04-29 11:37:26,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +14: [2023-04-29 11:37:26,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +14: [2023-04-29 11:37:26,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +14: [2023-04-29 11:37:26,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +14: [2023-04-29 11:37:26,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +14: [2023-04-29 11:37:26,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +15: [2023-04-29 11:37:26,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +15: [2023-04-29 11:37:26,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +15: [2023-04-29 11:37:26,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +32: [2023-04-29 11:37:26,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +32: [2023-04-29 11:37:26,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +21: [2023-04-29 11:37:26,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +25: [2023-04-29 11:37:26,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +21: [2023-04-29 11:37:26,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +15: [2023-04-29 11:37:26,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +51: [2023-04-29 11:37:26,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +63: [2023-04-29 11:37:26,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +63: [2023-04-29 11:37:26,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +63: [2023-04-29 11:37:26,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +51: [2023-04-29 11:37:26,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +51: [2023-04-29 11:37:26,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +63: [2023-04-29 11:37:26,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +63: [2023-04-29 11:37:26,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +63: [2023-04-29 11:37:26,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +63: [2023-04-29 11:37:26,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +51: [2023-04-29 11:37:26,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +51: [2023-04-29 11:37:26,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +51: [2023-04-29 11:37:26,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +51: [2023-04-29 11:37:26,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +25: [2023-04-29 11:37:26,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +63: [2023-04-29 11:37:26,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +51: [2023-04-29 11:37:26,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +25: [2023-04-29 11:37:26,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +32: [2023-04-29 11:37:26,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +25: [2023-04-29 11:37:26,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +25: [2023-04-29 11:37:26,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +25: [2023-04-29 11:37:26,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +50: [2023-04-29 11:37:26,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +14: [2023-04-29 11:37:26,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +50: [2023-04-29 11:37:26,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +15: [2023-04-29 11:37:26,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +32: [2023-04-29 11:37:26,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +15: [2023-04-29 11:37:26,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +14: [2023-04-29 11:37:26,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +14: [2023-04-29 11:37:26,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +15: [2023-04-29 11:37:26,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +14: [2023-04-29 11:37:26,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +58: [2023-04-29 11:37:26,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +58: [2023-04-29 11:37:26,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +14: [2023-04-29 11:37:26,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +25: [2023-04-29 11:37:26,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +50: [2023-04-29 11:37:26,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +58: [2023-04-29 11:37:26,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +58: [2023-04-29 11:37:26,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. + 3: [2023-04-29 11:37:26,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 3: [2023-04-29 11:37:26,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +32: [2023-04-29 11:37:26,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +63: [2023-04-29 11:37:26,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +25: [2023-04-29 11:37:26,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +32: [2023-04-29 11:37:26,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +14: [2023-04-29 11:37:26,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +51: [2023-04-29 11:37:26,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +51: [2023-04-29 11:37:26,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +63: [2023-04-29 11:37:26,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +14: [2023-04-29 11:37:26,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +15: [2023-04-29 11:37:26,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +32: [2023-04-29 11:37:26,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +14: [2023-04-29 11:37:26,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +15: [2023-04-29 11:37:26,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +63: [2023-04-29 11:37:26,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +63: [2023-04-29 11:37:26,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +15: [2023-04-29 11:37:26,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +35: [2023-04-29 11:37:26,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +21: [2023-04-29 11:37:26,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +32: [2023-04-29 11:37:26,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +35: [2023-04-29 11:37:26,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. + 9: [2023-04-29 11:37:26,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +16: [2023-04-29 11:37:26,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 9: [2023-04-29 11:37:26,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +15: [2023-04-29 11:37:26,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 9: [2023-04-29 11:37:26,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +63: [2023-04-29 11:37:26,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +12: [2023-04-29 11:37:26,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 3: [2023-04-29 11:37:26,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +63: [2023-04-29 11:37:26,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 3: [2023-04-29 11:37:26,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +16: [2023-04-29 11:37:26,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 3: [2023-04-29 11:37:26,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +63: [2023-04-29 11:37:26,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +12: [2023-04-29 11:37:26,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +12: [2023-04-29 11:37:26,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +63: [2023-04-29 11:37:26,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... + 3: [2023-04-29 11:37:26,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 3: [2023-04-29 11:37:26,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +12: [2023-04-29 11:37:26,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 3: [2023-04-29 11:37:26,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +21: [2023-04-29 11:37:26,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 9: [2023-04-29 11:37:26,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +15: [2023-04-29 11:37:26,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +60: [2023-04-29 11:37:26,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +60: [2023-04-29 11:37:26,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +16: [2023-04-29 11:37:26,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +60: [2023-04-29 11:37:26,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +58: [2023-04-29 11:37:26,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +58: [2023-04-29 11:37:26,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +60: [2023-04-29 11:37:26,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +51: [2023-04-29 11:37:26,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +57: [2023-04-29 11:37:26,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +58: [2023-04-29 11:37:26,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +51: [2023-04-29 11:37:26,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +58: [2023-04-29 11:37:26,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 3: [2023-04-29 11:37:26,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 3: [2023-04-29 11:37:26,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +51: [2023-04-29 11:37:26,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +51: [2023-04-29 11:37:26,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +51: [2023-04-29 11:37:26,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 9: [2023-04-29 11:37:26,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +16: [2023-04-29 11:37:26,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +51: [2023-04-29 11:37:26,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... + 3: [2023-04-29 11:37:26,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 3: [2023-04-29 11:37:26,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 3: [2023-04-29 11:37:26,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 3: [2023-04-29 11:37:26,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 3: [2023-04-29 11:37:26,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 9: [2023-04-29 11:37:26,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 3: [2023-04-29 11:37:26,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 9: [2023-04-29 11:37:26,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 9: [2023-04-29 11:37:26,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 9: [2023-04-29 11:37:26,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 9: [2023-04-29 11:37:26,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 9: [2023-04-29 11:37:26,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 9: [2023-04-29 11:37:26,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +44: [2023-04-29 11:37:26,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +44: [2023-04-29 11:37:26,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +44: [2023-04-29 11:37:26,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +44: [2023-04-29 11:37:26,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +57: [2023-04-29 11:37:26,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +57: [2023-04-29 11:37:26,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +35: [2023-04-29 11:37:26,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +35: [2023-04-29 11:37:26,677] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +57: [2023-04-29 11:37:26,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +22: [2023-04-29 11:37:26,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +22: [2023-04-29 11:37:26,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +22: [2023-04-29 11:37:26,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +22: [2023-04-29 11:37:26,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 0: [2023-04-29 11:37:26,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. + 0: [2023-04-29 11:37:26,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. + 0: [2023-04-29 11:37:26,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. + 0: [2023-04-29 11:37:26,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_04-model_01-model_states.pt. +42: [2023-04-29 11:37:26,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +42: [2023-04-29 11:37:26,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +42: [2023-04-29 11:37:26,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +42: [2023-04-29 11:37:26,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +45: [2023-04-29 11:37:26,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +45: [2023-04-29 11:37:26,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +45: [2023-04-29 11:37:26,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +45: [2023-04-29 11:37:26,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +40: [2023-04-29 11:37:26,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +40: [2023-04-29 11:37:26,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +40: [2023-04-29 11:37:26,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +45: [2023-04-29 11:37:26,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +45: [2023-04-29 11:37:26,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +45: [2023-04-29 11:37:26,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +40: [2023-04-29 11:37:26,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +40: [2023-04-29 11:37:26,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +40: [2023-04-29 11:37:26,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +40: [2023-04-29 11:37:26,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +52: [2023-04-29 11:37:26,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +45: [2023-04-29 11:37:26,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +40: [2023-04-29 11:37:26,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +47: [2023-04-29 11:37:26,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +47: [2023-04-29 11:37:26,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +52: [2023-04-29 11:37:26,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +52: [2023-04-29 11:37:26,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +52: [2023-04-29 11:37:26,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +52: [2023-04-29 11:37:26,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +52: [2023-04-29 11:37:26,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +52: [2023-04-29 11:37:26,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +52: [2023-04-29 11:37:26,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +62: [2023-04-29 11:37:26,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +62: [2023-04-29 11:37:26,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +62: [2023-04-29 11:37:26,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +22: [2023-04-29 11:37:26,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +22: [2023-04-29 11:37:26,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +22: [2023-04-29 11:37:26,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +62: [2023-04-29 11:37:26,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +62: [2023-04-29 11:37:26,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +62: [2023-04-29 11:37:26,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +47: [2023-04-29 11:37:26,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +62: [2023-04-29 11:37:26,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +22: [2023-04-29 11:37:26,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +62: [2023-04-29 11:37:26,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +47: [2023-04-29 11:37:26,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +17: [2023-04-29 11:37:26,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +17: [2023-04-29 11:37:26,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +17: [2023-04-29 11:37:26,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +17: [2023-04-29 11:37:26,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +17: [2023-04-29 11:37:26,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +47: [2023-04-29 11:37:26,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +47: [2023-04-29 11:37:26,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +47: [2023-04-29 11:37:26,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +47: [2023-04-29 11:37:26,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +40: [2023-04-29 11:37:26,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +17: [2023-04-29 11:37:26,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +17: [2023-04-29 11:37:26,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +17: [2023-04-29 11:37:26,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +28: [2023-04-29 11:37:26,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +28: [2023-04-29 11:37:26,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +28: [2023-04-29 11:37:26,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +28: [2023-04-29 11:37:26,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +28: [2023-04-29 11:37:26,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +28: [2023-04-29 11:37:26,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +28: [2023-04-29 11:37:26,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +28: [2023-04-29 11:37:26,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +50: [2023-04-29 11:37:26,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +59: [2023-04-29 11:37:26,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +59: [2023-04-29 11:37:26,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +59: [2023-04-29 11:37:26,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +52: [2023-04-29 11:37:26,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +42: [2023-04-29 11:37:26,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +42: [2023-04-29 11:37:26,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +42: [2023-04-29 11:37:26,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +59: [2023-04-29 11:37:26,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +42: [2023-04-29 11:37:26,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +45: [2023-04-29 11:37:26,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +50: [2023-04-29 11:37:26,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +45: [2023-04-29 11:37:26,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +45: [2023-04-29 11:37:26,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +56: [2023-04-29 11:37:26,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +56: [2023-04-29 11:37:26,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +45: [2023-04-29 11:37:26,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +38: [2023-04-29 11:37:26,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +38: [2023-04-29 11:37:26,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +40: [2023-04-29 11:37:26,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +40: [2023-04-29 11:37:26,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +39: [2023-04-29 11:37:26,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +39: [2023-04-29 11:37:26,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +52: [2023-04-29 11:37:26,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +52: [2023-04-29 11:37:26,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +39: [2023-04-29 11:37:26,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +39: [2023-04-29 11:37:26,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +52: [2023-04-29 11:37:26,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +62: [2023-04-29 11:37:26,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +32: [2023-04-29 11:37:26,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +17: [2023-04-29 11:37:26,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +36: [2023-04-29 11:37:26,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +36: [2023-04-29 11:37:26,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +45: [2023-04-29 11:37:26,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +18: [2023-04-29 11:37:26,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +45: [2023-04-29 11:37:26,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +62: [2023-04-29 11:37:26,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +47: [2023-04-29 11:37:26,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +45: [2023-04-29 11:37:26,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +45: [2023-04-29 11:37:26,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +47: [2023-04-29 11:37:26,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +56: [2023-04-29 11:37:26,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +47: [2023-04-29 11:37:26,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +47: [2023-04-29 11:37:26,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +38: [2023-04-29 11:37:26,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +56: [2023-04-29 11:37:26,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +56: [2023-04-29 11:37:26,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +56: [2023-04-29 11:37:26,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +56: [2023-04-29 11:37:26,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +47: [2023-04-29 11:37:26,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +40: [2023-04-29 11:37:26,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +40: [2023-04-29 11:37:26,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +38: [2023-04-29 11:37:26,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +42: [2023-04-29 11:37:26,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +28: [2023-04-29 11:37:26,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +40: [2023-04-29 11:37:26,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +56: [2023-04-29 11:37:26,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +28: [2023-04-29 11:37:26,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +28: [2023-04-29 11:37:26,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +28: [2023-04-29 11:37:26,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +28: [2023-04-29 11:37:26,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +28: [2023-04-29 11:37:26,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +28: [2023-04-29 11:37:26,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +40: [2023-04-29 11:37:26,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +35: [2023-04-29 11:37:26,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +47: [2023-04-29 11:37:26,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +40: [2023-04-29 11:37:26,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +32: [2023-04-29 11:37:26,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +47: [2023-04-29 11:37:26,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +32: [2023-04-29 11:37:26,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +47: [2023-04-29 11:37:26,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +32: [2023-04-29 11:37:26,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +28: [2023-04-29 11:37:26,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +52: [2023-04-29 11:37:26,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +35: [2023-04-29 11:37:26,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +52: [2023-04-29 11:37:26,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +36: [2023-04-29 11:37:26,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +36: [2023-04-29 11:37:26,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +13: [2023-04-29 11:37:26,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +52: [2023-04-29 11:37:26,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +13: [2023-04-29 11:37:26,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +13: [2023-04-29 11:37:26,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +52: [2023-04-29 11:37:26,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +60: [2023-04-29 11:37:26,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +13: [2023-04-29 11:37:26,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +13: [2023-04-29 11:37:26,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +13: [2023-04-29 11:37:26,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +13: [2023-04-29 11:37:26,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +57: [2023-04-29 11:37:26,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +13: [2023-04-29 11:37:26,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +56: [2023-04-29 11:37:26,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +56: [2023-04-29 11:37:26,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +62: [2023-04-29 11:37:26,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +62: [2023-04-29 11:37:26,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +62: [2023-04-29 11:37:26,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +38: [2023-04-29 11:37:26,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +38: [2023-04-29 11:37:26,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +43: [2023-04-29 11:37:26,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +43: [2023-04-29 11:37:26,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +38: [2023-04-29 11:37:26,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +62: [2023-04-29 11:37:26,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +43: [2023-04-29 11:37:26,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +43: [2023-04-29 11:37:26,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +62: [2023-04-29 11:37:26,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +36: [2023-04-29 11:37:26,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +36: [2023-04-29 11:37:26,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +62: [2023-04-29 11:37:26,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +56: [2023-04-29 11:37:26,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +56: [2023-04-29 11:37:26,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +38: [2023-04-29 11:37:26,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +56: [2023-04-29 11:37:26,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +56: [2023-04-29 11:37:26,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +56: [2023-04-29 11:37:26,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +56: [2023-04-29 11:37:26,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +42: [2023-04-29 11:37:26,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +60: [2023-04-29 11:37:26,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +60: [2023-04-29 11:37:26,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +44: [2023-04-29 11:37:26,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +13: [2023-04-29 11:37:26,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +11: [2023-04-29 11:37:26,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +11: [2023-04-29 11:37:26,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +22: [2023-04-29 11:37:26,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +22: [2023-04-29 11:37:26,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +58: [2023-04-29 11:37:26,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +42: [2023-04-29 11:37:26,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +42: [2023-04-29 11:37:26,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +44: [2023-04-29 11:37:26,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +22: [2023-04-29 11:37:26,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +60: [2023-04-29 11:37:26,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +13: [2023-04-29 11:37:26,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +36: [2023-04-29 11:37:26,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +36: [2023-04-29 11:37:26,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +13: [2023-04-29 11:37:26,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +57: [2023-04-29 11:37:26,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +11: [2023-04-29 11:37:26,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +11: [2023-04-29 11:37:26,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +44: [2023-04-29 11:37:26,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +55: [2023-04-29 11:37:26,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +55: [2023-04-29 11:37:26,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +11: [2023-04-29 11:37:26,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +11: [2023-04-29 11:37:26,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +11: [2023-04-29 11:37:26,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +55: [2023-04-29 11:37:26,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +44: [2023-04-29 11:37:26,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +55: [2023-04-29 11:37:26,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +11: [2023-04-29 11:37:26,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +37: [2023-04-29 11:37:26,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +37: [2023-04-29 11:37:26,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +58: [2023-04-29 11:37:26,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +37: [2023-04-29 11:37:26,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +37: [2023-04-29 11:37:26,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +13: [2023-04-29 11:37:26,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +26: [2023-04-29 11:37:26,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +26: [2023-04-29 11:37:26,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +35: [2023-04-29 11:37:26,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +57: [2023-04-29 11:37:26,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +31: [2023-04-29 11:37:26,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +18: [2023-04-29 11:37:26,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +18: [2023-04-29 11:37:26,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +57: [2023-04-29 11:37:26,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +26: [2023-04-29 11:37:26,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +26: [2023-04-29 11:37:26,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +13: [2023-04-29 11:37:26,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +26: [2023-04-29 11:37:26,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +26: [2023-04-29 11:37:26,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +26: [2023-04-29 11:37:26,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +13: [2023-04-29 11:37:26,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +31: [2023-04-29 11:37:26,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +31: [2023-04-29 11:37:26,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +31: [2023-04-29 11:37:26,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +31: [2023-04-29 11:37:26,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +26: [2023-04-29 11:37:26,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +13: [2023-04-29 11:37:26,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +22: [2023-04-29 11:37:26,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +22: [2023-04-29 11:37:26,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +22: [2023-04-29 11:37:26,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +58: [2023-04-29 11:37:26,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... + 0: [2023-04-29 11:37:26,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +13: [2023-04-29 11:37:26,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +11: [2023-04-29 11:37:26,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +11: [2023-04-29 11:37:26,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +36: [2023-04-29 11:37:26,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +11: [2023-04-29 11:37:26,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +11: [2023-04-29 11:37:26,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +49: [2023-04-29 11:37:26,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +42: [2023-04-29 11:37:26,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +42: [2023-04-29 11:37:26,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +58: [2023-04-29 11:37:26,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +49: [2023-04-29 11:37:26,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. + 0: [2023-04-29 11:37:26,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +18: [2023-04-29 11:37:26,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +11: [2023-04-29 11:37:26,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +11: [2023-04-29 11:37:26,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +11: [2023-04-29 11:37:26,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 0: [2023-04-29 11:37:26,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +11: [2023-04-29 11:37:26,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 0: [2023-04-29 11:37:26,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +29: [2023-04-29 11:37:26,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +29: [2023-04-29 11:37:26,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +26: [2023-04-29 11:37:26,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +26: [2023-04-29 11:37:26,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +22: [2023-04-29 11:37:26,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +31: [2023-04-29 11:37:26,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +26: [2023-04-29 11:37:26,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +26: [2023-04-29 11:37:26,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +12: [2023-04-29 11:37:26,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +17: [2023-04-29 11:37:26,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 1: [2023-04-29 11:37:26,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 1: [2023-04-29 11:37:26,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +50: [2023-04-29 11:37:26,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +53: [2023-04-29 11:37:26,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +53: [2023-04-29 11:37:26,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +53: [2023-04-29 11:37:26,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +53: [2023-04-29 11:37:26,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +12: [2023-04-29 11:37:26,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +17: [2023-04-29 11:37:26,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +29: [2023-04-29 11:37:26,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 1: [2023-04-29 11:37:26,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +50: [2023-04-29 11:37:26,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +12: [2023-04-29 11:37:26,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +17: [2023-04-29 11:37:26,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 1: [2023-04-29 11:37:26,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +50: [2023-04-29 11:37:26,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +12: [2023-04-29 11:37:26,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +17: [2023-04-29 11:37:26,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 1: [2023-04-29 11:37:26,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +50: [2023-04-29 11:37:26,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +12: [2023-04-29 11:37:26,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +17: [2023-04-29 11:37:26,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 1: [2023-04-29 11:37:26,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +23: [2023-04-29 11:37:26,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +12: [2023-04-29 11:37:26,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +17: [2023-04-29 11:37:26,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 1: [2023-04-29 11:37:26,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +12: [2023-04-29 11:37:26,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +17: [2023-04-29 11:37:26,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 1: [2023-04-29 11:37:26,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +23: [2023-04-29 11:37:26,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +12: [2023-04-29 11:37:26,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 1: [2023-04-29 11:37:26,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +29: [2023-04-29 11:37:26,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 1: [2023-04-29 11:37:26,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 1: [2023-04-29 11:37:26,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +29: [2023-04-29 11:37:26,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +29: [2023-04-29 11:37:26,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +29: [2023-04-29 11:37:26,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +38: [2023-04-29 11:37:26,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +36: [2023-04-29 11:37:26,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +26: [2023-04-29 11:37:26,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +18: [2023-04-29 11:37:26,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +29: [2023-04-29 11:37:26,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +36: [2023-04-29 11:37:26,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +31: [2023-04-29 11:37:26,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +31: [2023-04-29 11:37:26,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +31: [2023-04-29 11:37:26,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +36: [2023-04-29 11:37:26,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +31: [2023-04-29 11:37:26,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +49: [2023-04-29 11:37:26,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +31: [2023-04-29 11:37:26,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +36: [2023-04-29 11:37:26,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. + 1: [2023-04-29 11:37:26,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +53: [2023-04-29 11:37:26,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 1: [2023-04-29 11:37:26,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 1: [2023-04-29 11:37:26,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +31: [2023-04-29 11:37:26,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +26: [2023-04-29 11:37:26,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +31: [2023-04-29 11:37:26,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 1: [2023-04-29 11:37:26,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +26: [2023-04-29 11:37:26,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 1: [2023-04-29 11:37:26,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +26: [2023-04-29 11:37:26,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +38: [2023-04-29 11:37:26,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +23: [2023-04-29 11:37:26,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +23: [2023-04-29 11:37:26,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +23: [2023-04-29 11:37:26,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +23: [2023-04-29 11:37:26,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +23: [2023-04-29 11:37:26,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +42: [2023-04-29 11:37:26,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +23: [2023-04-29 11:37:26,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +58: [2023-04-29 11:37:26,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +53: [2023-04-29 11:37:26,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +53: [2023-04-29 11:37:26,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +59: [2023-04-29 11:37:26,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +50: [2023-04-29 11:37:26,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +50: [2023-04-29 11:37:26,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +34: [2023-04-29 11:37:26,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +34: [2023-04-29 11:37:26,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +59: [2023-04-29 11:37:26,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +53: [2023-04-29 11:37:26,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 2: [2023-04-29 11:37:26,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 2: [2023-04-29 11:37:26,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 2: [2023-04-29 11:37:26,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 2: [2023-04-29 11:37:26,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 2: [2023-04-29 11:37:26,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 2: [2023-04-29 11:37:26,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 2: [2023-04-29 11:37:26,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +59: [2023-04-29 11:37:26,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 2: [2023-04-29 11:37:26,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +59: [2023-04-29 11:37:26,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +25: [2023-04-29 11:37:26,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +29: [2023-04-29 11:37:26,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +29: [2023-04-29 11:37:26,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +29: [2023-04-29 11:37:26,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +39: [2023-04-29 11:37:26,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +23: [2023-04-29 11:37:26,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +29: [2023-04-29 11:37:26,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +36: [2023-04-29 11:37:26,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +29: [2023-04-29 11:37:26,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +23: [2023-04-29 11:37:26,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +22: [2023-04-29 11:37:26,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +29: [2023-04-29 11:37:26,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +29: [2023-04-29 11:37:26,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +23: [2023-04-29 11:37:26,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +29: [2023-04-29 11:37:26,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +38: [2023-04-29 11:37:26,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +23: [2023-04-29 11:37:26,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +31: [2023-04-29 11:37:26,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +31: [2023-04-29 11:37:26,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +31: [2023-04-29 11:37:26,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +34: [2023-04-29 11:37:26,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +38: [2023-04-29 11:37:26,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +34: [2023-04-29 11:37:26,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. + 2: [2023-04-29 11:37:26,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +14: [2023-04-29 11:37:26,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +34: [2023-04-29 11:37:26,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +38: [2023-04-29 11:37:26,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +36: [2023-04-29 11:37:26,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +48: [2023-04-29 11:37:26,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +48: [2023-04-29 11:37:26,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +25: [2023-04-29 11:37:26,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +49: [2023-04-29 11:37:26,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +58: [2023-04-29 11:37:26,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +58: [2023-04-29 11:37:26,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +34: [2023-04-29 11:37:26,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +42: [2023-04-29 11:37:26,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... + 2: [2023-04-29 11:37:26,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 2: [2023-04-29 11:37:26,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +39: [2023-04-29 11:37:26,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +39: [2023-04-29 11:37:26,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 2: [2023-04-29 11:37:26,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 2: [2023-04-29 11:37:26,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 2: [2023-04-29 11:37:26,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +36: [2023-04-29 11:37:26,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +43: [2023-04-29 11:37:26,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 2: [2023-04-29 11:37:26,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +23: [2023-04-29 11:37:26,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +23: [2023-04-29 11:37:26,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +23: [2023-04-29 11:37:26,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +43: [2023-04-29 11:37:26,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +43: [2023-04-29 11:37:26,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 2: [2023-04-29 11:37:26,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +39: [2023-04-29 11:37:26,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +23: [2023-04-29 11:37:26,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +50: [2023-04-29 11:37:26,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +48: [2023-04-29 11:37:26,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +38: [2023-04-29 11:37:26,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +48: [2023-04-29 11:37:26,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +63: [2023-04-29 11:37:26,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +59: [2023-04-29 11:37:26,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +59: [2023-04-29 11:37:26,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. + 5: [2023-04-29 11:37:26,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 5: [2023-04-29 11:37:26,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 5: [2023-04-29 11:37:26,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 5: [2023-04-29 11:37:26,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 5: [2023-04-29 11:37:26,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 5: [2023-04-29 11:37:26,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 5: [2023-04-29 11:37:26,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +59: [2023-04-29 11:37:26,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +59: [2023-04-29 11:37:26,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. + 5: [2023-04-29 11:37:26,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +25: [2023-04-29 11:37:26,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +43: [2023-04-29 11:37:26,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +53: [2023-04-29 11:37:26,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +53: [2023-04-29 11:37:26,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +32: [2023-04-29 11:37:26,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +34: [2023-04-29 11:37:26,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +53: [2023-04-29 11:37:26,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +58: [2023-04-29 11:37:26,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +12: [2023-04-29 11:37:26,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +49: [2023-04-29 11:37:26,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +44: [2023-04-29 11:37:26,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +44: [2023-04-29 11:37:26,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +48: [2023-04-29 11:37:26,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +48: [2023-04-29 11:37:26,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +55: [2023-04-29 11:37:26,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +38: [2023-04-29 11:37:26,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... + 3: [2023-04-29 11:37:26,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +49: [2023-04-29 11:37:26,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +49: [2023-04-29 11:37:26,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +49: [2023-04-29 11:37:26,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +49: [2023-04-29 11:37:26,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +63: [2023-04-29 11:37:26,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +25: [2023-04-29 11:37:26,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +55: [2023-04-29 11:37:26,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +55: [2023-04-29 11:37:26,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +34: [2023-04-29 11:37:26,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +55: [2023-04-29 11:37:26,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +53: [2023-04-29 11:37:26,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +48: [2023-04-29 11:37:26,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 5: [2023-04-29 11:37:26,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +48: [2023-04-29 11:37:26,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +44: [2023-04-29 11:37:26,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +59: [2023-04-29 11:37:26,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 5: [2023-04-29 11:37:26,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +44: [2023-04-29 11:37:26,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. + 5: [2023-04-29 11:37:26,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +59: [2023-04-29 11:37:26,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 5: [2023-04-29 11:37:26,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +59: [2023-04-29 11:37:26,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +14: [2023-04-29 11:37:26,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +14: [2023-04-29 11:37:26,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +38: [2023-04-29 11:37:26,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +12: [2023-04-29 11:37:26,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +37: [2023-04-29 11:37:26,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +59: [2023-04-29 11:37:26,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 3: [2023-04-29 11:37:26,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +34: [2023-04-29 11:37:26,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +34: [2023-04-29 11:37:26,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +18: [2023-04-29 11:37:26,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 5: [2023-04-29 11:37:26,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 5: [2023-04-29 11:37:26,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +44: [2023-04-29 11:37:26,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +44: [2023-04-29 11:37:26,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 5: [2023-04-29 11:37:26,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... + 5: [2023-04-29 11:37:26,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +37: [2023-04-29 11:37:26,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +37: [2023-04-29 11:37:26,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +44: [2023-04-29 11:37:26,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +63: [2023-04-29 11:37:26,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +63: [2023-04-29 11:37:26,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +49: [2023-04-29 11:37:26,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +14: [2023-04-29 11:37:26,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +44: [2023-04-29 11:37:26,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 3: [2023-04-29 11:37:26,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +34: [2023-04-29 11:37:26,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +34: [2023-04-29 11:37:26,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +50: [2023-04-29 11:37:26,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +18: [2023-04-29 11:37:26,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +37: [2023-04-29 11:37:26,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +49: [2023-04-29 11:37:26,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +32: [2023-04-29 11:37:26,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +12: [2023-04-29 11:37:26,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +12: [2023-04-29 11:37:26,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +12: [2023-04-29 11:37:26,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +50: [2023-04-29 11:37:26,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +50: [2023-04-29 11:37:26,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +19: [2023-04-29 11:37:26,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +19: [2023-04-29 11:37:26,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +58: [2023-04-29 11:37:26,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +58: [2023-04-29 11:37:26,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +48: [2023-04-29 11:37:26,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +48: [2023-04-29 11:37:26,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +48: [2023-04-29 11:37:26,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +48: [2023-04-29 11:37:26,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +40: [2023-04-29 11:37:26,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +19: [2023-04-29 11:37:26,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +19: [2023-04-29 11:37:26,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +19: [2023-04-29 11:37:26,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +19: [2023-04-29 11:37:26,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +19: [2023-04-29 11:37:26,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 9: [2023-04-29 11:37:26,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +19: [2023-04-29 11:37:26,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 9: [2023-04-29 11:37:26,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 3: [2023-04-29 11:37:26,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 9: [2023-04-29 11:37:26,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +51: [2023-04-29 11:37:26,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +18: [2023-04-29 11:37:26,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +50: [2023-04-29 11:37:26,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +58: [2023-04-29 11:37:26,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +42: [2023-04-29 11:37:26,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +14: [2023-04-29 11:37:26,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +12: [2023-04-29 11:37:26,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +12: [2023-04-29 11:37:26,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +12: [2023-04-29 11:37:26,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 9: [2023-04-29 11:37:26,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 9: [2023-04-29 11:37:26,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 9: [2023-04-29 11:37:26,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 9: [2023-04-29 11:37:26,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +54: [2023-04-29 11:37:26,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +54: [2023-04-29 11:37:26,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +19: [2023-04-29 11:37:26,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +19: [2023-04-29 11:37:26,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +19: [2023-04-29 11:37:26,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +19: [2023-04-29 11:37:26,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +32: [2023-04-29 11:37:26,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +25: [2023-04-29 11:37:26,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +19: [2023-04-29 11:37:26,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +58: [2023-04-29 11:37:26,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +54: [2023-04-29 11:37:26,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +54: [2023-04-29 11:37:26,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +19: [2023-04-29 11:37:26,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +19: [2023-04-29 11:37:26,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +63: [2023-04-29 11:37:26,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +22: [2023-04-29 11:37:26,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +19: [2023-04-29 11:37:26,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +45: [2023-04-29 11:37:26,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +49: [2023-04-29 11:37:26,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +51: [2023-04-29 11:37:26,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +51: [2023-04-29 11:37:26,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +51: [2023-04-29 11:37:26,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. + 3: [2023-04-29 11:37:26,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +17: [2023-04-29 11:37:26,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +25: [2023-04-29 11:37:26,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +52: [2023-04-29 11:37:26,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +28: [2023-04-29 11:37:26,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +22: [2023-04-29 11:37:26,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +22: [2023-04-29 11:37:26,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +63: [2023-04-29 11:37:26,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +22: [2023-04-29 11:37:26,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +45: [2023-04-29 11:37:26,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +32: [2023-04-29 11:37:26,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +32: [2023-04-29 11:37:26,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +47: [2023-04-29 11:37:26,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +46: [2023-04-29 11:37:26,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +46: [2023-04-29 11:37:26,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +46: [2023-04-29 11:37:26,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +46: [2023-04-29 11:37:26,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +53: [2023-04-29 11:37:26,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +53: [2023-04-29 11:37:26,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +62: [2023-04-29 11:37:26,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. + 3: [2023-04-29 11:37:26,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +28: [2023-04-29 11:37:26,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +28: [2023-04-29 11:37:26,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +52: [2023-04-29 11:37:26,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +52: [2023-04-29 11:37:26,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +42: [2023-04-29 11:37:26,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +42: [2023-04-29 11:37:26,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +42: [2023-04-29 11:37:26,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +41: [2023-04-29 11:37:26,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +41: [2023-04-29 11:37:26,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +41: [2023-04-29 11:37:26,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +41: [2023-04-29 11:37:26,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +41: [2023-04-29 11:37:26,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +41: [2023-04-29 11:37:26,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +41: [2023-04-29 11:37:26,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +28: [2023-04-29 11:37:26,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +41: [2023-04-29 11:37:26,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +38: [2023-04-29 11:37:26,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +49: [2023-04-29 11:37:26,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +52: [2023-04-29 11:37:26,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +14: [2023-04-29 11:37:26,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +34: [2023-04-29 11:37:26,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +49: [2023-04-29 11:37:26,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +62: [2023-04-29 11:37:26,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +17: [2023-04-29 11:37:26,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +17: [2023-04-29 11:37:26,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +17: [2023-04-29 11:37:26,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +53: [2023-04-29 11:37:26,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +25: [2023-04-29 11:37:26,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +47: [2023-04-29 11:37:26,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +45: [2023-04-29 11:37:26,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +46: [2023-04-29 11:37:26,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +32: [2023-04-29 11:37:26,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +44: [2023-04-29 11:37:26,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. + 3: [2023-04-29 11:37:26,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +14: [2023-04-29 11:37:26,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +63: [2023-04-29 11:37:26,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +46: [2023-04-29 11:37:26,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +46: [2023-04-29 11:37:26,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +34: [2023-04-29 11:37:26,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +46: [2023-04-29 11:37:26,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +47: [2023-04-29 11:37:26,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +36: [2023-04-29 11:37:26,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +63: [2023-04-29 11:37:26,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +56: [2023-04-29 11:37:26,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +56: [2023-04-29 11:37:26,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +56: [2023-04-29 11:37:26,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +13: [2023-04-29 11:37:26,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +13: [2023-04-29 11:37:26,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +49: [2023-04-29 11:37:26,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +41: [2023-04-29 11:37:26,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +41: [2023-04-29 11:37:26,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +60: [2023-04-29 11:37:26,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +60: [2023-04-29 11:37:26,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +25: [2023-04-29 11:37:26,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +41: [2023-04-29 11:37:26,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +61: [2023-04-29 11:37:26,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +61: [2023-04-29 11:37:26,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +61: [2023-04-29 11:37:26,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +61: [2023-04-29 11:37:26,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_27-model_01-model_states.pt. +45: [2023-04-29 11:37:26,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +40: [2023-04-29 11:37:26,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +47: [2023-04-29 11:37:26,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +33: [2023-04-29 11:37:26,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +53: [2023-04-29 11:37:26,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +33: [2023-04-29 11:37:26,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +33: [2023-04-29 11:37:26,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +11: [2023-04-29 11:37:26,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +33: [2023-04-29 11:37:26,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +40: [2023-04-29 11:37:26,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +60: [2023-04-29 11:37:26,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +60: [2023-04-29 11:37:26,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +36: [2023-04-29 11:37:26,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +38: [2023-04-29 11:37:26,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +37: [2023-04-29 11:37:26,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +14: [2023-04-29 11:37:26,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +49: [2023-04-29 11:37:26,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +44: [2023-04-29 11:37:26,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +38: [2023-04-29 11:37:26,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +38: [2023-04-29 11:37:26,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +11: [2023-04-29 11:37:26,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +32: [2023-04-29 11:37:26,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +60: [2023-04-29 11:37:26,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +58: [2023-04-29 11:37:26,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +50: [2023-04-29 11:37:26,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +62: [2023-04-29 11:37:26,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +62: [2023-04-29 11:37:26,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. + 3: [2023-04-29 11:37:26,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +41: [2023-04-29 11:37:26,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +41: [2023-04-29 11:37:26,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +60: [2023-04-29 11:37:26,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +56: [2023-04-29 11:37:26,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +37: [2023-04-29 11:37:26,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +37: [2023-04-29 11:37:26,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +37: [2023-04-29 11:37:26,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +50: [2023-04-29 11:37:26,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +51: [2023-04-29 11:37:26,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +60: [2023-04-29 11:37:26,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +41: [2023-04-29 11:37:26,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +48: [2023-04-29 11:37:26,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +37: [2023-04-29 11:37:26,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +12: [2023-04-29 11:37:26,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +41: [2023-04-29 11:37:26,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +41: [2023-04-29 11:37:26,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +13: [2023-04-29 11:37:26,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +60: [2023-04-29 11:37:26,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +60: [2023-04-29 11:37:26,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +40: [2023-04-29 11:37:26,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +44: [2023-04-29 11:37:26,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +44: [2023-04-29 11:37:26,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +34: [2023-04-29 11:37:26,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +34: [2023-04-29 11:37:26,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +60: [2023-04-29 11:37:26,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +32: [2023-04-29 11:37:26,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +48: [2023-04-29 11:37:26,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 0: [2023-04-29 11:37:26,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +40: [2023-04-29 11:37:26,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +58: [2023-04-29 11:37:26,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +11: [2023-04-29 11:37:26,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +11: [2023-04-29 11:37:26,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 1: [2023-04-29 11:37:26,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +42: [2023-04-29 11:37:26,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +13: [2023-04-29 11:37:26,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +48: [2023-04-29 11:37:26,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +48: [2023-04-29 11:37:26,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +60: [2023-04-29 11:37:26,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +60: [2023-04-29 11:37:26,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +12: [2023-04-29 11:37:26,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +12: [2023-04-29 11:37:26,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +26: [2023-04-29 11:37:26,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +46: [2023-04-29 11:37:26,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +46: [2023-04-29 11:37:26,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +58: [2023-04-29 11:37:26,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +54: [2023-04-29 11:37:26,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +60: [2023-04-29 11:37:26,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +52: [2023-04-29 11:37:26,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +54: [2023-04-29 11:37:26,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 1: [2023-04-29 11:37:26,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +29: [2023-04-29 11:37:26,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +26: [2023-04-29 11:37:26,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +31: [2023-04-29 11:37:26,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +44: [2023-04-29 11:37:26,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +54: [2023-04-29 11:37:26,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +12: [2023-04-29 11:37:26,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +44: [2023-04-29 11:37:26,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +58: [2023-04-29 11:37:26,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +44: [2023-04-29 11:37:26,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +55: [2023-04-29 11:37:26,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +55: [2023-04-29 11:37:26,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +37: [2023-04-29 11:37:26,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +37: [2023-04-29 11:37:26,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +36: [2023-04-29 11:37:26,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +37: [2023-04-29 11:37:26,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +36: [2023-04-29 11:37:26,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +54: [2023-04-29 11:37:26,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 0: [2023-04-29 11:37:26,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +22: [2023-04-29 11:37:26,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +23: [2023-04-29 11:37:26,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +55: [2023-04-29 11:37:26,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +55: [2023-04-29 11:37:26,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +60: [2023-04-29 11:37:26,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +60: [2023-04-29 11:37:26,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +26: [2023-04-29 11:37:26,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +45: [2023-04-29 11:37:26,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +26: [2023-04-29 11:37:26,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +53: [2023-04-29 11:37:26,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +47: [2023-04-29 11:37:26,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 1: [2023-04-29 11:37:26,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +50: [2023-04-29 11:37:26,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 1: [2023-04-29 11:37:26,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +46: [2023-04-29 11:37:26,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +17: [2023-04-29 11:37:26,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +32: [2023-04-29 11:37:26,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +23: [2023-04-29 11:37:26,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +31: [2023-04-29 11:37:26,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +31: [2023-04-29 11:37:26,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +46: [2023-04-29 11:37:26,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +32: [2023-04-29 11:37:26,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +60: [2023-04-29 11:37:26,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +31: [2023-04-29 11:37:26,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 0: [2023-04-29 11:37:26,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +62: [2023-04-29 11:37:26,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +32: [2023-04-29 11:37:26,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +32: [2023-04-29 11:37:26,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +28: [2023-04-29 11:37:26,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +38: [2023-04-29 11:37:26,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +44: [2023-04-29 11:37:26,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +59: [2023-04-29 11:37:26,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +59: [2023-04-29 11:37:26,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +55: [2023-04-29 11:37:26,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +55: [2023-04-29 11:37:26,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... + 0: [2023-04-29 11:37:26,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +45: [2023-04-29 11:37:26,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 0: [2023-04-29 11:37:26,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +55: [2023-04-29 11:37:26,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +22: [2023-04-29 11:37:26,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +34: [2023-04-29 11:37:26,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +52: [2023-04-29 11:37:26,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +52: [2023-04-29 11:37:26,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +55: [2023-04-29 11:37:26,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +28: [2023-04-29 11:37:26,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +62: [2023-04-29 11:37:26,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +22: [2023-04-29 11:37:26,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +22: [2023-04-29 11:37:26,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +51: [2023-04-29 11:37:26,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +29: [2023-04-29 11:37:26,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +29: [2023-04-29 11:37:26,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +29: [2023-04-29 11:37:26,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 9: [2023-04-29 11:37:26,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 9: [2023-04-29 11:37:26,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 9: [2023-04-29 11:37:26,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 9: [2023-04-29 11:37:26,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 9: [2023-04-29 11:37:26,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... + 9: [2023-04-29 11:37:26,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 9: [2023-04-29 11:37:26,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 9: [2023-04-29 11:37:26,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 9: [2023-04-29 11:37:26,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +42: [2023-04-29 11:37:26,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +51: [2023-04-29 11:37:26,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +51: [2023-04-29 11:37:26,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +28: [2023-04-29 11:37:26,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +52: [2023-04-29 11:37:26,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +32: [2023-04-29 11:37:26,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... + 0: [2023-04-29 11:37:26,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +45: [2023-04-29 11:37:26,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +42: [2023-04-29 11:37:26,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +42: [2023-04-29 11:37:26,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +32: [2023-04-29 11:37:26,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +59: [2023-04-29 11:37:26,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +59: [2023-04-29 11:37:26,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +17: [2023-04-29 11:37:26,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +47: [2023-04-29 11:37:26,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 0: [2023-04-29 11:37:26,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +23: [2023-04-29 11:37:26,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +23: [2023-04-29 11:37:26,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +36: [2023-04-29 11:37:26,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 0: [2023-04-29 11:37:26,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +17: [2023-04-29 11:37:26,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +28: [2023-04-29 11:37:26,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +45: [2023-04-29 11:37:26,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +59: [2023-04-29 11:37:26,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +17: [2023-04-29 11:37:26,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +32: [2023-04-29 11:37:26,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +32: [2023-04-29 11:37:26,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +59: [2023-04-29 11:37:26,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +11: [2023-04-29 11:37:26,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +34: [2023-04-29 11:37:26,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +47: [2023-04-29 11:37:26,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 2: [2023-04-29 11:37:26,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +47: [2023-04-29 11:37:26,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 2: [2023-04-29 11:37:26,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 2: [2023-04-29 11:37:26,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 2: [2023-04-29 11:37:26,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +56: [2023-04-29 11:37:26,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +56: [2023-04-29 11:37:26,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +36: [2023-04-29 11:37:26,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +13: [2023-04-29 11:37:26,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +56: [2023-04-29 11:37:26,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +13: [2023-04-29 11:37:26,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +40: [2023-04-29 11:37:26,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +33: [2023-04-29 11:37:26,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +11: [2023-04-29 11:37:26,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +61: [2023-04-29 11:37:26,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +37: [2023-04-29 11:37:26,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +38: [2023-04-29 11:37:26,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +61: [2023-04-29 11:37:26,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +61: [2023-04-29 11:37:26,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +61: [2023-04-29 11:37:26,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +61: [2023-04-29 11:37:26,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +33: [2023-04-29 11:37:26,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +33: [2023-04-29 11:37:26,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +33: [2023-04-29 11:37:26,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +62: [2023-04-29 11:37:26,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +62: [2023-04-29 11:37:26,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +56: [2023-04-29 11:37:26,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +44: [2023-04-29 11:37:26,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +61: [2023-04-29 11:37:26,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +38: [2023-04-29 11:37:26,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +59: [2023-04-29 11:37:26,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +61: [2023-04-29 11:37:26,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +12: [2023-04-29 11:37:26,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +59: [2023-04-29 11:37:26,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +38: [2023-04-29 11:37:26,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +48: [2023-04-29 11:37:26,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +33: [2023-04-29 11:37:26,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +11: [2023-04-29 11:37:26,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +53: [2023-04-29 11:37:26,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +53: [2023-04-29 11:37:26,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +53: [2023-04-29 11:37:26,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +11: [2023-04-29 11:37:26,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +61: [2023-04-29 11:37:26,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. + 1: [2023-04-29 11:37:26,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +37: [2023-04-29 11:37:26,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +29: [2023-04-29 11:37:26,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +33: [2023-04-29 11:37:26,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +40: [2023-04-29 11:37:26,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +61: [2023-04-29 11:37:26,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +33: [2023-04-29 11:37:26,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +40: [2023-04-29 11:37:26,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +46: [2023-04-29 11:37:26,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +46: [2023-04-29 11:37:26,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +59: [2023-04-29 11:37:26,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +55: [2023-04-29 11:37:26,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +55: [2023-04-29 11:37:26,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +53: [2023-04-29 11:37:26,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +33: [2023-04-29 11:37:26,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +31: [2023-04-29 11:37:26,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 1: [2023-04-29 11:37:26,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +61: [2023-04-29 11:37:26,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +33: [2023-04-29 11:37:26,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +33: [2023-04-29 11:37:26,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +12: [2023-04-29 11:37:26,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +12: [2023-04-29 11:37:26,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +59: [2023-04-29 11:37:26,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +33: [2023-04-29 11:37:26,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +55: [2023-04-29 11:37:26,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +55: [2023-04-29 11:37:26,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +59: [2023-04-29 11:37:26,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +61: [2023-04-29 11:37:26,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +23: [2023-04-29 11:37:26,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +12: [2023-04-29 11:37:26,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 5: [2023-04-29 11:37:26,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 5: [2023-04-29 11:37:26,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. + 5: [2023-04-29 11:37:26,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +44: [2023-04-29 11:37:26,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +26: [2023-04-29 11:37:26,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +13: [2023-04-29 11:37:26,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +13: [2023-04-29 11:37:26,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +61: [2023-04-29 11:37:26,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +44: [2023-04-29 11:37:26,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +26: [2023-04-29 11:37:26,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +59: [2023-04-29 11:37:26,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. + 5: [2023-04-29 11:37:26,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +46: [2023-04-29 11:37:26,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +48: [2023-04-29 11:37:26,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +31: [2023-04-29 11:37:26,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +36: [2023-04-29 11:37:26,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +44: [2023-04-29 11:37:26,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +31: [2023-04-29 11:37:26,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +31: [2023-04-29 11:37:26,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +55: [2023-04-29 11:37:26,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +55: [2023-04-29 11:37:26,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... + 1: [2023-04-29 11:37:26,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +55: [2023-04-29 11:37:26,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +55: [2023-04-29 11:37:26,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +23: [2023-04-29 11:37:26,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +36: [2023-04-29 11:37:26,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +26: [2023-04-29 11:37:26,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +26: [2023-04-29 11:37:26,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +19: [2023-04-29 11:37:26,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +46: [2023-04-29 11:37:26,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +33: [2023-04-29 11:37:26,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 1: [2023-04-29 11:37:26,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +48: [2023-04-29 11:37:26,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +34: [2023-04-29 11:37:26,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +19: [2023-04-29 11:37:26,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +29: [2023-04-29 11:37:26,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +19: [2023-04-29 11:37:26,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +29: [2023-04-29 11:37:26,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +19: [2023-04-29 11:37:26,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +29: [2023-04-29 11:37:26,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +34: [2023-04-29 11:37:26,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +34: [2023-04-29 11:37:26,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +35: [2023-04-29 11:37:26,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +35: [2023-04-29 11:37:26,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +23: [2023-04-29 11:37:26,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +23: [2023-04-29 11:37:26,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 2: [2023-04-29 11:37:26,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +35: [2023-04-29 11:37:26,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +35: [2023-04-29 11:37:26,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +34: [2023-04-29 11:37:26,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. + 2: [2023-04-29 11:37:26,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +48: [2023-04-29 11:37:26,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 2: [2023-04-29 11:37:26,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 2: [2023-04-29 11:37:26,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +48: [2023-04-29 11:37:26,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +44: [2023-04-29 11:37:26,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +59: [2023-04-29 11:37:26,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +37: [2023-04-29 11:37:26,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +37: [2023-04-29 11:37:26,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +37: [2023-04-29 11:37:26,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +37: [2023-04-29 11:37:26,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +59: [2023-04-29 11:37:26,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +53: [2023-04-29 11:37:26,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +53: [2023-04-29 11:37:26,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +53: [2023-04-29 11:37:26,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +53: [2023-04-29 11:37:26,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +59: [2023-04-29 11:37:26,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +41: [2023-04-29 11:37:26,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +34: [2023-04-29 11:37:26,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +34: [2023-04-29 11:37:26,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +57: [2023-04-29 11:37:26,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +57: [2023-04-29 11:37:26,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +57: [2023-04-29 11:37:26,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +57: [2023-04-29 11:37:26,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +59: [2023-04-29 11:37:26,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +46: [2023-04-29 11:37:26,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +60: [2023-04-29 11:37:26,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +37: [2023-04-29 11:37:26,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +37: [2023-04-29 11:37:26,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +53: [2023-04-29 11:37:26,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +53: [2023-04-29 11:37:26,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +44: [2023-04-29 11:37:26,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +44: [2023-04-29 11:37:26,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +19: [2023-04-29 11:37:26,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +19: [2023-04-29 11:37:26,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +37: [2023-04-29 11:37:26,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +60: [2023-04-29 11:37:26,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. + 5: [2023-04-29 11:37:26,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +48: [2023-04-29 11:37:26,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +53: [2023-04-29 11:37:26,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +53: [2023-04-29 11:37:26,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +53: [2023-04-29 11:37:26,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +16: [2023-04-29 11:37:26,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +16: [2023-04-29 11:37:26,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +44: [2023-04-29 11:37:26,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +19: [2023-04-29 11:37:26,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +19: [2023-04-29 11:37:26,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 5: [2023-04-29 11:37:26,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +48: [2023-04-29 11:37:26,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +35: [2023-04-29 11:37:26,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +41: [2023-04-29 11:37:26,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +35: [2023-04-29 11:37:26,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 5: [2023-04-29 11:37:26,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 5: [2023-04-29 11:37:26,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +16: [2023-04-29 11:37:26,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +16: [2023-04-29 11:37:26,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +16: [2023-04-29 11:37:26,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +16: [2023-04-29 11:37:26,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +16: [2023-04-29 11:37:26,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +60: [2023-04-29 11:37:26,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +60: [2023-04-29 11:37:26,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +16: [2023-04-29 11:37:26,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +41: [2023-04-29 11:37:26,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +35: [2023-04-29 11:37:26,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +39: [2023-04-29 11:37:26,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +39: [2023-04-29 11:37:26,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +34: [2023-04-29 11:37:26,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +34: [2023-04-29 11:37:26,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +16: [2023-04-29 11:37:26,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +34: [2023-04-29 11:37:26,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +16: [2023-04-29 11:37:26,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +46: [2023-04-29 11:37:26,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +35: [2023-04-29 11:37:26,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +46: [2023-04-29 11:37:26,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +46: [2023-04-29 11:37:26,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +39: [2023-04-29 11:37:26,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +39: [2023-04-29 11:37:26,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +39: [2023-04-29 11:37:26,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +39: [2023-04-29 11:37:26,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +39: [2023-04-29 11:37:26,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +39: [2023-04-29 11:37:26,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +48: [2023-04-29 11:37:26,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +34: [2023-04-29 11:37:26,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +37: [2023-04-29 11:37:26,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +53: [2023-04-29 11:37:26,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +55: [2023-04-29 11:37:26,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +55: [2023-04-29 11:37:26,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +55: [2023-04-29 11:37:26,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +55: [2023-04-29 11:37:26,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +39: [2023-04-29 11:37:26,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +39: [2023-04-29 11:37:26,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +39: [2023-04-29 11:37:26,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +48: [2023-04-29 11:37:26,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +41: [2023-04-29 11:37:26,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +16: [2023-04-29 11:37:26,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +48: [2023-04-29 11:37:26,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +16: [2023-04-29 11:37:26,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +48: [2023-04-29 11:37:26,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +16: [2023-04-29 11:37:26,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +48: [2023-04-29 11:37:26,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +39: [2023-04-29 11:37:26,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +39: [2023-04-29 11:37:26,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +39: [2023-04-29 11:37:26,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +16: [2023-04-29 11:37:26,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +16: [2023-04-29 11:37:26,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt... +16: [2023-04-29 11:37:26,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt... +39: [2023-04-29 11:37:26,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +39: [2023-04-29 11:37:26,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +41: [2023-04-29 11:37:26,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +53: [2023-04-29 11:37:26,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +46: [2023-04-29 11:37:26,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +33: [2023-04-29 11:37:26,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +34: [2023-04-29 11:37:26,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +34: [2023-04-29 11:37:26,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +57: [2023-04-29 11:37:26,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +48: [2023-04-29 11:37:26,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +57: [2023-04-29 11:37:26,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +60: [2023-04-29 11:37:26,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +57: [2023-04-29 11:37:26,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +57: [2023-04-29 11:37:26,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +48: [2023-04-29 11:37:26,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +48: [2023-04-29 11:37:26,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +61: [2023-04-29 11:37:26,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +60: [2023-04-29 11:37:26,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +33: [2023-04-29 11:37:26,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +48: [2023-04-29 11:37:26,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +37: [2023-04-29 11:37:26,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +37: [2023-04-29 11:37:26,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +43: [2023-04-29 11:37:26,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +43: [2023-04-29 11:37:26,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +43: [2023-04-29 11:37:26,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +43: [2023-04-29 11:37:26,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +43: [2023-04-29 11:37:26,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +43: [2023-04-29 11:37:26,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +43: [2023-04-29 11:37:26,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +43: [2023-04-29 11:37:26,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +61: [2023-04-29 11:37:26,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +61: [2023-04-29 11:37:26,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +41: [2023-04-29 11:37:26,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +34: [2023-04-29 11:37:26,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +34: [2023-04-29 11:37:26,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +61: [2023-04-29 11:37:26,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +60: [2023-04-29 11:37:26,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +43: [2023-04-29 11:37:26,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +61: [2023-04-29 11:37:26,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +61: [2023-04-29 11:37:26,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +61: [2023-04-29 11:37:26,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +37: [2023-04-29 11:37:26,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +33: [2023-04-29 11:37:26,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +33: [2023-04-29 11:37:26,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +33: [2023-04-29 11:37:26,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +61: [2023-04-29 11:37:26,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +43: [2023-04-29 11:37:26,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +43: [2023-04-29 11:37:26,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +43: [2023-04-29 11:37:26,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +43: [2023-04-29 11:37:26,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +60: [2023-04-29 11:37:26,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +43: [2023-04-29 11:37:26,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt... +46: [2023-04-29 11:37:26,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +46: [2023-04-29 11:37:26,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +43: [2023-04-29 11:37:26,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +41: [2023-04-29 11:37:26,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +43: [2023-04-29 11:37:26,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +33: [2023-04-29 11:37:26,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +46: [2023-04-29 11:37:26,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +55: [2023-04-29 11:37:26,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +33: [2023-04-29 11:37:26,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +33: [2023-04-29 11:37:26,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +61: [2023-04-29 11:37:26,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +61: [2023-04-29 11:37:26,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +61: [2023-04-29 11:37:26,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt... +46: [2023-04-29 11:37:26,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +46: [2023-04-29 11:37:26,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +46: [2023-04-29 11:37:26,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +55: [2023-04-29 11:37:26,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +46: [2023-04-29 11:37:26,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +46: [2023-04-29 11:37:26,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +33: [2023-04-29 11:37:26,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +41: [2023-04-29 11:37:26,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +33: [2023-04-29 11:37:26,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +55: [2023-04-29 11:37:26,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +55: [2023-04-29 11:37:26,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +33: [2023-04-29 11:37:26,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +46: [2023-04-29 11:37:26,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +61: [2023-04-29 11:37:26,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +33: [2023-04-29 11:37:26,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +61: [2023-04-29 11:37:26,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +37: [2023-04-29 11:37:26,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +37: [2023-04-29 11:37:26,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +61: [2023-04-29 11:37:26,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +46: [2023-04-29 11:37:26,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +63: [2023-04-29 11:37:26,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +63: [2023-04-29 11:37:26,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +63: [2023-04-29 11:37:26,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +61: [2023-04-29 11:37:26,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +37: [2023-04-29 11:37:26,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +63: [2023-04-29 11:37:26,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +33: [2023-04-29 11:37:26,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +33: [2023-04-29 11:37:26,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +54: [2023-04-29 11:37:26,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +54: [2023-04-29 11:37:26,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +54: [2023-04-29 11:37:26,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +54: [2023-04-29 11:37:26,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +54: [2023-04-29 11:37:26,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +54: [2023-04-29 11:37:26,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +54: [2023-04-29 11:37:26,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +54: [2023-04-29 11:37:26,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +46: [2023-04-29 11:37:26,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +54: [2023-04-29 11:37:26,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +33: [2023-04-29 11:37:26,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +54: [2023-04-29 11:37:26,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +54: [2023-04-29 11:37:26,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +54: [2023-04-29 11:37:26,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +54: [2023-04-29 11:37:26,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +54: [2023-04-29 11:37:26,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +54: [2023-04-29 11:37:26,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +54: [2023-04-29 11:37:26,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +27: [2023-04-29 11:37:26,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +27: [2023-04-29 11:37:26,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +27: [2023-04-29 11:37:26,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +27: [2023-04-29 11:37:26,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +30: [2023-04-29 11:37:26,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +30: [2023-04-29 11:37:26,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +30: [2023-04-29 11:37:26,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +30: [2023-04-29 11:37:26,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +61: [2023-04-29 11:37:26,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +39: [2023-04-29 11:37:26,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +33: [2023-04-29 11:37:26,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +39: [2023-04-29 11:37:26,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +39: [2023-04-29 11:37:26,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +39: [2023-04-29 11:37:26,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +16: [2023-04-29 11:37:26,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +16: [2023-04-29 11:37:26,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +16: [2023-04-29 11:37:26,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +63: [2023-04-29 11:37:26,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +63: [2023-04-29 11:37:26,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +47: [2023-04-29 11:37:26,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +47: [2023-04-29 11:37:26,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +47: [2023-04-29 11:37:26,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +47: [2023-04-29 11:37:26,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +63: [2023-04-29 11:37:26,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +16: [2023-04-29 11:37:26,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_00-model_states.pt. +63: [2023-04-29 11:37:26,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +43: [2023-04-29 11:37:26,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +45: [2023-04-29 11:37:26,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +45: [2023-04-29 11:37:26,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +43: [2023-04-29 11:37:26,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +45: [2023-04-29 11:37:26,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +49: [2023-04-29 11:37:26,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +45: [2023-04-29 11:37:26,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +49: [2023-04-29 11:37:26,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +49: [2023-04-29 11:37:26,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +43: [2023-04-29 11:37:26,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +43: [2023-04-29 11:37:26,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_00-model_states.pt. +49: [2023-04-29 11:37:26,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +30: [2023-04-29 11:37:26,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +27: [2023-04-29 11:37:26,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +27: [2023-04-29 11:37:26,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +39: [2023-04-29 11:37:26,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +27: [2023-04-29 11:37:26,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +27: [2023-04-29 11:37:26,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +30: [2023-04-29 11:37:26,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +30: [2023-04-29 11:37:26,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +51: [2023-04-29 11:37:26,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +51: [2023-04-29 11:37:26,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +51: [2023-04-29 11:37:26,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +51: [2023-04-29 11:37:26,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +30: [2023-04-29 11:37:26,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +52: [2023-04-29 11:37:26,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +52: [2023-04-29 11:37:26,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +39: [2023-04-29 11:37:26,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +39: [2023-04-29 11:37:26,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +39: [2023-04-29 11:37:26,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +52: [2023-04-29 11:37:26,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +52: [2023-04-29 11:37:26,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +47: [2023-04-29 11:37:26,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +16: [2023-04-29 11:37:26,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +47: [2023-04-29 11:37:26,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +16: [2023-04-29 11:37:26,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +58: [2023-04-29 11:37:26,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +58: [2023-04-29 11:37:26,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +58: [2023-04-29 11:37:26,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +58: [2023-04-29 11:37:26,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +43: [2023-04-29 11:37:26,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +47: [2023-04-29 11:37:26,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +47: [2023-04-29 11:37:26,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +16: [2023-04-29 11:37:26,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +49: [2023-04-29 11:37:26,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +45: [2023-04-29 11:37:26,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +45: [2023-04-29 11:37:26,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +45: [2023-04-29 11:37:26,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +45: [2023-04-29 11:37:26,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +43: [2023-04-29 11:37:26,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +43: [2023-04-29 11:37:26,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +49: [2023-04-29 11:37:26,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +16: [2023-04-29 11:37:26,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +44: [2023-04-29 11:37:26,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +44: [2023-04-29 11:37:26,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +44: [2023-04-29 11:37:26,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +43: [2023-04-29 11:37:26,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +44: [2023-04-29 11:37:26,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +54: [2023-04-29 11:37:26,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +49: [2023-04-29 11:37:26,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +51: [2023-04-29 11:37:26,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +49: [2023-04-29 11:37:26,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +51: [2023-04-29 11:37:26,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +54: [2023-04-29 11:37:26,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +51: [2023-04-29 11:37:26,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +51: [2023-04-29 11:37:26,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +54: [2023-04-29 11:37:26,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +52: [2023-04-29 11:37:26,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +54: [2023-04-29 11:37:26,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +58: [2023-04-29 11:37:26,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +52: [2023-04-29 11:37:26,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +58: [2023-04-29 11:37:26,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +58: [2023-04-29 11:37:26,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +52: [2023-04-29 11:37:26,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +58: [2023-04-29 11:37:26,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +52: [2023-04-29 11:37:26,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +36: [2023-04-29 11:37:26,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +36: [2023-04-29 11:37:26,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +36: [2023-04-29 11:37:26,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +36: [2023-04-29 11:37:26,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +44: [2023-04-29 11:37:26,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +54: [2023-04-29 11:37:26,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +56: [2023-04-29 11:37:26,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +56: [2023-04-29 11:37:26,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +56: [2023-04-29 11:37:26,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +56: [2023-04-29 11:37:26,998] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +44: [2023-04-29 11:37:26,999] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +44: [2023-04-29 11:37:26,999] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +44: [2023-04-29 11:37:27,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +42: [2023-04-29 11:37:27,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +42: [2023-04-29 11:37:27,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +42: [2023-04-29 11:37:27,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +42: [2023-04-29 11:37:27,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +54: [2023-04-29 11:37:27,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 8: [2023-04-29 11:37:27,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. + 8: [2023-04-29 11:37:27,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. + 8: [2023-04-29 11:37:27,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. + 8: [2023-04-29 11:37:27,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +30: [2023-04-29 11:37:27,010] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +30: [2023-04-29 11:37:27,010] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +30: [2023-04-29 11:37:27,010] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +30: [2023-04-29 11:37:27,010] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +30: [2023-04-29 11:37:27,010] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +50: [2023-04-29 11:37:27,013] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +50: [2023-04-29 11:37:27,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +40: [2023-04-29 11:37:27,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +40: [2023-04-29 11:37:27,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +40: [2023-04-29 11:37:27,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +40: [2023-04-29 11:37:27,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +54: [2023-04-29 11:37:27,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +54: [2023-04-29 11:37:27,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +30: [2023-04-29 11:37:27,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +30: [2023-04-29 11:37:27,016] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +30: [2023-04-29 11:37:27,016] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +30: [2023-04-29 11:37:27,016] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +30: [2023-04-29 11:37:27,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +50: [2023-04-29 11:37:27,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +50: [2023-04-29 11:37:27,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +30: [2023-04-29 11:37:27,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +36: [2023-04-29 11:37:27,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +56: [2023-04-29 11:37:27,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +30: [2023-04-29 11:37:27,022] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +30: [2023-04-29 11:37:27,022] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +38: [2023-04-29 11:37:27,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +38: [2023-04-29 11:37:27,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +56: [2023-04-29 11:37:27,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +56: [2023-04-29 11:37:27,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +30: [2023-04-29 11:37:27,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +36: [2023-04-29 11:37:27,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +56: [2023-04-29 11:37:27,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +41: [2023-04-29 11:37:27,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +41: [2023-04-29 11:37:27,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +38: [2023-04-29 11:37:27,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +36: [2023-04-29 11:37:27,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +37: [2023-04-29 11:37:27,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +36: [2023-04-29 11:37:27,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +37: [2023-04-29 11:37:27,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +37: [2023-04-29 11:37:27,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +41: [2023-04-29 11:37:27,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +37: [2023-04-29 11:37:27,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +41: [2023-04-29 11:37:27,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +32: [2023-04-29 11:37:27,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +32: [2023-04-29 11:37:27,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +32: [2023-04-29 11:37:27,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +32: [2023-04-29 11:37:27,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +30: [2023-04-29 11:37:27,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +30: [2023-04-29 11:37:27,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +24: [2023-04-29 11:37:27,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +24: [2023-04-29 11:37:27,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +24: [2023-04-29 11:37:27,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +42: [2023-04-29 11:37:27,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +24: [2023-04-29 11:37:27,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +62: [2023-04-29 11:37:27,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +62: [2023-04-29 11:37:27,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +62: [2023-04-29 11:37:27,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +62: [2023-04-29 11:37:27,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. + 8: [2023-04-29 11:37:27,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +42: [2023-04-29 11:37:27,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +20: [2023-04-29 11:37:27,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +20: [2023-04-29 11:37:27,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +20: [2023-04-29 11:37:27,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +42: [2023-04-29 11:37:27,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +20: [2023-04-29 11:37:27,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. + 8: [2023-04-29 11:37:27,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +42: [2023-04-29 11:37:27,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +40: [2023-04-29 11:37:27,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +50: [2023-04-29 11:37:27,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +50: [2023-04-29 11:37:27,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +40: [2023-04-29 11:37:27,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +40: [2023-04-29 11:37:27,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +50: [2023-04-29 11:37:27,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 8: [2023-04-29 11:37:27,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +50: [2023-04-29 11:37:27,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +40: [2023-04-29 11:37:27,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 8: [2023-04-29 11:37:27,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +41: [2023-04-29 11:37:27,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 0: [2023-04-29 11:37:27,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 0: [2023-04-29 11:37:27,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 0: [2023-04-29 11:37:27,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 0: [2023-04-29 11:37:27,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +38: [2023-04-29 11:37:27,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +38: [2023-04-29 11:37:27,052] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +41: [2023-04-29 11:37:27,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +24: [2023-04-29 11:37:27,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +37: [2023-04-29 11:37:27,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +38: [2023-04-29 11:37:27,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +38: [2023-04-29 11:37:27,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +24: [2023-04-29 11:37:27,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +41: [2023-04-29 11:37:27,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +32: [2023-04-29 11:37:27,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +32: [2023-04-29 11:37:27,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +32: [2023-04-29 11:37:27,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. + 0: [2023-04-29 11:37:27,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 0: [2023-04-29 11:37:27,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 0: [2023-04-29 11:37:27,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +32: [2023-04-29 11:37:27,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. + 0: [2023-04-29 11:37:27,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +24: [2023-04-29 11:37:27,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +24: [2023-04-29 11:37:27,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +41: [2023-04-29 11:37:27,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +37: [2023-04-29 11:37:27,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +32: [2023-04-29 11:37:27,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 4: [2023-04-29 11:37:27,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 4: [2023-04-29 11:37:27,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 4: [2023-04-29 11:37:27,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 4: [2023-04-29 11:37:27,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +32: [2023-04-29 11:37:27,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +62: [2023-04-29 11:37:27,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +32: [2023-04-29 11:37:27,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +32: [2023-04-29 11:37:27,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +27: [2023-04-29 11:37:27,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +27: [2023-04-29 11:37:27,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +27: [2023-04-29 11:37:27,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +27: [2023-04-29 11:37:27,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +27: [2023-04-29 11:37:27,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +27: [2023-04-29 11:37:27,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +27: [2023-04-29 11:37:27,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +37: [2023-04-29 11:37:27,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +37: [2023-04-29 11:37:27,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +27: [2023-04-29 11:37:27,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +32: [2023-04-29 11:37:27,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +20: [2023-04-29 11:37:27,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +20: [2023-04-29 11:37:27,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +32: [2023-04-29 11:37:27,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +10: [2023-04-29 11:37:27,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +10: [2023-04-29 11:37:27,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +10: [2023-04-29 11:37:27,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +10: [2023-04-29 11:37:27,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +32: [2023-04-29 11:37:27,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 4: [2023-04-29 11:37:27,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 4: [2023-04-29 11:37:27,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 7: [2023-04-29 11:37:27,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 4: [2023-04-29 11:37:27,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 4: [2023-04-29 11:37:27,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +32: [2023-04-29 11:37:27,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +62: [2023-04-29 11:37:27,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +20: [2023-04-29 11:37:27,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +20: [2023-04-29 11:37:27,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +27: [2023-04-29 11:37:27,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +27: [2023-04-29 11:37:27,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +62: [2023-04-29 11:37:27,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +27: [2023-04-29 11:37:27,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +27: [2023-04-29 11:37:27,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +27: [2023-04-29 11:37:27,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +27: [2023-04-29 11:37:27,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +27: [2023-04-29 11:37:27,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +27: [2023-04-29 11:37:27,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +10: [2023-04-29 11:37:27,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +10: [2023-04-29 11:37:27,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +10: [2023-04-29 11:37:27,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +10: [2023-04-29 11:37:27,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +62: [2023-04-29 11:37:27,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +30: [2023-04-29 11:37:27,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 7: [2023-04-29 11:37:27,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +30: [2023-04-29 11:37:27,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +38: [2023-04-29 11:37:27,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +30: [2023-04-29 11:37:27,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +30: [2023-04-29 11:37:27,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +60: [2023-04-29 11:37:27,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +60: [2023-04-29 11:37:27,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +60: [2023-04-29 11:37:27,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +60: [2023-04-29 11:37:27,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +30: [2023-04-29 11:37:27,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +30: [2023-04-29 11:37:27,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +30: [2023-04-29 11:37:27,114] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +30: [2023-04-29 11:37:27,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +34: [2023-04-29 11:37:27,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +34: [2023-04-29 11:37:27,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +34: [2023-04-29 11:37:27,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +34: [2023-04-29 11:37:27,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. + 4: [2023-04-29 11:37:27,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +27: [2023-04-29 11:37:27,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +32: [2023-04-29 11:37:27,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +53: [2023-04-29 11:37:27,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +53: [2023-04-29 11:37:27,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. + 4: [2023-04-29 11:37:27,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. + 4: [2023-04-29 11:37:27,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. + 4: [2023-04-29 11:37:27,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. + 4: [2023-04-29 11:37:27,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. + 7: [2023-04-29 11:37:27,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +60: [2023-04-29 11:37:27,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +55: [2023-04-29 11:37:27,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +55: [2023-04-29 11:37:27,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +55: [2023-04-29 11:37:27,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +60: [2023-04-29 11:37:27,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +55: [2023-04-29 11:37:27,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. + 0: [2023-04-29 11:37:27,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 0: [2023-04-29 11:37:27,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +60: [2023-04-29 11:37:27,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 0: [2023-04-29 11:37:27,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +32: [2023-04-29 11:37:27,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +60: [2023-04-29 11:37:27,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +32: [2023-04-29 11:37:27,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +53: [2023-04-29 11:37:27,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +39: [2023-04-29 11:37:27,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +39: [2023-04-29 11:37:27,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +53: [2023-04-29 11:37:27,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +27: [2023-04-29 11:37:27,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 0: [2023-04-29 11:37:27,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +39: [2023-04-29 11:37:27,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +39: [2023-04-29 11:37:27,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +27: [2023-04-29 11:37:27,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +59: [2023-04-29 11:37:27,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +59: [2023-04-29 11:37:27,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +59: [2023-04-29 11:37:27,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +59: [2023-04-29 11:37:27,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +52: [2023-04-29 11:37:27,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +52: [2023-04-29 11:37:27,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +52: [2023-04-29 11:37:27,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +52: [2023-04-29 11:37:27,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +52: [2023-04-29 11:37:27,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +52: [2023-04-29 11:37:27,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +52: [2023-04-29 11:37:27,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +50: [2023-04-29 11:37:27,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +50: [2023-04-29 11:37:27,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +52: [2023-04-29 11:37:27,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +50: [2023-04-29 11:37:27,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +50: [2023-04-29 11:37:27,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +32: [2023-04-29 11:37:27,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +32: [2023-04-29 11:37:27,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +32: [2023-04-29 11:37:27,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +50: [2023-04-29 11:37:27,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +50: [2023-04-29 11:37:27,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +50: [2023-04-29 11:37:27,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +50: [2023-04-29 11:37:27,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. + 4: [2023-04-29 11:37:27,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 4: [2023-04-29 11:37:27,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 4: [2023-04-29 11:37:27,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +57: [2023-04-29 11:37:27,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +57: [2023-04-29 11:37:27,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +57: [2023-04-29 11:37:27,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +57: [2023-04-29 11:37:27,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +57: [2023-04-29 11:37:27,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +57: [2023-04-29 11:37:27,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +57: [2023-04-29 11:37:27,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +57: [2023-04-29 11:37:27,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +52: [2023-04-29 11:37:27,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +62: [2023-04-29 11:37:27,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +62: [2023-04-29 11:37:27,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +62: [2023-04-29 11:37:27,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +62: [2023-04-29 11:37:27,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +62: [2023-04-29 11:37:27,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +18: [2023-04-29 11:37:27,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +18: [2023-04-29 11:37:27,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +18: [2023-04-29 11:37:27,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +18: [2023-04-29 11:37:27,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +10: [2023-04-29 11:37:27,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +52: [2023-04-29 11:37:27,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +32: [2023-04-29 11:37:27,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +32: [2023-04-29 11:37:27,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +51: [2023-04-29 11:37:27,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +51: [2023-04-29 11:37:27,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +51: [2023-04-29 11:37:27,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +51: [2023-04-29 11:37:27,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +51: [2023-04-29 11:37:27,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +51: [2023-04-29 11:37:27,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +51: [2023-04-29 11:37:27,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +42: [2023-04-29 11:37:27,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +42: [2023-04-29 11:37:27,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +42: [2023-04-29 11:37:27,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +50: [2023-04-29 11:37:27,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +42: [2023-04-29 11:37:27,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +51: [2023-04-29 11:37:27,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +52: [2023-04-29 11:37:27,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +42: [2023-04-29 11:37:27,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +42: [2023-04-29 11:37:27,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +42: [2023-04-29 11:37:27,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +42: [2023-04-29 11:37:27,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +52: [2023-04-29 11:37:27,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 7: [2023-04-29 11:37:27,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +50: [2023-04-29 11:37:27,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +50: [2023-04-29 11:37:27,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +40: [2023-04-29 11:37:27,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +40: [2023-04-29 11:37:27,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +40: [2023-04-29 11:37:27,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +40: [2023-04-29 11:37:27,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +40: [2023-04-29 11:37:27,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +40: [2023-04-29 11:37:27,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +40: [2023-04-29 11:37:27,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +40: [2023-04-29 11:37:27,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +57: [2023-04-29 11:37:27,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +10: [2023-04-29 11:37:27,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +10: [2023-04-29 11:37:27,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +10: [2023-04-29 11:37:27,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +28: [2023-04-29 11:37:27,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +28: [2023-04-29 11:37:27,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +32: [2023-04-29 11:37:27,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +57: [2023-04-29 11:37:27,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +57: [2023-04-29 11:37:27,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +62: [2023-04-29 11:37:27,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +27: [2023-04-29 11:37:27,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +25: [2023-04-29 11:37:27,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +25: [2023-04-29 11:37:27,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +57: [2023-04-29 11:37:27,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +32: [2023-04-29 11:37:27,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +57: [2023-04-29 11:37:27,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +42: [2023-04-29 11:37:27,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +62: [2023-04-29 11:37:27,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +57: [2023-04-29 11:37:27,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +57: [2023-04-29 11:37:27,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +62: [2023-04-29 11:37:27,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +57: [2023-04-29 11:37:27,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +52: [2023-04-29 11:37:27,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +51: [2023-04-29 11:37:27,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +51: [2023-04-29 11:37:27,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +62: [2023-04-29 11:37:27,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +52: [2023-04-29 11:37:27,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +50: [2023-04-29 11:37:27,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +40: [2023-04-29 11:37:27,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +52: [2023-04-29 11:37:27,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +25: [2023-04-29 11:37:27,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +62: [2023-04-29 11:37:27,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +52: [2023-04-29 11:37:27,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +42: [2023-04-29 11:37:27,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +42: [2023-04-29 11:37:27,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +21: [2023-04-29 11:37:27,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +21: [2023-04-29 11:37:27,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +21: [2023-04-29 11:37:27,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +50: [2023-04-29 11:37:27,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +21: [2023-04-29 11:37:27,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +40: [2023-04-29 11:37:27,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +40: [2023-04-29 11:37:27,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +42: [2023-04-29 11:37:27,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +50: [2023-04-29 11:37:27,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +25: [2023-04-29 11:37:27,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +62: [2023-04-29 11:37:27,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +50: [2023-04-29 11:37:27,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +28: [2023-04-29 11:37:27,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +32: [2023-04-29 11:37:27,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +40: [2023-04-29 11:37:27,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +28: [2023-04-29 11:37:27,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +46: [2023-04-29 11:37:27,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +46: [2023-04-29 11:37:27,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +34: [2023-04-29 11:37:27,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +46: [2023-04-29 11:37:27,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +34: [2023-04-29 11:37:27,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +27: [2023-04-29 11:37:27,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +51: [2023-04-29 11:37:27,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +50: [2023-04-29 11:37:27,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +46: [2023-04-29 11:37:27,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +32: [2023-04-29 11:37:27,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +40: [2023-04-29 11:37:27,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +40: [2023-04-29 11:37:27,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +40: [2023-04-29 11:37:27,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +40: [2023-04-29 11:37:27,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +35: [2023-04-29 11:37:27,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +35: [2023-04-29 11:37:27,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +42: [2023-04-29 11:37:27,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +42: [2023-04-29 11:37:27,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +42: [2023-04-29 11:37:27,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +21: [2023-04-29 11:37:27,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 4: [2023-04-29 11:37:27,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +21: [2023-04-29 11:37:27,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +51: [2023-04-29 11:37:27,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +51: [2023-04-29 11:37:27,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +42: [2023-04-29 11:37:27,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 4: [2023-04-29 11:37:27,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +51: [2023-04-29 11:37:27,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +34: [2023-04-29 11:37:27,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +34: [2023-04-29 11:37:27,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +51: [2023-04-29 11:37:27,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +51: [2023-04-29 11:37:27,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +21: [2023-04-29 11:37:27,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +13: [2023-04-29 11:37:27,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +13: [2023-04-29 11:37:27,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +13: [2023-04-29 11:37:27,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +55: [2023-04-29 11:37:27,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +21: [2023-04-29 11:37:27,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +13: [2023-04-29 11:37:27,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +35: [2023-04-29 11:37:27,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +35: [2023-04-29 11:37:27,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +35: [2023-04-29 11:37:27,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +35: [2023-04-29 11:37:27,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +35: [2023-04-29 11:37:27,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +35: [2023-04-29 11:37:27,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +10: [2023-04-29 11:37:27,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +10: [2023-04-29 11:37:27,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +62: [2023-04-29 11:37:27,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... + 4: [2023-04-29 11:37:27,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +55: [2023-04-29 11:37:27,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +62: [2023-04-29 11:37:27,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +10: [2023-04-29 11:37:27,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +43: [2023-04-29 11:37:27,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +43: [2023-04-29 11:37:27,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +43: [2023-04-29 11:37:27,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +33: [2023-04-29 11:37:27,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +33: [2023-04-29 11:37:27,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +43: [2023-04-29 11:37:27,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +20: [2023-04-29 11:37:27,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +20: [2023-04-29 11:37:27,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +20: [2023-04-29 11:37:27,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +20: [2023-04-29 11:37:27,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 0: [2023-04-29 11:37:27,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +20: [2023-04-29 11:37:27,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +20: [2023-04-29 11:37:27,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +20: [2023-04-29 11:37:27,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +62: [2023-04-29 11:37:27,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +20: [2023-04-29 11:37:27,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +10: [2023-04-29 11:37:27,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +59: [2023-04-29 11:37:27,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +35: [2023-04-29 11:37:27,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +53: [2023-04-29 11:37:27,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +53: [2023-04-29 11:37:27,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +55: [2023-04-29 11:37:27,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +35: [2023-04-29 11:37:27,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +55: [2023-04-29 11:37:27,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +61: [2023-04-29 11:37:27,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +61: [2023-04-29 11:37:27,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +61: [2023-04-29 11:37:27,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. +27: [2023-04-29 11:37:27,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +59: [2023-04-29 11:37:27,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +35: [2023-04-29 11:37:27,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +33: [2023-04-29 11:37:27,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. + 0: [2023-04-29 11:37:27,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +61: [2023-04-29 11:37:27,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_28-model_01-model_states.pt. + 8: [2023-04-29 11:37:27,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +33: [2023-04-29 11:37:27,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +53: [2023-04-29 11:37:27,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 8: [2023-04-29 11:37:27,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 8: [2023-04-29 11:37:27,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 8: [2023-04-29 11:37:27,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +35: [2023-04-29 11:37:27,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +35: [2023-04-29 11:37:27,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... + 8: [2023-04-29 11:37:27,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 8: [2023-04-29 11:37:27,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 8: [2023-04-29 11:37:27,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 0: [2023-04-29 11:37:27,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 8: [2023-04-29 11:37:27,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +59: [2023-04-29 11:37:27,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +39: [2023-04-29 11:37:27,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +39: [2023-04-29 11:37:27,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +35: [2023-04-29 11:37:27,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +53: [2023-04-29 11:37:27,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +39: [2023-04-29 11:37:27,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 0: [2023-04-29 11:37:27,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +20: [2023-04-29 11:37:27,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +59: [2023-04-29 11:37:27,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +18: [2023-04-29 11:37:27,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +27: [2023-04-29 11:37:27,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 4: [2023-04-29 11:37:27,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +32: [2023-04-29 11:37:27,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +18: [2023-04-29 11:37:27,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +35: [2023-04-29 11:37:27,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +35: [2023-04-29 11:37:27,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +18: [2023-04-29 11:37:27,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +48: [2023-04-29 11:37:27,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +48: [2023-04-29 11:37:27,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +20: [2023-04-29 11:37:27,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +20: [2023-04-29 11:37:27,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +62: [2023-04-29 11:37:27,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +62: [2023-04-29 11:37:27,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +20: [2023-04-29 11:37:27,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +20: [2023-04-29 11:37:27,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +20: [2023-04-29 11:37:27,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +20: [2023-04-29 11:37:27,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +18: [2023-04-29 11:37:27,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 8: [2023-04-29 11:37:27,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +39: [2023-04-29 11:37:27,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 8: [2023-04-29 11:37:27,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 4: [2023-04-29 11:37:27,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +20: [2023-04-29 11:37:27,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... + 8: [2023-04-29 11:37:27,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +18: [2023-04-29 11:37:27,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +18: [2023-04-29 11:37:27,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +18: [2023-04-29 11:37:27,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +32: [2023-04-29 11:37:27,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +48: [2023-04-29 11:37:27,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +48: [2023-04-29 11:37:27,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +27: [2023-04-29 11:37:27,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 8: [2023-04-29 11:37:27,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +48: [2023-04-29 11:37:27,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +48: [2023-04-29 11:37:27,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +48: [2023-04-29 11:37:27,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +32: [2023-04-29 11:37:27,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +48: [2023-04-29 11:37:27,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +18: [2023-04-29 11:37:27,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 8: [2023-04-29 11:37:27,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... + 8: [2023-04-29 11:37:27,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +10: [2023-04-29 11:37:27,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 8: [2023-04-29 11:37:27,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +25: [2023-04-29 11:37:27,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 8: [2023-04-29 11:37:27,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +18: [2023-04-29 11:37:27,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +25: [2023-04-29 11:37:27,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +48: [2023-04-29 11:37:27,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. + 7: [2023-04-29 11:37:27,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +18: [2023-04-29 11:37:27,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +28: [2023-04-29 11:37:27,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +28: [2023-04-29 11:37:27,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +48: [2023-04-29 11:37:27,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. + 4: [2023-04-29 11:37:27,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 4: [2023-04-29 11:37:27,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 4: [2023-04-29 11:37:27,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +46: [2023-04-29 11:37:27,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +28: [2023-04-29 11:37:27,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +18: [2023-04-29 11:37:27,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +10: [2023-04-29 11:37:27,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +46: [2023-04-29 11:37:27,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +46: [2023-04-29 11:37:27,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +46: [2023-04-29 11:37:27,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +48: [2023-04-29 11:37:27,175] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +25: [2023-04-29 11:37:27,175] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +18: [2023-04-29 11:37:27,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +46: [2023-04-29 11:37:27,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +46: [2023-04-29 11:37:27,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +10: [2023-04-29 11:37:27,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +48: [2023-04-29 11:37:27,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +10: [2023-04-29 11:37:27,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +25: [2023-04-29 11:37:27,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +46: [2023-04-29 11:37:27,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +46: [2023-04-29 11:37:27,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +28: [2023-04-29 11:37:27,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 6: [2023-04-29 11:37:27,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 6: [2023-04-29 11:37:27,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 6: [2023-04-29 11:37:27,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +46: [2023-04-29 11:37:27,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 6: [2023-04-29 11:37:27,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +46: [2023-04-29 11:37:27,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +43: [2023-04-29 11:37:27,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +43: [2023-04-29 11:37:27,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +32: [2023-04-29 11:37:27,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +46: [2023-04-29 11:37:27,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +43: [2023-04-29 11:37:27,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +46: [2023-04-29 11:37:27,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +13: [2023-04-29 11:37:27,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +33: [2023-04-29 11:37:27,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +13: [2023-04-29 11:37:27,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +10: [2023-04-29 11:37:27,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +43: [2023-04-29 11:37:27,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +13: [2023-04-29 11:37:27,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +13: [2023-04-29 11:37:27,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 6: [2023-04-29 11:37:27,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +61: [2023-04-29 11:37:27,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 6: [2023-04-29 11:37:27,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +10: [2023-04-29 11:37:27,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 6: [2023-04-29 11:37:27,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 6: [2023-04-29 11:37:27,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +61: [2023-04-29 11:37:27,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +61: [2023-04-29 11:37:27,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +61: [2023-04-29 11:37:27,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +10: [2023-04-29 11:37:27,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +33: [2023-04-29 11:37:27,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +52: [2023-04-29 11:37:27,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +10: [2023-04-29 11:37:27,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +33: [2023-04-29 11:37:27,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +33: [2023-04-29 11:37:27,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +57: [2023-04-29 11:37:27,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +15: [2023-04-29 11:37:27,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +15: [2023-04-29 11:37:27,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +15: [2023-04-29 11:37:27,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +15: [2023-04-29 11:37:27,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +48: [2023-04-29 11:37:27,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +62: [2023-04-29 11:37:27,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +15: [2023-04-29 11:37:27,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +15: [2023-04-29 11:37:27,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +48: [2023-04-29 11:37:27,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +15: [2023-04-29 11:37:27,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +15: [2023-04-29 11:37:27,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +50: [2023-04-29 11:37:27,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +48: [2023-04-29 11:37:27,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +48: [2023-04-29 11:37:27,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +40: [2023-04-29 11:37:27,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +62: [2023-04-29 11:37:27,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +52: [2023-04-29 11:37:27,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +52: [2023-04-29 11:37:27,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +54: [2023-04-29 11:37:27,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +57: [2023-04-29 11:37:27,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +54: [2023-04-29 11:37:27,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +54: [2023-04-29 11:37:27,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +17: [2023-04-29 11:37:27,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +17: [2023-04-29 11:37:27,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +17: [2023-04-29 11:37:27,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +54: [2023-04-29 11:37:27,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +25: [2023-04-29 11:37:27,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +25: [2023-04-29 11:37:27,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +17: [2023-04-29 11:37:27,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +49: [2023-04-29 11:37:27,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +49: [2023-04-29 11:37:27,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +49: [2023-04-29 11:37:27,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +25: [2023-04-29 11:37:27,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +25: [2023-04-29 11:37:27,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +49: [2023-04-29 11:37:27,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +49: [2023-04-29 11:37:27,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +49: [2023-04-29 11:37:27,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +49: [2023-04-29 11:37:27,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +49: [2023-04-29 11:37:27,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +57: [2023-04-29 11:37:27,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +52: [2023-04-29 11:37:27,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +57: [2023-04-29 11:37:27,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +51: [2023-04-29 11:37:27,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +21: [2023-04-29 11:37:27,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +52: [2023-04-29 11:37:27,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +62: [2023-04-29 11:37:27,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +42: [2023-04-29 11:37:27,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +42: [2023-04-29 11:37:27,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +42: [2023-04-29 11:37:27,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +21: [2023-04-29 11:37:27,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +49: [2023-04-29 11:37:27,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +25: [2023-04-29 11:37:27,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +25: [2023-04-29 11:37:27,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +49: [2023-04-29 11:37:27,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +44: [2023-04-29 11:37:27,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +44: [2023-04-29 11:37:27,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +44: [2023-04-29 11:37:27,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +44: [2023-04-29 11:37:27,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +44: [2023-04-29 11:37:27,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +44: [2023-04-29 11:37:27,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +44: [2023-04-29 11:37:27,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +44: [2023-04-29 11:37:27,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +49: [2023-04-29 11:37:27,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +25: [2023-04-29 11:37:27,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +42: [2023-04-29 11:37:27,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +35: [2023-04-29 11:37:27,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +49: [2023-04-29 11:37:27,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +25: [2023-04-29 11:37:27,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +49: [2023-04-29 11:37:27,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... + 9: [2023-04-29 11:37:27,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. + 9: [2023-04-29 11:37:27,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. + 9: [2023-04-29 11:37:27,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +49: [2023-04-29 11:37:27,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 9: [2023-04-29 11:37:27,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +49: [2023-04-29 11:37:27,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +49: [2023-04-29 11:37:27,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +50: [2023-04-29 11:37:27,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. + 4: [2023-04-29 11:37:27,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +40: [2023-04-29 11:37:27,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +40: [2023-04-29 11:37:27,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +40: [2023-04-29 11:37:27,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. + 4: [2023-04-29 11:37:27,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +50: [2023-04-29 11:37:27,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +57: [2023-04-29 11:37:27,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +44: [2023-04-29 11:37:27,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +44: [2023-04-29 11:37:27,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +44: [2023-04-29 11:37:27,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +44: [2023-04-29 11:37:27,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +44: [2023-04-29 11:37:27,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +50: [2023-04-29 11:37:27,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +44: [2023-04-29 11:37:27,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +44: [2023-04-29 11:37:27,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +35: [2023-04-29 11:37:27,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +44: [2023-04-29 11:37:27,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +20: [2023-04-29 11:37:27,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 4: [2023-04-29 11:37:27,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +62: [2023-04-29 11:37:27,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +51: [2023-04-29 11:37:27,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. + 4: [2023-04-29 11:37:27,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +62: [2023-04-29 11:37:27,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +41: [2023-04-29 11:37:27,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +41: [2023-04-29 11:37:27,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. + 8: [2023-04-29 11:37:27,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 0: [2023-04-29 11:37:27,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. + 0: [2023-04-29 11:37:27,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. + 0: [2023-04-29 11:37:27,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. + 0: [2023-04-29 11:37:27,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +59: [2023-04-29 11:37:27,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +59: [2023-04-29 11:37:27,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +50: [2023-04-29 11:37:27,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +58: [2023-04-29 11:37:27,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +58: [2023-04-29 11:37:27,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +58: [2023-04-29 11:37:27,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +58: [2023-04-29 11:37:27,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +58: [2023-04-29 11:37:27,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +58: [2023-04-29 11:37:27,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +58: [2023-04-29 11:37:27,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +58: [2023-04-29 11:37:27,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +40: [2023-04-29 11:37:27,229] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 8: [2023-04-29 11:37:27,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +41: [2023-04-29 11:37:27,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +20: [2023-04-29 11:37:27,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 7: [2023-04-29 11:37:27,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. + 7: [2023-04-29 11:37:27,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +41: [2023-04-29 11:37:27,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +41: [2023-04-29 11:37:27,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +41: [2023-04-29 11:37:27,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +41: [2023-04-29 11:37:27,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +59: [2023-04-29 11:37:27,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +59: [2023-04-29 11:37:27,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +59: [2023-04-29 11:37:27,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +59: [2023-04-29 11:37:27,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +59: [2023-04-29 11:37:27,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +41: [2023-04-29 11:37:27,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +11: [2023-04-29 11:37:27,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +11: [2023-04-29 11:37:27,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +11: [2023-04-29 11:37:27,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 3: [2023-04-29 11:37:27,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +59: [2023-04-29 11:37:27,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. + 3: [2023-04-29 11:37:27,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 3: [2023-04-29 11:37:27,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +11: [2023-04-29 11:37:27,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 3: [2023-04-29 11:37:27,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +51: [2023-04-29 11:37:27,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +41: [2023-04-29 11:37:27,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +59: [2023-04-29 11:37:27,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +21: [2023-04-29 11:37:27,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +41: [2023-04-29 11:37:27,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... + 7: [2023-04-29 11:37:27,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +59: [2023-04-29 11:37:27,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... + 7: [2023-04-29 11:37:27,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +18: [2023-04-29 11:37:27,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +18: [2023-04-29 11:37:27,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +59: [2023-04-29 11:37:27,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +60: [2023-04-29 11:37:27,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +60: [2023-04-29 11:37:27,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +41: [2023-04-29 11:37:27,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +52: [2023-04-29 11:37:27,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +46: [2023-04-29 11:37:27,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 2: [2023-04-29 11:37:27,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +20: [2023-04-29 11:37:27,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +59: [2023-04-29 11:37:27,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... + 2: [2023-04-29 11:37:27,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. + 2: [2023-04-29 11:37:27,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +59: [2023-04-29 11:37:27,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 2: [2023-04-29 11:37:27,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +25: [2023-04-29 11:37:27,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +58: [2023-04-29 11:37:27,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +58: [2023-04-29 11:37:27,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +58: [2023-04-29 11:37:27,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 3: [2023-04-29 11:37:27,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +54: [2023-04-29 11:37:27,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 3: [2023-04-29 11:37:27,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +62: [2023-04-29 11:37:27,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +58: [2023-04-29 11:37:27,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +58: [2023-04-29 11:37:27,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +58: [2023-04-29 11:37:27,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +46: [2023-04-29 11:37:27,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +20: [2023-04-29 11:37:27,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +58: [2023-04-29 11:37:27,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +58: [2023-04-29 11:37:27,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +60: [2023-04-29 11:37:27,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +60: [2023-04-29 11:37:27,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +60: [2023-04-29 11:37:27,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +60: [2023-04-29 11:37:27,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +59: [2023-04-29 11:37:27,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +60: [2023-04-29 11:37:27,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +54: [2023-04-29 11:37:27,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +60: [2023-04-29 11:37:27,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +59: [2023-04-29 11:37:27,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +11: [2023-04-29 11:37:27,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +11: [2023-04-29 11:37:27,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +11: [2023-04-29 11:37:27,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +52: [2023-04-29 11:37:27,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +51: [2023-04-29 11:37:27,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. + 3: [2023-04-29 11:37:27,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +14: [2023-04-29 11:37:27,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +14: [2023-04-29 11:37:27,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +11: [2023-04-29 11:37:27,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +14: [2023-04-29 11:37:27,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +57: [2023-04-29 11:37:27,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +57: [2023-04-29 11:37:27,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +57: [2023-04-29 11:37:27,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 4: [2023-04-29 11:37:27,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 4: [2023-04-29 11:37:27,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +14: [2023-04-29 11:37:27,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +41: [2023-04-29 11:37:27,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... + 3: [2023-04-29 11:37:27,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +21: [2023-04-29 11:37:27,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +17: [2023-04-29 11:37:27,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +59: [2023-04-29 11:37:27,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +18: [2023-04-29 11:37:27,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +60: [2023-04-29 11:37:27,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +46: [2023-04-29 11:37:27,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +18: [2023-04-29 11:37:27,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +46: [2023-04-29 11:37:27,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +54: [2023-04-29 11:37:27,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +25: [2023-04-29 11:37:27,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +21: [2023-04-29 11:37:27,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +41: [2023-04-29 11:37:27,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +54: [2023-04-29 11:37:27,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +17: [2023-04-29 11:37:27,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +60: [2023-04-29 11:37:27,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +62: [2023-04-29 11:37:27,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +52: [2023-04-29 11:37:27,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +17: [2023-04-29 11:37:27,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +41: [2023-04-29 11:37:27,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +35: [2023-04-29 11:37:27,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +35: [2023-04-29 11:37:27,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +60: [2023-04-29 11:37:27,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +21: [2023-04-29 11:37:27,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +17: [2023-04-29 11:37:27,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +60: [2023-04-29 11:37:27,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +41: [2023-04-29 11:37:27,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... + 8: [2023-04-29 11:37:27,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +42: [2023-04-29 11:37:27,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 8: [2023-04-29 11:37:27,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +21: [2023-04-29 11:37:27,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +21: [2023-04-29 11:37:27,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +60: [2023-04-29 11:37:27,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +18: [2023-04-29 11:37:27,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +51: [2023-04-29 11:37:27,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +48: [2023-04-29 11:37:27,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +41: [2023-04-29 11:37:27,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +60: [2023-04-29 11:37:27,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +10: [2023-04-29 11:37:27,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +14: [2023-04-29 11:37:27,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +14: [2023-04-29 11:37:27,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +42: [2023-04-29 11:37:27,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +60: [2023-04-29 11:37:27,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 9: [2023-04-29 11:37:27,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +60: [2023-04-29 11:37:27,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... + 4: [2023-04-29 11:37:27,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... + 4: [2023-04-29 11:37:27,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +33: [2023-04-29 11:37:27,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +33: [2023-04-29 11:37:27,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +25: [2023-04-29 11:37:27,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +14: [2023-04-29 11:37:27,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +42: [2023-04-29 11:37:27,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 6: [2023-04-29 11:37:27,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. + 6: [2023-04-29 11:37:27,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. + 9: [2023-04-29 11:37:27,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +14: [2023-04-29 11:37:27,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +20: [2023-04-29 11:37:27,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 9: [2023-04-29 11:37:27,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +42: [2023-04-29 11:37:27,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 6: [2023-04-29 11:37:27,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. + 9: [2023-04-29 11:37:27,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +35: [2023-04-29 11:37:27,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +46: [2023-04-29 11:37:27,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +36: [2023-04-29 11:37:27,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +36: [2023-04-29 11:37:27,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +33: [2023-04-29 11:37:27,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +33: [2023-04-29 11:37:27,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 6: [2023-04-29 11:37:27,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +46: [2023-04-29 11:37:27,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +33: [2023-04-29 11:37:27,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +35: [2023-04-29 11:37:27,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +25: [2023-04-29 11:37:27,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +47: [2023-04-29 11:37:27,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +47: [2023-04-29 11:37:27,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +47: [2023-04-29 11:37:27,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +10: [2023-04-29 11:37:27,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +36: [2023-04-29 11:37:27,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +47: [2023-04-29 11:37:27,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +36: [2023-04-29 11:37:27,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +36: [2023-04-29 11:37:27,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +36: [2023-04-29 11:37:27,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +36: [2023-04-29 11:37:27,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +38: [2023-04-29 11:37:27,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +38: [2023-04-29 11:37:27,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +38: [2023-04-29 11:37:27,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +38: [2023-04-29 11:37:27,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +38: [2023-04-29 11:37:27,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +36: [2023-04-29 11:37:27,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +47: [2023-04-29 11:37:27,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +47: [2023-04-29 11:37:27,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +47: [2023-04-29 11:37:27,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +38: [2023-04-29 11:37:27,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +38: [2023-04-29 11:37:27,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +47: [2023-04-29 11:37:27,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +38: [2023-04-29 11:37:27,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +45: [2023-04-29 11:37:27,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +45: [2023-04-29 11:37:27,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +40: [2023-04-29 11:37:27,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +29: [2023-04-29 11:37:27,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +29: [2023-04-29 11:37:27,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +45: [2023-04-29 11:37:27,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +29: [2023-04-29 11:37:27,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +45: [2023-04-29 11:37:27,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +45: [2023-04-29 11:37:27,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +45: [2023-04-29 11:37:27,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +45: [2023-04-29 11:37:27,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +33: [2023-04-29 11:37:27,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +48: [2023-04-29 11:37:27,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +48: [2023-04-29 11:37:27,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +29: [2023-04-29 11:37:27,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +45: [2023-04-29 11:37:27,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. + 6: [2023-04-29 11:37:27,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 6: [2023-04-29 11:37:27,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +33: [2023-04-29 11:37:27,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +25: [2023-04-29 11:37:27,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +33: [2023-04-29 11:37:27,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +53: [2023-04-29 11:37:27,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +53: [2023-04-29 11:37:27,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +53: [2023-04-29 11:37:27,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +53: [2023-04-29 11:37:27,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +36: [2023-04-29 11:37:27,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 8: [2023-04-29 11:37:27,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +53: [2023-04-29 11:37:27,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +53: [2023-04-29 11:37:27,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +53: [2023-04-29 11:37:27,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +53: [2023-04-29 11:37:27,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +46: [2023-04-29 11:37:27,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +21: [2023-04-29 11:37:27,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +25: [2023-04-29 11:37:27,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +21: [2023-04-29 11:37:27,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +40: [2023-04-29 11:37:27,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +40: [2023-04-29 11:37:27,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +12: [2023-04-29 11:37:27,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +12: [2023-04-29 11:37:27,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +33: [2023-04-29 11:37:27,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +36: [2023-04-29 11:37:27,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +11: [2023-04-29 11:37:27,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +11: [2023-04-29 11:37:27,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +33: [2023-04-29 11:37:27,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +12: [2023-04-29 11:37:27,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +12: [2023-04-29 11:37:27,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +18: [2023-04-29 11:37:27,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +25: [2023-04-29 11:37:27,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... + 6: [2023-04-29 11:37:27,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 6: [2023-04-29 11:37:27,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +47: [2023-04-29 11:37:27,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... + 8: [2023-04-29 11:37:27,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +38: [2023-04-29 11:37:27,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 0: [2023-04-29 11:37:27,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +47: [2023-04-29 11:37:27,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +36: [2023-04-29 11:37:27,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +36: [2023-04-29 11:37:27,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... + 0: [2023-04-29 11:37:27,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +18: [2023-04-29 11:37:27,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +18: [2023-04-29 11:37:27,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 0: [2023-04-29 11:37:27,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +18: [2023-04-29 11:37:27,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +18: [2023-04-29 11:37:27,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +29: [2023-04-29 11:37:27,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +47: [2023-04-29 11:37:27,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +11: [2023-04-29 11:37:27,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +62: [2023-04-29 11:37:27,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +53: [2023-04-29 11:37:27,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +20: [2023-04-29 11:37:27,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +11: [2023-04-29 11:37:27,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +10: [2023-04-29 11:37:27,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +46: [2023-04-29 11:37:27,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +10: [2023-04-29 11:37:27,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +45: [2023-04-29 11:37:27,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +45: [2023-04-29 11:37:27,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +45: [2023-04-29 11:37:27,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +18: [2023-04-29 11:37:27,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +29: [2023-04-29 11:37:27,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +45: [2023-04-29 11:37:27,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +47: [2023-04-29 11:37:27,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +45: [2023-04-29 11:37:27,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +38: [2023-04-29 11:37:27,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +47: [2023-04-29 11:37:27,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +29: [2023-04-29 11:37:27,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +45: [2023-04-29 11:37:27,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +50: [2023-04-29 11:37:27,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +38: [2023-04-29 11:37:27,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +38: [2023-04-29 11:37:27,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +47: [2023-04-29 11:37:27,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +29: [2023-04-29 11:37:27,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +47: [2023-04-29 11:37:27,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... + 7: [2023-04-29 11:37:27,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +45: [2023-04-29 11:37:27,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +47: [2023-04-29 11:37:27,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +38: [2023-04-29 11:37:27,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +50: [2023-04-29 11:37:27,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +36: [2023-04-29 11:37:27,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +45: [2023-04-29 11:37:27,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +53: [2023-04-29 11:37:27,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 0: [2023-04-29 11:37:27,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +38: [2023-04-29 11:37:27,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +55: [2023-04-29 11:37:27,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +53: [2023-04-29 11:37:27,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +53: [2023-04-29 11:37:27,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +38: [2023-04-29 11:37:27,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +53: [2023-04-29 11:37:27,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +55: [2023-04-29 11:37:27,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +36: [2023-04-29 11:37:27,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +53: [2023-04-29 11:37:27,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +36: [2023-04-29 11:37:27,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +25: [2023-04-29 11:37:27,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +38: [2023-04-29 11:37:27,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +53: [2023-04-29 11:37:27,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +36: [2023-04-29 11:37:27,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +53: [2023-04-29 11:37:27,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +50: [2023-04-29 11:37:27,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +10: [2023-04-29 11:37:27,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +31: [2023-04-29 11:37:27,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +31: [2023-04-29 11:37:27,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +31: [2023-04-29 11:37:27,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +10: [2023-04-29 11:37:27,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +55: [2023-04-29 11:37:27,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +55: [2023-04-29 11:37:27,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +55: [2023-04-29 11:37:27,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +10: [2023-04-29 11:37:27,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +55: [2023-04-29 11:37:27,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +55: [2023-04-29 11:37:27,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +55: [2023-04-29 11:37:27,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. + 2: [2023-04-29 11:37:27,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +31: [2023-04-29 11:37:27,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +21: [2023-04-29 11:37:27,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +20: [2023-04-29 11:37:27,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 2: [2023-04-29 11:37:27,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +46: [2023-04-29 11:37:27,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +46: [2023-04-29 11:37:27,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +14: [2023-04-29 11:37:27,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +14: [2023-04-29 11:37:27,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +46: [2023-04-29 11:37:27,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +15: [2023-04-29 11:37:27,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +51: [2023-04-29 11:37:27,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +18: [2023-04-29 11:37:27,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +20: [2023-04-29 11:37:27,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +31: [2023-04-29 11:37:27,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +18: [2023-04-29 11:37:27,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... + 2: [2023-04-29 11:37:27,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 2: [2023-04-29 11:37:27,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +15: [2023-04-29 11:37:27,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +15: [2023-04-29 11:37:27,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +15: [2023-04-29 11:37:27,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +55: [2023-04-29 11:37:27,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +15: [2023-04-29 11:37:27,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +33: [2023-04-29 11:37:27,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +26: [2023-04-29 11:37:27,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +26: [2023-04-29 11:37:27,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +55: [2023-04-29 11:37:27,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +10: [2023-04-29 11:37:27,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +14: [2023-04-29 11:37:27,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +55: [2023-04-29 11:37:27,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +14: [2023-04-29 11:37:27,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +48: [2023-04-29 11:37:27,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +31: [2023-04-29 11:37:27,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +31: [2023-04-29 11:37:27,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +55: [2023-04-29 11:37:27,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +31: [2023-04-29 11:37:27,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +55: [2023-04-29 11:37:27,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +26: [2023-04-29 11:37:27,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +26: [2023-04-29 11:37:27,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +21: [2023-04-29 11:37:27,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +33: [2023-04-29 11:37:27,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +55: [2023-04-29 11:37:27,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +61: [2023-04-29 11:37:27,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +61: [2023-04-29 11:37:27,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +61: [2023-04-29 11:37:27,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +61: [2023-04-29 11:37:27,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +61: [2023-04-29 11:37:27,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +61: [2023-04-29 11:37:27,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +21: [2023-04-29 11:37:27,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +61: [2023-04-29 11:37:27,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +55: [2023-04-29 11:37:27,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +48: [2023-04-29 11:37:27,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +48: [2023-04-29 11:37:27,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +61: [2023-04-29 11:37:27,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +55: [2023-04-29 11:37:27,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... + 8: [2023-04-29 11:37:27,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +21: [2023-04-29 11:37:27,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +46: [2023-04-29 11:37:27,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +15: [2023-04-29 11:37:27,272] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +15: [2023-04-29 11:37:27,272] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +15: [2023-04-29 11:37:27,272] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +33: [2023-04-29 11:37:27,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +35: [2023-04-29 11:37:27,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +35: [2023-04-29 11:37:27,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +51: [2023-04-29 11:37:27,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 8: [2023-04-29 11:37:27,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +33: [2023-04-29 11:37:27,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +51: [2023-04-29 11:37:27,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +46: [2023-04-29 11:37:27,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +61: [2023-04-29 11:37:27,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... + 6: [2023-04-29 11:37:27,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +61: [2023-04-29 11:37:27,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +61: [2023-04-29 11:37:27,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +48: [2023-04-29 11:37:27,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... + 6: [2023-04-29 11:37:27,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +61: [2023-04-29 11:37:27,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +25: [2023-04-29 11:37:27,278] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +61: [2023-04-29 11:37:27,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +61: [2023-04-29 11:37:27,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +12: [2023-04-29 11:37:27,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +61: [2023-04-29 11:37:27,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +33: [2023-04-29 11:37:27,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +16: [2023-04-29 11:37:27,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +16: [2023-04-29 11:37:27,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +61: [2023-04-29 11:37:27,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +16: [2023-04-29 11:37:27,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +16: [2023-04-29 11:37:27,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +46: [2023-04-29 11:37:27,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 6: [2023-04-29 11:37:27,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +33: [2023-04-29 11:37:27,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +37: [2023-04-29 11:37:27,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +37: [2023-04-29 11:37:27,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +48: [2023-04-29 11:37:27,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 6: [2023-04-29 11:37:27,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +12: [2023-04-29 11:37:27,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +37: [2023-04-29 11:37:27,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +37: [2023-04-29 11:37:27,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +37: [2023-04-29 11:37:27,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +37: [2023-04-29 11:37:27,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +37: [2023-04-29 11:37:27,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +12: [2023-04-29 11:37:27,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +37: [2023-04-29 11:37:27,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +12: [2023-04-29 11:37:27,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +11: [2023-04-29 11:37:27,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +11: [2023-04-29 11:37:27,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +25: [2023-04-29 11:37:27,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +48: [2023-04-29 11:37:27,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +49: [2023-04-29 11:37:27,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 6: [2023-04-29 11:37:27,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 6: [2023-04-29 11:37:27,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 6: [2023-04-29 11:37:27,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 6: [2023-04-29 11:37:27,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +37: [2023-04-29 11:37:27,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +37: [2023-04-29 11:37:27,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +11: [2023-04-29 11:37:27,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +25: [2023-04-29 11:37:27,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +11: [2023-04-29 11:37:27,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +23: [2023-04-29 11:37:27,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +23: [2023-04-29 11:37:27,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +44: [2023-04-29 11:37:27,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +48: [2023-04-29 11:37:27,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +18: [2023-04-29 11:37:27,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +25: [2023-04-29 11:37:27,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +59: [2023-04-29 11:37:27,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +37: [2023-04-29 11:37:27,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +21: [2023-04-29 11:37:27,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +21: [2023-04-29 11:37:27,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +44: [2023-04-29 11:37:27,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +37: [2023-04-29 11:37:27,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +37: [2023-04-29 11:37:27,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +18: [2023-04-29 11:37:27,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +18: [2023-04-29 11:37:27,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +37: [2023-04-29 11:37:27,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +23: [2023-04-29 11:37:27,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +23: [2023-04-29 11:37:27,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +37: [2023-04-29 11:37:27,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +37: [2023-04-29 11:37:27,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +48: [2023-04-29 11:37:27,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +44: [2023-04-29 11:37:27,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +48: [2023-04-29 11:37:27,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +49: [2023-04-29 11:37:27,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +49: [2023-04-29 11:37:27,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +49: [2023-04-29 11:37:27,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +44: [2023-04-29 11:37:27,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +28: [2023-04-29 11:37:27,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +28: [2023-04-29 11:37:27,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +28: [2023-04-29 11:37:27,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +28: [2023-04-29 11:37:27,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +28: [2023-04-29 11:37:27,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +28: [2023-04-29 11:37:27,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +28: [2023-04-29 11:37:27,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +28: [2023-04-29 11:37:27,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +14: [2023-04-29 11:37:27,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 3: [2023-04-29 11:37:27,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +26: [2023-04-29 11:37:27,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +48: [2023-04-29 11:37:27,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +14: [2023-04-29 11:37:27,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +46: [2023-04-29 11:37:27,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +46: [2023-04-29 11:37:27,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +15: [2023-04-29 11:37:27,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +14: [2023-04-29 11:37:27,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +14: [2023-04-29 11:37:27,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +26: [2023-04-29 11:37:27,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +48: [2023-04-29 11:37:27,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +26: [2023-04-29 11:37:27,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +26: [2023-04-29 11:37:27,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 3: [2023-04-29 11:37:27,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 3: [2023-04-29 11:37:27,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +28: [2023-04-29 11:37:27,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +28: [2023-04-29 11:37:27,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +24: [2023-04-29 11:37:27,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +24: [2023-04-29 11:37:27,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +24: [2023-04-29 11:37:27,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +24: [2023-04-29 11:37:27,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +24: [2023-04-29 11:37:27,301] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +28: [2023-04-29 11:37:27,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +24: [2023-04-29 11:37:27,301] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +28: [2023-04-29 11:37:27,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +28: [2023-04-29 11:37:27,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +28: [2023-04-29 11:37:27,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +24: [2023-04-29 11:37:27,301] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +28: [2023-04-29 11:37:27,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +24: [2023-04-29 11:37:27,301] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +15: [2023-04-29 11:37:27,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +15: [2023-04-29 11:37:27,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +28: [2023-04-29 11:37:27,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +15: [2023-04-29 11:37:27,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +48: [2023-04-29 11:37:27,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +41: [2023-04-29 11:37:27,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +31: [2023-04-29 11:37:27,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +31: [2023-04-29 11:37:27,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +31: [2023-04-29 11:37:27,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +22: [2023-04-29 11:37:27,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +22: [2023-04-29 11:37:27,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +22: [2023-04-29 11:37:27,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 3: [2023-04-29 11:37:27,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +13: [2023-04-29 11:37:27,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +22: [2023-04-29 11:37:27,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +13: [2023-04-29 11:37:27,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +13: [2023-04-29 11:37:27,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +58: [2023-04-29 11:37:27,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +13: [2023-04-29 11:37:27,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +13: [2023-04-29 11:37:27,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +13: [2023-04-29 11:37:27,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +13: [2023-04-29 11:37:27,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +48: [2023-04-29 11:37:27,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +13: [2023-04-29 11:37:27,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +11: [2023-04-29 11:37:27,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +15: [2023-04-29 11:37:27,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +24: [2023-04-29 11:37:27,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +24: [2023-04-29 11:37:27,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +15: [2023-04-29 11:37:27,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +31: [2023-04-29 11:37:27,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +60: [2023-04-29 11:37:27,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +60: [2023-04-29 11:37:27,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +25: [2023-04-29 11:37:27,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +24: [2023-04-29 11:37:27,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +24: [2023-04-29 11:37:27,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +29: [2023-04-29 11:37:27,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +29: [2023-04-29 11:37:27,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +16: [2023-04-29 11:37:27,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +29: [2023-04-29 11:37:27,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +16: [2023-04-29 11:37:27,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +36: [2023-04-29 11:37:27,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +59: [2023-04-29 11:37:27,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +29: [2023-04-29 11:37:27,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +59: [2023-04-29 11:37:27,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +59: [2023-04-29 11:37:27,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +58: [2023-04-29 11:37:27,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +58: [2023-04-29 11:37:27,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +24: [2023-04-29 11:37:27,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +15: [2023-04-29 11:37:27,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +16: [2023-04-29 11:37:27,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +24: [2023-04-29 11:37:27,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +14: [2023-04-29 11:37:27,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +22: [2023-04-29 11:37:27,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +15: [2023-04-29 11:37:27,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +24: [2023-04-29 11:37:27,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +24: [2023-04-29 11:37:27,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +22: [2023-04-29 11:37:27,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +13: [2023-04-29 11:37:27,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +49: [2023-04-29 11:37:27,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +22: [2023-04-29 11:37:27,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +13: [2023-04-29 11:37:27,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +22: [2023-04-29 11:37:27,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +13: [2023-04-29 11:37:27,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +58: [2023-04-29 11:37:27,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +41: [2023-04-29 11:37:27,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +16: [2023-04-29 11:37:27,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +25: [2023-04-29 11:37:27,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +45: [2023-04-29 11:37:27,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +11: [2023-04-29 11:37:27,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +13: [2023-04-29 11:37:27,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +13: [2023-04-29 11:37:27,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +13: [2023-04-29 11:37:27,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +13: [2023-04-29 11:37:27,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +13: [2023-04-29 11:37:27,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +23: [2023-04-29 11:37:27,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +23: [2023-04-29 11:37:27,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +60: [2023-04-29 11:37:27,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +59: [2023-04-29 11:37:27,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +60: [2023-04-29 11:37:27,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +38: [2023-04-29 11:37:27,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +12: [2023-04-29 11:37:27,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +12: [2023-04-29 11:37:27,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +25: [2023-04-29 11:37:27,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +33: [2023-04-29 11:37:27,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 1: [2023-04-29 11:37:27,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. + 1: [2023-04-29 11:37:27,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +47: [2023-04-29 11:37:27,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +44: [2023-04-29 11:37:27,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +45: [2023-04-29 11:37:27,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +44: [2023-04-29 11:37:27,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 1: [2023-04-29 11:37:27,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +12: [2023-04-29 11:37:27,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +12: [2023-04-29 11:37:27,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +41: [2023-04-29 11:37:27,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. + 1: [2023-04-29 11:37:27,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +44: [2023-04-29 11:37:27,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +45: [2023-04-29 11:37:27,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +56: [2023-04-29 11:37:27,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +56: [2023-04-29 11:37:27,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +36: [2023-04-29 11:37:27,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +23: [2023-04-29 11:37:27,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +53: [2023-04-29 11:37:27,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +41: [2023-04-29 11:37:27,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +56: [2023-04-29 11:37:27,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +12: [2023-04-29 11:37:27,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +56: [2023-04-29 11:37:27,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +56: [2023-04-29 11:37:27,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +56: [2023-04-29 11:37:27,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +56: [2023-04-29 11:37:27,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +33: [2023-04-29 11:37:27,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +33: [2023-04-29 11:37:27,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +23: [2023-04-29 11:37:27,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +56: [2023-04-29 11:37:27,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +12: [2023-04-29 11:37:27,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +33: [2023-04-29 11:37:27,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +47: [2023-04-29 11:37:27,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +38: [2023-04-29 11:37:27,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. + 7: [2023-04-29 11:37:27,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +44: [2023-04-29 11:37:27,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +25: [2023-04-29 11:37:27,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +17: [2023-04-29 11:37:27,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +17: [2023-04-29 11:37:27,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +17: [2023-04-29 11:37:27,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +17: [2023-04-29 11:37:27,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +17: [2023-04-29 11:37:27,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +17: [2023-04-29 11:37:27,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +17: [2023-04-29 11:37:27,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +17: [2023-04-29 11:37:27,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +49: [2023-04-29 11:37:27,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +14: [2023-04-29 11:37:27,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +14: [2023-04-29 11:37:27,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +49: [2023-04-29 11:37:27,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 3: [2023-04-29 11:37:27,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +11: [2023-04-29 11:37:27,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +11: [2023-04-29 11:37:27,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +29: [2023-04-29 11:37:27,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +49: [2023-04-29 11:37:27,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 0: [2023-04-29 11:37:27,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +12: [2023-04-29 11:37:27,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +56: [2023-04-29 11:37:27,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +56: [2023-04-29 11:37:27,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +12: [2023-04-29 11:37:27,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 3: [2023-04-29 11:37:27,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +56: [2023-04-29 11:37:27,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +56: [2023-04-29 11:37:27,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +56: [2023-04-29 11:37:27,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +56: [2023-04-29 11:37:27,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... + 0: [2023-04-29 11:37:27,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +19: [2023-04-29 11:37:27,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +38: [2023-04-29 11:37:27,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +19: [2023-04-29 11:37:27,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +19: [2023-04-29 11:37:27,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +56: [2023-04-29 11:37:27,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +11: [2023-04-29 11:37:27,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +56: [2023-04-29 11:37:27,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +19: [2023-04-29 11:37:27,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +36: [2023-04-29 11:37:27,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +17: [2023-04-29 11:37:27,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +47: [2023-04-29 11:37:27,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. + 5: [2023-04-29 11:37:27,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. + 5: [2023-04-29 11:37:27,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. + 5: [2023-04-29 11:37:27,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. + 5: [2023-04-29 11:37:27,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. + 7: [2023-04-29 11:37:27,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +36: [2023-04-29 11:37:27,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +60: [2023-04-29 11:37:27,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 3: [2023-04-29 11:37:27,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +47: [2023-04-29 11:37:27,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. + 7: [2023-04-29 11:37:27,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 0: [2023-04-29 11:37:27,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +17: [2023-04-29 11:37:27,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +17: [2023-04-29 11:37:27,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 3: [2023-04-29 11:37:27,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +53: [2023-04-29 11:37:27,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +53: [2023-04-29 11:37:27,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +53: [2023-04-29 11:37:27,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +17: [2023-04-29 11:37:27,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +17: [2023-04-29 11:37:27,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +45: [2023-04-29 11:37:27,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +58: [2023-04-29 11:37:27,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +38: [2023-04-29 11:37:27,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. + 0: [2023-04-29 11:37:27,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +60: [2023-04-29 11:37:27,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +17: [2023-04-29 11:37:27,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +41: [2023-04-29 11:37:27,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +29: [2023-04-29 11:37:27,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +55: [2023-04-29 11:37:27,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +55: [2023-04-29 11:37:27,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +17: [2023-04-29 11:37:27,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 0: [2023-04-29 11:37:27,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +14: [2023-04-29 11:37:27,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 0: [2023-04-29 11:37:27,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +17: [2023-04-29 11:37:27,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +31: [2023-04-29 11:37:27,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +59: [2023-04-29 11:37:27,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +59: [2023-04-29 11:37:27,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +55: [2023-04-29 11:37:27,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +31: [2023-04-29 11:37:27,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +59: [2023-04-29 11:37:27,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +29: [2023-04-29 11:37:27,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +14: [2023-04-29 11:37:27,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +29: [2023-04-29 11:37:27,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +31: [2023-04-29 11:37:27,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +36: [2023-04-29 11:37:27,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +58: [2023-04-29 11:37:27,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +31: [2023-04-29 11:37:27,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +29: [2023-04-29 11:37:27,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +58: [2023-04-29 11:37:27,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +21: [2023-04-29 11:37:27,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +55: [2023-04-29 11:37:27,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. + 0: [2023-04-29 11:37:27,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +63: [2023-04-29 11:37:27,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +63: [2023-04-29 11:37:27,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +63: [2023-04-29 11:37:27,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +63: [2023-04-29 11:37:27,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +63: [2023-04-29 11:37:27,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +63: [2023-04-29 11:37:27,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +63: [2023-04-29 11:37:27,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +63: [2023-04-29 11:37:27,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +38: [2023-04-29 11:37:27,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +11: [2023-04-29 11:37:27,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 0: [2023-04-29 11:37:27,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +61: [2023-04-29 11:37:27,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +45: [2023-04-29 11:37:27,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +29: [2023-04-29 11:37:27,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +29: [2023-04-29 11:37:27,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +29: [2023-04-29 11:37:27,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +58: [2023-04-29 11:37:27,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +31: [2023-04-29 11:37:27,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +54: [2023-04-29 11:37:27,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +54: [2023-04-29 11:37:27,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +54: [2023-04-29 11:37:27,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +54: [2023-04-29 11:37:27,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +54: [2023-04-29 11:37:27,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +54: [2023-04-29 11:37:27,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +54: [2023-04-29 11:37:27,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +21: [2023-04-29 11:37:27,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +54: [2023-04-29 11:37:27,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 1: [2023-04-29 11:37:27,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +63: [2023-04-29 11:37:27,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +61: [2023-04-29 11:37:27,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +60: [2023-04-29 11:37:27,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +63: [2023-04-29 11:37:27,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +63: [2023-04-29 11:37:27,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +63: [2023-04-29 11:37:27,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +63: [2023-04-29 11:37:27,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +45: [2023-04-29 11:37:27,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +33: [2023-04-29 11:37:27,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +30: [2023-04-29 11:37:27,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +30: [2023-04-29 11:37:27,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +45: [2023-04-29 11:37:27,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +63: [2023-04-29 11:37:27,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +30: [2023-04-29 11:37:27,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +63: [2023-04-29 11:37:27,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +30: [2023-04-29 11:37:27,345] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +41: [2023-04-29 11:37:27,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +63: [2023-04-29 11:37:27,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... + 1: [2023-04-29 11:37:27,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +47: [2023-04-29 11:37:27,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 1: [2023-04-29 11:37:27,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +53: [2023-04-29 11:37:27,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +21: [2023-04-29 11:37:27,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +60: [2023-04-29 11:37:27,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +54: [2023-04-29 11:37:27,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +54: [2023-04-29 11:37:27,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... + 6: [2023-04-29 11:37:27,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 6: [2023-04-29 11:37:27,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +12: [2023-04-29 11:37:27,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +54: [2023-04-29 11:37:27,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +61: [2023-04-29 11:37:27,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +54: [2023-04-29 11:37:27,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... + 6: [2023-04-29 11:37:27,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +54: [2023-04-29 11:37:27,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... + 1: [2023-04-29 11:37:27,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +54: [2023-04-29 11:37:27,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +61: [2023-04-29 11:37:27,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +54: [2023-04-29 11:37:27,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +41: [2023-04-29 11:37:27,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +54: [2023-04-29 11:37:27,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +47: [2023-04-29 11:37:27,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +36: [2023-04-29 11:37:27,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +21: [2023-04-29 11:37:27,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +33: [2023-04-29 11:37:27,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +12: [2023-04-29 11:37:27,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +29: [2023-04-29 11:37:27,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +31: [2023-04-29 11:37:27,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +31: [2023-04-29 11:37:27,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +31: [2023-04-29 11:37:27,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +33: [2023-04-29 11:37:27,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +33: [2023-04-29 11:37:27,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +41: [2023-04-29 11:37:27,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +38: [2023-04-29 11:37:27,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +19: [2023-04-29 11:37:27,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 6: [2023-04-29 11:37:27,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... + 6: [2023-04-29 11:37:27,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +14: [2023-04-29 11:37:27,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +37: [2023-04-29 11:37:27,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 6: [2023-04-29 11:37:27,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +14: [2023-04-29 11:37:27,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +11: [2023-04-29 11:37:27,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 5: [2023-04-29 11:37:27,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +24: [2023-04-29 11:37:27,357] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +37: [2023-04-29 11:37:27,357] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 6: [2023-04-29 11:37:27,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +11: [2023-04-29 11:37:27,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 5: [2023-04-29 11:37:27,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +47: [2023-04-29 11:37:27,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +47: [2023-04-29 11:37:27,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +14: [2023-04-29 11:37:27,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 5: [2023-04-29 11:37:27,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 5: [2023-04-29 11:37:27,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +12: [2023-04-29 11:37:27,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +24: [2023-04-29 11:37:27,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +36: [2023-04-29 11:37:27,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +38: [2023-04-29 11:37:27,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +19: [2023-04-29 11:37:27,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +12: [2023-04-29 11:37:27,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +12: [2023-04-29 11:37:27,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +19: [2023-04-29 11:37:27,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +19: [2023-04-29 11:37:27,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +45: [2023-04-29 11:37:27,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +55: [2023-04-29 11:37:27,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +14: [2023-04-29 11:37:27,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +11: [2023-04-29 11:37:27,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +11: [2023-04-29 11:37:27,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +14: [2023-04-29 11:37:27,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +38: [2023-04-29 11:37:27,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +36: [2023-04-29 11:37:27,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +53: [2023-04-29 11:37:27,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 6: [2023-04-29 11:37:27,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +61: [2023-04-29 11:37:27,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +55: [2023-04-29 11:37:27,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +55: [2023-04-29 11:37:27,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +55: [2023-04-29 11:37:27,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +21: [2023-04-29 11:37:27,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +39: [2023-04-29 11:37:27,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +39: [2023-04-29 11:37:27,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +12: [2023-04-29 11:37:27,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +28: [2023-04-29 11:37:27,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +28: [2023-04-29 11:37:27,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +13: [2023-04-29 11:37:27,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +53: [2023-04-29 11:37:27,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +53: [2023-04-29 11:37:27,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +12: [2023-04-29 11:37:27,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +12: [2023-04-29 11:37:27,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +26: [2023-04-29 11:37:27,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +26: [2023-04-29 11:37:27,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +26: [2023-04-29 11:37:27,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +26: [2023-04-29 11:37:27,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +26: [2023-04-29 11:37:27,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +31: [2023-04-29 11:37:27,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +11: [2023-04-29 11:37:27,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +11: [2023-04-29 11:37:27,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +39: [2023-04-29 11:37:27,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +39: [2023-04-29 11:37:27,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +39: [2023-04-29 11:37:27,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +29: [2023-04-29 11:37:27,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +39: [2023-04-29 11:37:27,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +39: [2023-04-29 11:37:27,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +39: [2023-04-29 11:37:27,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +21: [2023-04-29 11:37:27,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +29: [2023-04-29 11:37:27,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +29: [2023-04-29 11:37:27,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +15: [2023-04-29 11:37:27,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +15: [2023-04-29 11:37:27,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +30: [2023-04-29 11:37:27,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 1: [2023-04-29 11:37:27,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 1: [2023-04-29 11:37:27,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 1: [2023-04-29 11:37:27,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 1: [2023-04-29 11:37:27,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +21: [2023-04-29 11:37:27,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +61: [2023-04-29 11:37:27,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +11: [2023-04-29 11:37:27,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +28: [2023-04-29 11:37:27,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +39: [2023-04-29 11:37:27,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +22: [2023-04-29 11:37:27,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +39: [2023-04-29 11:37:27,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +26: [2023-04-29 11:37:27,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +28: [2023-04-29 11:37:27,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +26: [2023-04-29 11:37:27,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +32: [2023-04-29 11:37:27,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +32: [2023-04-29 11:37:27,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +26: [2023-04-29 11:37:27,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +39: [2023-04-29 11:37:27,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +37: [2023-04-29 11:37:27,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +37: [2023-04-29 11:37:27,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +26: [2023-04-29 11:37:27,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +22: [2023-04-29 11:37:27,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +22: [2023-04-29 11:37:27,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +26: [2023-04-29 11:37:27,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +11: [2023-04-29 11:37:27,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +26: [2023-04-29 11:37:27,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +13: [2023-04-29 11:37:27,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 1: [2023-04-29 11:37:27,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +13: [2023-04-29 11:37:27,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 2: [2023-04-29 11:37:27,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 2: [2023-04-29 11:37:27,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +23: [2023-04-29 11:37:27,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +23: [2023-04-29 11:37:27,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +32: [2023-04-29 11:37:27,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +15: [2023-04-29 11:37:27,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 2: [2023-04-29 11:37:27,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +32: [2023-04-29 11:37:27,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. + 2: [2023-04-29 11:37:27,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 2: [2023-04-29 11:37:27,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +15: [2023-04-29 11:37:27,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +15: [2023-04-29 11:37:27,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... + 2: [2023-04-29 11:37:27,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 2: [2023-04-29 11:37:27,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 2: [2023-04-29 11:37:27,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +30: [2023-04-29 11:37:27,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +30: [2023-04-29 11:37:27,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +39: [2023-04-29 11:37:27,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +39: [2023-04-29 11:37:27,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +61: [2023-04-29 11:37:27,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +26: [2023-04-29 11:37:27,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +39: [2023-04-29 11:37:27,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +26: [2023-04-29 11:37:27,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +37: [2023-04-29 11:37:27,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +11: [2023-04-29 11:37:27,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... + 1: [2023-04-29 11:37:27,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 1: [2023-04-29 11:37:27,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +39: [2023-04-29 11:37:27,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +30: [2023-04-29 11:37:27,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +39: [2023-04-29 11:37:27,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +23: [2023-04-29 11:37:27,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +23: [2023-04-29 11:37:27,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +19: [2023-04-29 11:37:27,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +19: [2023-04-29 11:37:27,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +24: [2023-04-29 11:37:27,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +21: [2023-04-29 11:37:27,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +22: [2023-04-29 11:37:27,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +19: [2023-04-29 11:37:27,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +24: [2023-04-29 11:37:27,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +22: [2023-04-29 11:37:27,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +19: [2023-04-29 11:37:27,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +11: [2023-04-29 11:37:27,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... + 1: [2023-04-29 11:37:27,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +24: [2023-04-29 11:37:27,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +15: [2023-04-29 11:37:27,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +26: [2023-04-29 11:37:27,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +14: [2023-04-29 11:37:27,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +15: [2023-04-29 11:37:27,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... + 2: [2023-04-29 11:37:27,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +14: [2023-04-29 11:37:27,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +14: [2023-04-29 11:37:27,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +22: [2023-04-29 11:37:27,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +22: [2023-04-29 11:37:27,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +22: [2023-04-29 11:37:27,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 2: [2023-04-29 11:37:27,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +61: [2023-04-29 11:37:27,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 2: [2023-04-29 11:37:27,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... + 2: [2023-04-29 11:37:27,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +23: [2023-04-29 11:37:27,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +23: [2023-04-29 11:37:27,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 2: [2023-04-29 11:37:27,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 2: [2023-04-29 11:37:27,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... + 2: [2023-04-29 11:37:27,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +34: [2023-04-29 11:37:27,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +34: [2023-04-29 11:37:27,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. + 2: [2023-04-29 11:37:27,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +23: [2023-04-29 11:37:27,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +31: [2023-04-29 11:37:27,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +31: [2023-04-29 11:37:27,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +31: [2023-04-29 11:37:27,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +19: [2023-04-29 11:37:27,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +19: [2023-04-29 11:37:27,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +26: [2023-04-29 11:37:27,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +23: [2023-04-29 11:37:27,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +37: [2023-04-29 11:37:27,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +19: [2023-04-29 11:37:27,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +24: [2023-04-29 11:37:27,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +15: [2023-04-29 11:37:27,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +26: [2023-04-29 11:37:27,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +13: [2023-04-29 11:37:27,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +34: [2023-04-29 11:37:27,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +34: [2023-04-29 11:37:27,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +34: [2023-04-29 11:37:27,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +34: [2023-04-29 11:37:27,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +34: [2023-04-29 11:37:27,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +34: [2023-04-29 11:37:27,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +14: [2023-04-29 11:37:27,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +14: [2023-04-29 11:37:27,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +19: [2023-04-29 11:37:27,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +14: [2023-04-29 11:37:27,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +23: [2023-04-29 11:37:27,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +34: [2023-04-29 11:37:27,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +34: [2023-04-29 11:37:27,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +34: [2023-04-29 11:37:27,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +34: [2023-04-29 11:37:27,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +34: [2023-04-29 11:37:27,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +34: [2023-04-29 11:37:27,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +12: [2023-04-29 11:37:27,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +12: [2023-04-29 11:37:27,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +43: [2023-04-29 11:37:27,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +43: [2023-04-29 11:37:27,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +28: [2023-04-29 11:37:27,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +34: [2023-04-29 11:37:27,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +13: [2023-04-29 11:37:27,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +43: [2023-04-29 11:37:27,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +43: [2023-04-29 11:37:27,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +43: [2023-04-29 11:37:27,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +43: [2023-04-29 11:37:27,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +43: [2023-04-29 11:37:27,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +43: [2023-04-29 11:37:27,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +34: [2023-04-29 11:37:27,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +12: [2023-04-29 11:37:27,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +17: [2023-04-29 11:37:27,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +12: [2023-04-29 11:37:27,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +56: [2023-04-29 11:37:27,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +56: [2023-04-29 11:37:27,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +56: [2023-04-29 11:37:27,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +23: [2023-04-29 11:37:27,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +28: [2023-04-29 11:37:27,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +17: [2023-04-29 11:37:27,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +23: [2023-04-29 11:37:27,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +43: [2023-04-29 11:37:27,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +27: [2023-04-29 11:37:27,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +27: [2023-04-29 11:37:27,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +27: [2023-04-29 11:37:27,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +27: [2023-04-29 11:37:27,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +23: [2023-04-29 11:37:27,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +56: [2023-04-29 11:37:27,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +43: [2023-04-29 11:37:27,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +43: [2023-04-29 11:37:27,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +43: [2023-04-29 11:37:27,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +17: [2023-04-29 11:37:27,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +17: [2023-04-29 11:37:27,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +43: [2023-04-29 11:37:27,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +54: [2023-04-29 11:37:27,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +28: [2023-04-29 11:37:27,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +43: [2023-04-29 11:37:27,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt... +23: [2023-04-29 11:37:27,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +43: [2023-04-29 11:37:27,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +43: [2023-04-29 11:37:27,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt... +13: [2023-04-29 11:37:27,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +32: [2023-04-29 11:37:27,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +63: [2023-04-29 11:37:27,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +13: [2023-04-29 11:37:27,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +23: [2023-04-29 11:37:27,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +23: [2023-04-29 11:37:27,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +32: [2023-04-29 11:37:27,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +32: [2023-04-29 11:37:27,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +28: [2023-04-29 11:37:27,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +32: [2023-04-29 11:37:27,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +37: [2023-04-29 11:37:27,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +29: [2023-04-29 11:37:27,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +37: [2023-04-29 11:37:27,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +22: [2023-04-29 11:37:27,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +63: [2023-04-29 11:37:27,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +24: [2023-04-29 11:37:27,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +24: [2023-04-29 11:37:27,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +29: [2023-04-29 11:37:27,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +22: [2023-04-29 11:37:27,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +22: [2023-04-29 11:37:27,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +23: [2023-04-29 11:37:27,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +29: [2023-04-29 11:37:27,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +54: [2023-04-29 11:37:27,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +29: [2023-04-29 11:37:27,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +22: [2023-04-29 11:37:27,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 1: [2023-04-29 11:37:27,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +31: [2023-04-29 11:37:27,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +29: [2023-04-29 11:37:27,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +63: [2023-04-29 11:37:27,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +13: [2023-04-29 11:37:27,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +31: [2023-04-29 11:37:27,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +31: [2023-04-29 11:37:27,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +29: [2023-04-29 11:37:27,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +29: [2023-04-29 11:37:27,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +22: [2023-04-29 11:37:27,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +63: [2023-04-29 11:37:27,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +22: [2023-04-29 11:37:27,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +22: [2023-04-29 11:37:27,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 1: [2023-04-29 11:37:27,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +22: [2023-04-29 11:37:27,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +54: [2023-04-29 11:37:27,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +31: [2023-04-29 11:37:27,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 1: [2023-04-29 11:37:27,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... + 3: [2023-04-29 11:37:27,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. + 3: [2023-04-29 11:37:27,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. + 3: [2023-04-29 11:37:27,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +31: [2023-04-29 11:37:27,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +54: [2023-04-29 11:37:27,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 1: [2023-04-29 11:37:27,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 3: [2023-04-29 11:37:27,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_05-model_01-model_states.pt. +29: [2023-04-29 11:37:27,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +31: [2023-04-29 11:37:27,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +19: [2023-04-29 11:37:27,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 1: [2023-04-29 11:37:27,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +31: [2023-04-29 11:37:27,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... + 1: [2023-04-29 11:37:27,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +17: [2023-04-29 11:37:27,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +12: [2023-04-29 11:37:27,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +12: [2023-04-29 11:37:27,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +56: [2023-04-29 11:37:27,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +31: [2023-04-29 11:37:27,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +39: [2023-04-29 11:37:27,425] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +56: [2023-04-29 11:37:27,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +56: [2023-04-29 11:37:27,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +56: [2023-04-29 11:37:27,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +27: [2023-04-29 11:37:27,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +27: [2023-04-29 11:37:27,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +27: [2023-04-29 11:37:27,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +17: [2023-04-29 11:37:27,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +27: [2023-04-29 11:37:27,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +12: [2023-04-29 11:37:27,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 1: [2023-04-29 11:37:27,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +54: [2023-04-29 11:37:27,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +63: [2023-04-29 11:37:27,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +26: [2023-04-29 11:37:27,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +19: [2023-04-29 11:37:27,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +12: [2023-04-29 11:37:27,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 1: [2023-04-29 11:37:27,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +17: [2023-04-29 11:37:27,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +17: [2023-04-29 11:37:27,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 1: [2023-04-29 11:37:27,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +19: [2023-04-29 11:37:27,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +63: [2023-04-29 11:37:27,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +19: [2023-04-29 11:37:27,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +26: [2023-04-29 11:37:27,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +39: [2023-04-29 11:37:27,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +39: [2023-04-29 11:37:27,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +54: [2023-04-29 11:37:27,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +19: [2023-04-29 11:37:27,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +19: [2023-04-29 11:37:27,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +63: [2023-04-29 11:37:27,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +26: [2023-04-29 11:37:27,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 2: [2023-04-29 11:37:27,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +63: [2023-04-29 11:37:27,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +19: [2023-04-29 11:37:27,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +19: [2023-04-29 11:37:27,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... + 3: [2023-04-29 11:37:27,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 3: [2023-04-29 11:37:27,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 3: [2023-04-29 11:37:27,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +26: [2023-04-29 11:37:27,448] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +49: [2023-04-29 11:37:27,448] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +49: [2023-04-29 11:37:27,448] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +23: [2023-04-29 11:37:27,448] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 3: [2023-04-29 11:37:27,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +49: [2023-04-29 11:37:27,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +49: [2023-04-29 11:37:27,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +39: [2023-04-29 11:37:27,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 5: [2023-04-29 11:37:27,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +19: [2023-04-29 11:37:27,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... + 5: [2023-04-29 11:37:27,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +43: [2023-04-29 11:37:27,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. + 5: [2023-04-29 11:37:27,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 5: [2023-04-29 11:37:27,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 5: [2023-04-29 11:37:27,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 5: [2023-04-29 11:37:27,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 5: [2023-04-29 11:37:27,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 5: [2023-04-29 11:37:27,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +39: [2023-04-29 11:37:27,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. + 1: [2023-04-29 11:37:27,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 2: [2023-04-29 11:37:27,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 2: [2023-04-29 11:37:27,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 2: [2023-04-29 11:37:27,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +23: [2023-04-29 11:37:27,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 1: [2023-04-29 11:37:27,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +54: [2023-04-29 11:37:27,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +54: [2023-04-29 11:37:27,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +26: [2023-04-29 11:37:27,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 1: [2023-04-29 11:37:27,453] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +19: [2023-04-29 11:37:27,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +23: [2023-04-29 11:37:27,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +23: [2023-04-29 11:37:27,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 1: [2023-04-29 11:37:27,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 5: [2023-04-29 11:37:27,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +44: [2023-04-29 11:37:27,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +44: [2023-04-29 11:37:27,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. + 5: [2023-04-29 11:37:27,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... + 5: [2023-04-29 11:37:27,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +34: [2023-04-29 11:37:27,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +34: [2023-04-29 11:37:27,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. + 5: [2023-04-29 11:37:27,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +19: [2023-04-29 11:37:27,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 5: [2023-04-29 11:37:27,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 5: [2023-04-29 11:37:27,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +44: [2023-04-29 11:37:27,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. + 5: [2023-04-29 11:37:27,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +44: [2023-04-29 11:37:27,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. + 5: [2023-04-29 11:37:27,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +34: [2023-04-29 11:37:27,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +52: [2023-04-29 11:37:27,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +52: [2023-04-29 11:37:27,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +34: [2023-04-29 11:37:27,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +52: [2023-04-29 11:37:27,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +52: [2023-04-29 11:37:27,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +19: [2023-04-29 11:37:27,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +26: [2023-04-29 11:37:27,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +22: [2023-04-29 11:37:27,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +43: [2023-04-29 11:37:27,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +43: [2023-04-29 11:37:27,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +39: [2023-04-29 11:37:27,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +39: [2023-04-29 11:37:27,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +43: [2023-04-29 11:37:27,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_00-model_states.pt. +19: [2023-04-29 11:37:27,470] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +52: [2023-04-29 11:37:27,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +22: [2023-04-29 11:37:27,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +52: [2023-04-29 11:37:27,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +49: [2023-04-29 11:37:27,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +52: [2023-04-29 11:37:27,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +52: [2023-04-29 11:37:27,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +26: [2023-04-29 11:37:27,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 2: [2023-04-29 11:37:27,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +23: [2023-04-29 11:37:27,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +26: [2023-04-29 11:37:27,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +43: [2023-04-29 11:37:27,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +49: [2023-04-29 11:37:27,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +42: [2023-04-29 11:37:27,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +42: [2023-04-29 11:37:27,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +42: [2023-04-29 11:37:27,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +42: [2023-04-29 11:37:27,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +23: [2023-04-29 11:37:27,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +19: [2023-04-29 11:37:27,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +22: [2023-04-29 11:37:27,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +22: [2023-04-29 11:37:27,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +39: [2023-04-29 11:37:27,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 2: [2023-04-29 11:37:27,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +58: [2023-04-29 11:37:27,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. + 2: [2023-04-29 11:37:27,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +58: [2023-04-29 11:37:27,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +34: [2023-04-29 11:37:27,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 2: [2023-04-29 11:37:27,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +23: [2023-04-29 11:37:27,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +22: [2023-04-29 11:37:27,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 1: [2023-04-29 11:37:27,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +58: [2023-04-29 11:37:27,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +58: [2023-04-29 11:37:27,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. + 9: [2023-04-29 11:37:27,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 9: [2023-04-29 11:37:27,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 9: [2023-04-29 11:37:27,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 9: [2023-04-29 11:37:27,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +19: [2023-04-29 11:37:27,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 9: [2023-04-29 11:37:27,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 9: [2023-04-29 11:37:27,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 9: [2023-04-29 11:37:27,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +49: [2023-04-29 11:37:27,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 9: [2023-04-29 11:37:27,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +34: [2023-04-29 11:37:27,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 1: [2023-04-29 11:37:27,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +44: [2023-04-29 11:37:27,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +44: [2023-04-29 11:37:27,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +23: [2023-04-29 11:37:27,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 1: [2023-04-29 11:37:27,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +44: [2023-04-29 11:37:27,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +22: [2023-04-29 11:37:27,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +22: [2023-04-29 11:37:27,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +49: [2023-04-29 11:37:27,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +44: [2023-04-29 11:37:27,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +22: [2023-04-29 11:37:27,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +35: [2023-04-29 11:37:27,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. + 9: [2023-04-29 11:37:27,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 9: [2023-04-29 11:37:27,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +35: [2023-04-29 11:37:27,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. + 9: [2023-04-29 11:37:27,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... + 9: [2023-04-29 11:37:27,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +57: [2023-04-29 11:37:27,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +57: [2023-04-29 11:37:27,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +57: [2023-04-29 11:37:27,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. + 9: [2023-04-29 11:37:27,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +57: [2023-04-29 11:37:27,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. + 9: [2023-04-29 11:37:27,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... + 9: [2023-04-29 11:37:27,493] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... + 9: [2023-04-29 11:37:27,493] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +43: [2023-04-29 11:37:27,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +43: [2023-04-29 11:37:27,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +35: [2023-04-29 11:37:27,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +35: [2023-04-29 11:37:27,495] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +19: [2023-04-29 11:37:27,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +43: [2023-04-29 11:37:27,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +34: [2023-04-29 11:37:27,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +34: [2023-04-29 11:37:27,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +50: [2023-04-29 11:37:27,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +50: [2023-04-29 11:37:27,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +50: [2023-04-29 11:37:27,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +50: [2023-04-29 11:37:27,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +42: [2023-04-29 11:37:27,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +30: [2023-04-29 11:37:27,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +30: [2023-04-29 11:37:27,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +30: [2023-04-29 11:37:27,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +30: [2023-04-29 11:37:27,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +30: [2023-04-29 11:37:27,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +30: [2023-04-29 11:37:27,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +30: [2023-04-29 11:37:27,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +30: [2023-04-29 11:37:27,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 3: [2023-04-29 11:37:27,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 3: [2023-04-29 11:37:27,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +42: [2023-04-29 11:37:27,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +42: [2023-04-29 11:37:27,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +58: [2023-04-29 11:37:27,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +42: [2023-04-29 11:37:27,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +58: [2023-04-29 11:37:27,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +58: [2023-04-29 11:37:27,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +30: [2023-04-29 11:37:27,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +30: [2023-04-29 11:37:27,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +30: [2023-04-29 11:37:27,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... + 3: [2023-04-29 11:37:27,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +58: [2023-04-29 11:37:27,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +30: [2023-04-29 11:37:27,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +30: [2023-04-29 11:37:27,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 3: [2023-04-29 11:37:27,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... + 3: [2023-04-29 11:37:27,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +30: [2023-04-29 11:37:27,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +30: [2023-04-29 11:37:27,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +30: [2023-04-29 11:37:27,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +57: [2023-04-29 11:37:27,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +37: [2023-04-29 11:37:27,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +37: [2023-04-29 11:37:27,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +37: [2023-04-29 11:37:27,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +37: [2023-04-29 11:37:27,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. + 3: [2023-04-29 11:37:27,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +57: [2023-04-29 11:37:27,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +35: [2023-04-29 11:37:27,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +35: [2023-04-29 11:37:27,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 3: [2023-04-29 11:37:27,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +57: [2023-04-29 11:37:27,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +57: [2023-04-29 11:37:27,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 3: [2023-04-29 11:37:27,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +40: [2023-04-29 11:37:27,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +40: [2023-04-29 11:37:27,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +40: [2023-04-29 11:37:27,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +40: [2023-04-29 11:37:27,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +35: [2023-04-29 11:37:27,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +35: [2023-04-29 11:37:27,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +50: [2023-04-29 11:37:27,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +40: [2023-04-29 11:37:27,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +40: [2023-04-29 11:37:27,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +40: [2023-04-29 11:37:27,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +40: [2023-04-29 11:37:27,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 5: [2023-04-29 11:37:27,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 5: [2023-04-29 11:37:27,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 5: [2023-04-29 11:37:27,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +50: [2023-04-29 11:37:27,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 5: [2023-04-29 11:37:27,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +52: [2023-04-29 11:37:27,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +50: [2023-04-29 11:37:27,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +50: [2023-04-29 11:37:27,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 0: [2023-04-29 11:37:27,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 0: [2023-04-29 11:37:27,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 0: [2023-04-29 11:37:27,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 0: [2023-04-29 11:37:27,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +50: [2023-04-29 11:37:27,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +50: [2023-04-29 11:37:27,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +50: [2023-04-29 11:37:27,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +50: [2023-04-29 11:37:27,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +50: [2023-04-29 11:37:27,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +52: [2023-04-29 11:37:27,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +52: [2023-04-29 11:37:27,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 0: [2023-04-29 11:37:27,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 0: [2023-04-29 11:37:27,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 0: [2023-04-29 11:37:27,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 0: [2023-04-29 11:37:27,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +52: [2023-04-29 11:37:27,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +33: [2023-04-29 11:37:27,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +33: [2023-04-29 11:37:27,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +33: [2023-04-29 11:37:27,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +33: [2023-04-29 11:37:27,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. + 9: [2023-04-29 11:37:27,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +37: [2023-04-29 11:37:27,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +50: [2023-04-29 11:37:27,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +37: [2023-04-29 11:37:27,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +37: [2023-04-29 11:37:27,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +37: [2023-04-29 11:37:27,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +50: [2023-04-29 11:37:27,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +40: [2023-04-29 11:37:27,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +40: [2023-04-29 11:37:27,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +50: [2023-04-29 11:37:27,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 9: [2023-04-29 11:37:27,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +40: [2023-04-29 11:37:27,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +40: [2023-04-29 11:37:27,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +52: [2023-04-29 11:37:27,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +48: [2023-04-29 11:37:27,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +48: [2023-04-29 11:37:27,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +62: [2023-04-29 11:37:27,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +62: [2023-04-29 11:37:27,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +62: [2023-04-29 11:37:27,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +48: [2023-04-29 11:37:27,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +62: [2023-04-29 11:37:27,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +48: [2023-04-29 11:37:27,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. + 5: [2023-04-29 11:37:27,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 5: [2023-04-29 11:37:27,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 5: [2023-04-29 11:37:27,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +62: [2023-04-29 11:37:27,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +62: [2023-04-29 11:37:27,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 5: [2023-04-29 11:37:27,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +62: [2023-04-29 11:37:27,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +62: [2023-04-29 11:37:27,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 9: [2023-04-29 11:37:27,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +32: [2023-04-29 11:37:27,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +32: [2023-04-29 11:37:27,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +32: [2023-04-29 11:37:27,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +32: [2023-04-29 11:37:27,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +32: [2023-04-29 11:37:27,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 8: [2023-04-29 11:37:27,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. + 8: [2023-04-29 11:37:27,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. + 8: [2023-04-29 11:37:27,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +49: [2023-04-29 11:37:27,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 8: [2023-04-29 11:37:27,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +32: [2023-04-29 11:37:27,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +32: [2023-04-29 11:37:27,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +49: [2023-04-29 11:37:27,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +49: [2023-04-29 11:37:27,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +32: [2023-04-29 11:37:27,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +49: [2023-04-29 11:37:27,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +49: [2023-04-29 11:37:27,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +49: [2023-04-29 11:37:27,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +49: [2023-04-29 11:37:27,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +49: [2023-04-29 11:37:27,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +52: [2023-04-29 11:37:27,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 9: [2023-04-29 11:37:27,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +52: [2023-04-29 11:37:27,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +33: [2023-04-29 11:37:27,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 9: [2023-04-29 11:37:27,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +52: [2023-04-29 11:37:27,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 4: [2023-04-29 11:37:27,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. + 4: [2023-04-29 11:37:27,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. + 4: [2023-04-29 11:37:27,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. + 4: [2023-04-29 11:37:27,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +49: [2023-04-29 11:37:27,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +46: [2023-04-29 11:37:27,574] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +46: [2023-04-29 11:37:27,574] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +58: [2023-04-29 11:37:27,574] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +58: [2023-04-29 11:37:27,574] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +33: [2023-04-29 11:37:27,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +18: [2023-04-29 11:37:27,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +18: [2023-04-29 11:37:27,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +18: [2023-04-29 11:37:27,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +58: [2023-04-29 11:37:27,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +58: [2023-04-29 11:37:27,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +42: [2023-04-29 11:37:27,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +42: [2023-04-29 11:37:27,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +58: [2023-04-29 11:37:27,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +58: [2023-04-29 11:37:27,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +58: [2023-04-29 11:37:27,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +18: [2023-04-29 11:37:27,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +32: [2023-04-29 11:37:27,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +33: [2023-04-29 11:37:27,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +33: [2023-04-29 11:37:27,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +49: [2023-04-29 11:37:27,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +49: [2023-04-29 11:37:27,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +46: [2023-04-29 11:37:27,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +32: [2023-04-29 11:37:27,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +32: [2023-04-29 11:37:27,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +46: [2023-04-29 11:37:27,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +62: [2023-04-29 11:37:27,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +62: [2023-04-29 11:37:27,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +62: [2023-04-29 11:37:27,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +32: [2023-04-29 11:37:27,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +32: [2023-04-29 11:37:27,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +62: [2023-04-29 11:37:27,577] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +49: [2023-04-29 11:37:27,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +30: [2023-04-29 11:37:27,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +42: [2023-04-29 11:37:27,577] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +42: [2023-04-29 11:37:27,577] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +20: [2023-04-29 11:37:27,577] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +20: [2023-04-29 11:37:27,577] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +20: [2023-04-29 11:37:27,577] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +20: [2023-04-29 11:37:27,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +32: [2023-04-29 11:37:27,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +42: [2023-04-29 11:37:27,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +32: [2023-04-29 11:37:27,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +49: [2023-04-29 11:37:27,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +49: [2023-04-29 11:37:27,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +49: [2023-04-29 11:37:27,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +49: [2023-04-29 11:37:27,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +32: [2023-04-29 11:37:27,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +58: [2023-04-29 11:37:27,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... + 9: [2023-04-29 11:37:27,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +44: [2023-04-29 11:37:27,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +44: [2023-04-29 11:37:27,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +44: [2023-04-29 11:37:27,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +44: [2023-04-29 11:37:27,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +44: [2023-04-29 11:37:27,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +44: [2023-04-29 11:37:27,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +44: [2023-04-29 11:37:27,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +52: [2023-04-29 11:37:27,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +52: [2023-04-29 11:37:27,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +52: [2023-04-29 11:37:27,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +44: [2023-04-29 11:37:27,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +58: [2023-04-29 11:37:27,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +52: [2023-04-29 11:37:27,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +40: [2023-04-29 11:37:27,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +40: [2023-04-29 11:37:27,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +42: [2023-04-29 11:37:27,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +42: [2023-04-29 11:37:27,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +58: [2023-04-29 11:37:27,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +51: [2023-04-29 11:37:27,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +51: [2023-04-29 11:37:27,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +51: [2023-04-29 11:37:27,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +51: [2023-04-29 11:37:27,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +58: [2023-04-29 11:37:27,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +42: [2023-04-29 11:37:27,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +58: [2023-04-29 11:37:27,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +58: [2023-04-29 11:37:27,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +30: [2023-04-29 11:37:27,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +30: [2023-04-29 11:37:27,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +42: [2023-04-29 11:37:27,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +58: [2023-04-29 11:37:27,584] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +42: [2023-04-29 11:37:27,584] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +42: [2023-04-29 11:37:27,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +30: [2023-04-29 11:37:27,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +42: [2023-04-29 11:37:27,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +42: [2023-04-29 11:37:27,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +44: [2023-04-29 11:37:27,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +48: [2023-04-29 11:37:27,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +44: [2023-04-29 11:37:27,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +44: [2023-04-29 11:37:27,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +44: [2023-04-29 11:37:27,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +44: [2023-04-29 11:37:27,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +44: [2023-04-29 11:37:27,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +44: [2023-04-29 11:37:27,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +44: [2023-04-29 11:37:27,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +40: [2023-04-29 11:37:27,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +40: [2023-04-29 11:37:27,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +50: [2023-04-29 11:37:27,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +51: [2023-04-29 11:37:27,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +51: [2023-04-29 11:37:27,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +51: [2023-04-29 11:37:27,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +48: [2023-04-29 11:37:27,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +51: [2023-04-29 11:37:27,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +51: [2023-04-29 11:37:27,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +48: [2023-04-29 11:37:27,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +48: [2023-04-29 11:37:27,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +51: [2023-04-29 11:37:27,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +42: [2023-04-29 11:37:27,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +42: [2023-04-29 11:37:27,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +58: [2023-04-29 11:37:27,594] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +42: [2023-04-29 11:37:27,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +51: [2023-04-29 11:37:27,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +51: [2023-04-29 11:37:27,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. + 8: [2023-04-29 11:37:27,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +50: [2023-04-29 11:37:27,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... + 9: [2023-04-29 11:37:27,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 4: [2023-04-29 11:37:27,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +40: [2023-04-29 11:37:27,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 4: [2023-04-29 11:37:27,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 8: [2023-04-29 11:37:27,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 4: [2023-04-29 11:37:27,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 9: [2023-04-29 11:37:27,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +30: [2023-04-29 11:37:27,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +18: [2023-04-29 11:37:27,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +46: [2023-04-29 11:37:27,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +46: [2023-04-29 11:37:27,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +18: [2023-04-29 11:37:27,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 8: [2023-04-29 11:37:27,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +46: [2023-04-29 11:37:27,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +50: [2023-04-29 11:37:27,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +58: [2023-04-29 11:37:27,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +18: [2023-04-29 11:37:27,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +18: [2023-04-29 11:37:27,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +41: [2023-04-29 11:37:27,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +41: [2023-04-29 11:37:27,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +41: [2023-04-29 11:37:27,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +41: [2023-04-29 11:37:27,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. + 4: [2023-04-29 11:37:27,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 8: [2023-04-29 11:37:27,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +46: [2023-04-29 11:37:27,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +35: [2023-04-29 11:37:27,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +35: [2023-04-29 11:37:27,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +20: [2023-04-29 11:37:27,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +20: [2023-04-29 11:37:27,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +35: [2023-04-29 11:37:27,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +35: [2023-04-29 11:37:27,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +35: [2023-04-29 11:37:27,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +35: [2023-04-29 11:37:27,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +35: [2023-04-29 11:37:27,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +35: [2023-04-29 11:37:27,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +50: [2023-04-29 11:37:27,607] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +20: [2023-04-29 11:37:27,608] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +30: [2023-04-29 11:37:27,608] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +50: [2023-04-29 11:37:27,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 0: [2023-04-29 11:37:27,610] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 0: [2023-04-29 11:37:27,610] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +52: [2023-04-29 11:37:27,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 0: [2023-04-29 11:37:27,610] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +35: [2023-04-29 11:37:27,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +30: [2023-04-29 11:37:27,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +20: [2023-04-29 11:37:27,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +52: [2023-04-29 11:37:27,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +30: [2023-04-29 11:37:27,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +35: [2023-04-29 11:37:27,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... + 0: [2023-04-29 11:37:27,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +35: [2023-04-29 11:37:27,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +50: [2023-04-29 11:37:27,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +35: [2023-04-29 11:37:27,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +62: [2023-04-29 11:37:27,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +35: [2023-04-29 11:37:27,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +35: [2023-04-29 11:37:27,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +35: [2023-04-29 11:37:27,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +35: [2023-04-29 11:37:27,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +51: [2023-04-29 11:37:27,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +62: [2023-04-29 11:37:27,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +62: [2023-04-29 11:37:27,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +62: [2023-04-29 11:37:27,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +52: [2023-04-29 11:37:27,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +52: [2023-04-29 11:37:27,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +51: [2023-04-29 11:37:27,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +50: [2023-04-29 11:37:27,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +50: [2023-04-29 11:37:27,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +40: [2023-04-29 11:37:27,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +40: [2023-04-29 11:37:27,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +50: [2023-04-29 11:37:27,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +41: [2023-04-29 11:37:27,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +41: [2023-04-29 11:37:27,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +51: [2023-04-29 11:37:27,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +40: [2023-04-29 11:37:27,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +50: [2023-04-29 11:37:27,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +50: [2023-04-29 11:37:27,633] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +41: [2023-04-29 11:37:27,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +51: [2023-04-29 11:37:27,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +40: [2023-04-29 11:37:27,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +41: [2023-04-29 11:37:27,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +44: [2023-04-29 11:37:27,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 8: [2023-04-29 11:37:27,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +50: [2023-04-29 11:37:27,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 8: [2023-04-29 11:37:27,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +49: [2023-04-29 11:37:27,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +62: [2023-04-29 11:37:27,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 8: [2023-04-29 11:37:27,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 8: [2023-04-29 11:37:27,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +62: [2023-04-29 11:37:27,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +41: [2023-04-29 11:37:27,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +41: [2023-04-29 11:37:27,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +41: [2023-04-29 11:37:27,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +41: [2023-04-29 11:37:27,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +27: [2023-04-29 11:37:27,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 0: [2023-04-29 11:37:27,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +27: [2023-04-29 11:37:27,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +27: [2023-04-29 11:37:27,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +27: [2023-04-29 11:37:27,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +27: [2023-04-29 11:37:27,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +27: [2023-04-29 11:37:27,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +27: [2023-04-29 11:37:27,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +27: [2023-04-29 11:37:27,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 8: [2023-04-29 11:37:27,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 8: [2023-04-29 11:37:27,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +32: [2023-04-29 11:37:27,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +32: [2023-04-29 11:37:27,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 0: [2023-04-29 11:37:27,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 0: [2023-04-29 11:37:27,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +53: [2023-04-29 11:37:27,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +53: [2023-04-29 11:37:27,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +53: [2023-04-29 11:37:27,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +53: [2023-04-29 11:37:27,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +50: [2023-04-29 11:37:27,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 8: [2023-04-29 11:37:27,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 8: [2023-04-29 11:37:27,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +41: [2023-04-29 11:37:27,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +27: [2023-04-29 11:37:27,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 4: [2023-04-29 11:37:27,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 4: [2023-04-29 11:37:27,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 4: [2023-04-29 11:37:27,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 4: [2023-04-29 11:37:27,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 0: [2023-04-29 11:37:27,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +27: [2023-04-29 11:37:27,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +27: [2023-04-29 11:37:27,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +27: [2023-04-29 11:37:27,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +27: [2023-04-29 11:37:27,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +27: [2023-04-29 11:37:27,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +27: [2023-04-29 11:37:27,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +42: [2023-04-29 11:37:27,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +42: [2023-04-29 11:37:27,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +42: [2023-04-29 11:37:27,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +27: [2023-04-29 11:37:27,650] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +53: [2023-04-29 11:37:27,650] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +41: [2023-04-29 11:37:27,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +32: [2023-04-29 11:37:27,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +40: [2023-04-29 11:37:27,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +41: [2023-04-29 11:37:27,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +53: [2023-04-29 11:37:27,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +41: [2023-04-29 11:37:27,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +53: [2023-04-29 11:37:27,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +10: [2023-04-29 11:37:27,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +10: [2023-04-29 11:37:27,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +58: [2023-04-29 11:37:27,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +58: [2023-04-29 11:37:27,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +40: [2023-04-29 11:37:27,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +44: [2023-04-29 11:37:27,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +53: [2023-04-29 11:37:27,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 4: [2023-04-29 11:37:27,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +58: [2023-04-29 11:37:27,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +59: [2023-04-29 11:37:27,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +59: [2023-04-29 11:37:27,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +58: [2023-04-29 11:37:27,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +49: [2023-04-29 11:37:27,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +49: [2023-04-29 11:37:27,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +49: [2023-04-29 11:37:27,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +59: [2023-04-29 11:37:27,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +59: [2023-04-29 11:37:27,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +32: [2023-04-29 11:37:27,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 4: [2023-04-29 11:37:27,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +42: [2023-04-29 11:37:27,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +10: [2023-04-29 11:37:27,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 4: [2023-04-29 11:37:27,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 4: [2023-04-29 11:37:27,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +25: [2023-04-29 11:37:27,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +25: [2023-04-29 11:37:27,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +40: [2023-04-29 11:37:27,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 8: [2023-04-29 11:37:27,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +44: [2023-04-29 11:37:27,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +10: [2023-04-29 11:37:27,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +44: [2023-04-29 11:37:27,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +10: [2023-04-29 11:37:27,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +25: [2023-04-29 11:37:27,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +21: [2023-04-29 11:37:27,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +21: [2023-04-29 11:37:27,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +21: [2023-04-29 11:37:27,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +25: [2023-04-29 11:37:27,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +21: [2023-04-29 11:37:27,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +10: [2023-04-29 11:37:27,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +24: [2023-04-29 11:37:27,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +24: [2023-04-29 11:37:27,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. + 8: [2023-04-29 11:37:27,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +53: [2023-04-29 11:37:27,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +53: [2023-04-29 11:37:27,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. + 4: [2023-04-29 11:37:27,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +53: [2023-04-29 11:37:27,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +37: [2023-04-29 11:37:27,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +37: [2023-04-29 11:37:27,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +10: [2023-04-29 11:37:27,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +13: [2023-04-29 11:37:27,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +13: [2023-04-29 11:37:27,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +13: [2023-04-29 11:37:27,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +37: [2023-04-29 11:37:27,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +37: [2023-04-29 11:37:27,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +37: [2023-04-29 11:37:27,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +37: [2023-04-29 11:37:27,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +37: [2023-04-29 11:37:27,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +13: [2023-04-29 11:37:27,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +37: [2023-04-29 11:37:27,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 4: [2023-04-29 11:37:27,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +62: [2023-04-29 11:37:27,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +10: [2023-04-29 11:37:27,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +53: [2023-04-29 11:37:27,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +24: [2023-04-29 11:37:27,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +44: [2023-04-29 11:37:27,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +59: [2023-04-29 11:37:27,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +37: [2023-04-29 11:37:27,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +24: [2023-04-29 11:37:27,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +55: [2023-04-29 11:37:27,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +55: [2023-04-29 11:37:27,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +55: [2023-04-29 11:37:27,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +59: [2023-04-29 11:37:27,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +55: [2023-04-29 11:37:27,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +49: [2023-04-29 11:37:27,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +59: [2023-04-29 11:37:27,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +20: [2023-04-29 11:37:27,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +20: [2023-04-29 11:37:27,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +20: [2023-04-29 11:37:27,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +20: [2023-04-29 11:37:27,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +21: [2023-04-29 11:37:27,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +50: [2023-04-29 11:37:27,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +21: [2023-04-29 11:37:27,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +59: [2023-04-29 11:37:27,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +21: [2023-04-29 11:37:27,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +40: [2023-04-29 11:37:27,667] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +40: [2023-04-29 11:37:27,667] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +21: [2023-04-29 11:37:27,667] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +37: [2023-04-29 11:37:27,667] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +45: [2023-04-29 11:37:27,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +45: [2023-04-29 11:37:27,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +40: [2023-04-29 11:37:27,667] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +45: [2023-04-29 11:37:27,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +45: [2023-04-29 11:37:27,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +45: [2023-04-29 11:37:27,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +45: [2023-04-29 11:37:27,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +62: [2023-04-29 11:37:27,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 4: [2023-04-29 11:37:27,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... + 4: [2023-04-29 11:37:27,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +45: [2023-04-29 11:37:27,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +45: [2023-04-29 11:37:27,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +40: [2023-04-29 11:37:27,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +20: [2023-04-29 11:37:27,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +20: [2023-04-29 11:37:27,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +37: [2023-04-29 11:37:27,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +32: [2023-04-29 11:37:27,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +32: [2023-04-29 11:37:27,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +56: [2023-04-29 11:37:27,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +56: [2023-04-29 11:37:27,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +56: [2023-04-29 11:37:27,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +37: [2023-04-29 11:37:27,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +37: [2023-04-29 11:37:27,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +56: [2023-04-29 11:37:27,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +28: [2023-04-29 11:37:27,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +28: [2023-04-29 11:37:27,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +28: [2023-04-29 11:37:27,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +28: [2023-04-29 11:37:27,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +37: [2023-04-29 11:37:27,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +37: [2023-04-29 11:37:27,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +37: [2023-04-29 11:37:27,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +20: [2023-04-29 11:37:27,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +20: [2023-04-29 11:37:27,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +61: [2023-04-29 11:37:27,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +61: [2023-04-29 11:37:27,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +36: [2023-04-29 11:37:27,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +36: [2023-04-29 11:37:27,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +36: [2023-04-29 11:37:27,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +36: [2023-04-29 11:37:27,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +45: [2023-04-29 11:37:27,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +45: [2023-04-29 11:37:27,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +47: [2023-04-29 11:37:27,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +47: [2023-04-29 11:37:27,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +45: [2023-04-29 11:37:27,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +20: [2023-04-29 11:37:27,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +20: [2023-04-29 11:37:27,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +50: [2023-04-29 11:37:27,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +61: [2023-04-29 11:37:27,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +45: [2023-04-29 11:37:27,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +61: [2023-04-29 11:37:27,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +54: [2023-04-29 11:37:27,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +54: [2023-04-29 11:37:27,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +35: [2023-04-29 11:37:27,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +47: [2023-04-29 11:37:27,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +59: [2023-04-29 11:37:27,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +59: [2023-04-29 11:37:27,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +47: [2023-04-29 11:37:27,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +47: [2023-04-29 11:37:27,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +47: [2023-04-29 11:37:27,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +62: [2023-04-29 11:37:27,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +20: [2023-04-29 11:37:27,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +32: [2023-04-29 11:37:27,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +42: [2023-04-29 11:37:27,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +42: [2023-04-29 11:37:27,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +42: [2023-04-29 11:37:27,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +59: [2023-04-29 11:37:27,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +59: [2023-04-29 11:37:27,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +54: [2023-04-29 11:37:27,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +54: [2023-04-29 11:37:27,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +52: [2023-04-29 11:37:27,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +20: [2023-04-29 11:37:27,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +44: [2023-04-29 11:37:27,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +25: [2023-04-29 11:37:27,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +47: [2023-04-29 11:37:27,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +58: [2023-04-29 11:37:27,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +47: [2023-04-29 11:37:27,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +50: [2023-04-29 11:37:27,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +20: [2023-04-29 11:37:27,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +20: [2023-04-29 11:37:27,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +32: [2023-04-29 11:37:27,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +62: [2023-04-29 11:37:27,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 8: [2023-04-29 11:37:27,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +52: [2023-04-29 11:37:27,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +25: [2023-04-29 11:37:27,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +58: [2023-04-29 11:37:27,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +58: [2023-04-29 11:37:27,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +58: [2023-04-29 11:37:27,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +25: [2023-04-29 11:37:27,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +49: [2023-04-29 11:37:27,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +44: [2023-04-29 11:37:27,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +25: [2023-04-29 11:37:27,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 4: [2023-04-29 11:37:27,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 8: [2023-04-29 11:37:27,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +49: [2023-04-29 11:37:27,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +20: [2023-04-29 11:37:27,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +49: [2023-04-29 11:37:27,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +51: [2023-04-29 11:37:27,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +51: [2023-04-29 11:37:27,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 4: [2023-04-29 11:37:27,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +38: [2023-04-29 11:37:27,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +38: [2023-04-29 11:37:27,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +38: [2023-04-29 11:37:27,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +38: [2023-04-29 11:37:27,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +47: [2023-04-29 11:37:27,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +47: [2023-04-29 11:37:27,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +47: [2023-04-29 11:37:27,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +47: [2023-04-29 11:37:27,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +34: [2023-04-29 11:37:27,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +34: [2023-04-29 11:37:27,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +40: [2023-04-29 11:37:27,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +60: [2023-04-29 11:37:27,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +60: [2023-04-29 11:37:27,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +60: [2023-04-29 11:37:27,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +60: [2023-04-29 11:37:27,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +13: [2023-04-29 11:37:27,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +51: [2023-04-29 11:37:27,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +51: [2023-04-29 11:37:27,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +51: [2023-04-29 11:37:27,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 8: [2023-04-29 11:37:27,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +20: [2023-04-29 11:37:27,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +52: [2023-04-29 11:37:27,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +52: [2023-04-29 11:37:27,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +44: [2023-04-29 11:37:27,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +55: [2023-04-29 11:37:27,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +51: [2023-04-29 11:37:27,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +55: [2023-04-29 11:37:27,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +42: [2023-04-29 11:37:27,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +52: [2023-04-29 11:37:27,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +55: [2023-04-29 11:37:27,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +51: [2023-04-29 11:37:27,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +53: [2023-04-29 11:37:27,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +10: [2023-04-29 11:37:27,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +24: [2023-04-29 11:37:27,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +10: [2023-04-29 11:37:27,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +10: [2023-04-29 11:37:27,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. + 4: [2023-04-29 11:37:27,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +10: [2023-04-29 11:37:27,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +53: [2023-04-29 11:37:27,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +24: [2023-04-29 11:37:27,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +35: [2023-04-29 11:37:27,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +53: [2023-04-29 11:37:27,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +13: [2023-04-29 11:37:27,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 4: [2023-04-29 11:37:27,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +35: [2023-04-29 11:37:27,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +35: [2023-04-29 11:37:27,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +34: [2023-04-29 11:37:27,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +13: [2023-04-29 11:37:27,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 8: [2023-04-29 11:37:27,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +34: [2023-04-29 11:37:27,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +52: [2023-04-29 11:37:27,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +55: [2023-04-29 11:37:27,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +13: [2023-04-29 11:37:27,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +40: [2023-04-29 11:37:27,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +24: [2023-04-29 11:37:27,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +17: [2023-04-29 11:37:27,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +17: [2023-04-29 11:37:27,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +17: [2023-04-29 11:37:27,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +24: [2023-04-29 11:37:27,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +17: [2023-04-29 11:37:27,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +60: [2023-04-29 11:37:27,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 8: [2023-04-29 11:37:27,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +60: [2023-04-29 11:37:27,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +51: [2023-04-29 11:37:27,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +60: [2023-04-29 11:37:27,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +53: [2023-04-29 11:37:27,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +28: [2023-04-29 11:37:27,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +60: [2023-04-29 11:37:27,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +40: [2023-04-29 11:37:27,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +45: [2023-04-29 11:37:27,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +45: [2023-04-29 11:37:27,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +36: [2023-04-29 11:37:27,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 8: [2023-04-29 11:37:27,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +52: [2023-04-29 11:37:27,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +45: [2023-04-29 11:37:27,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +45: [2023-04-29 11:37:27,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +56: [2023-04-29 11:37:27,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +56: [2023-04-29 11:37:27,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +56: [2023-04-29 11:37:27,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +40: [2023-04-29 11:37:27,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +56: [2023-04-29 11:37:27,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +35: [2023-04-29 11:37:27,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +28: [2023-04-29 11:37:27,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +41: [2023-04-29 11:37:27,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +28: [2023-04-29 11:37:27,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +52: [2023-04-29 11:37:27,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +61: [2023-04-29 11:37:27,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +28: [2023-04-29 11:37:27,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +36: [2023-04-29 11:37:27,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +61: [2023-04-29 11:37:27,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +36: [2023-04-29 11:37:27,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +41: [2023-04-29 11:37:27,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +61: [2023-04-29 11:37:27,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +47: [2023-04-29 11:37:27,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +47: [2023-04-29 11:37:27,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +47: [2023-04-29 11:37:27,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +60: [2023-04-29 11:37:27,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +60: [2023-04-29 11:37:27,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +60: [2023-04-29 11:37:27,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +61: [2023-04-29 11:37:27,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +54: [2023-04-29 11:37:27,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +60: [2023-04-29 11:37:27,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +54: [2023-04-29 11:37:27,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 8: [2023-04-29 11:37:27,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +54: [2023-04-29 11:37:27,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +54: [2023-04-29 11:37:27,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 8: [2023-04-29 11:37:27,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +36: [2023-04-29 11:37:27,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +27: [2023-04-29 11:37:27,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +47: [2023-04-29 11:37:27,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +41: [2023-04-29 11:37:27,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +41: [2023-04-29 11:37:27,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +62: [2023-04-29 11:37:27,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 6: [2023-04-29 11:37:27,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 6: [2023-04-29 11:37:27,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 6: [2023-04-29 11:37:27,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 6: [2023-04-29 11:37:27,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +27: [2023-04-29 11:37:27,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +11: [2023-04-29 11:37:27,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +11: [2023-04-29 11:37:27,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +27: [2023-04-29 11:37:27,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +27: [2023-04-29 11:37:27,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +34: [2023-04-29 11:37:27,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +62: [2023-04-29 11:37:27,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +62: [2023-04-29 11:37:27,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +34: [2023-04-29 11:37:27,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +17: [2023-04-29 11:37:27,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +62: [2023-04-29 11:37:27,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +62: [2023-04-29 11:37:27,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +62: [2023-04-29 11:37:27,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 4: [2023-04-29 11:37:27,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +11: [2023-04-29 11:37:27,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +11: [2023-04-29 11:37:27,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 6: [2023-04-29 11:37:27,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +59: [2023-04-29 11:37:27,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +38: [2023-04-29 11:37:27,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 6: [2023-04-29 11:37:27,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 6: [2023-04-29 11:37:27,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 6: [2023-04-29 11:37:27,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +11: [2023-04-29 11:37:27,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +38: [2023-04-29 11:37:27,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +37: [2023-04-29 11:37:27,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +11: [2023-04-29 11:37:27,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +53: [2023-04-29 11:37:27,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +10: [2023-04-29 11:37:27,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +41: [2023-04-29 11:37:27,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +41: [2023-04-29 11:37:27,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +17: [2023-04-29 11:37:27,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +38: [2023-04-29 11:37:27,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +62: [2023-04-29 11:37:27,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +51: [2023-04-29 11:37:27,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +11: [2023-04-29 11:37:27,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +11: [2023-04-29 11:37:27,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +34: [2023-04-29 11:37:27,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +35: [2023-04-29 11:37:27,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +17: [2023-04-29 11:37:27,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +35: [2023-04-29 11:37:27,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +10: [2023-04-29 11:37:27,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +59: [2023-04-29 11:37:27,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +17: [2023-04-29 11:37:27,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +10: [2023-04-29 11:37:27,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +35: [2023-04-29 11:37:27,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +38: [2023-04-29 11:37:27,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +59: [2023-04-29 11:37:27,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +59: [2023-04-29 11:37:27,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +34: [2023-04-29 11:37:27,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +62: [2023-04-29 11:37:27,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +62: [2023-04-29 11:37:27,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +51: [2023-04-29 11:37:27,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +62: [2023-04-29 11:37:27,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +10: [2023-04-29 11:37:27,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +21: [2023-04-29 11:37:27,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 8: [2023-04-29 11:37:27,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +41: [2023-04-29 11:37:27,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 8: [2023-04-29 11:37:27,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +51: [2023-04-29 11:37:27,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +41: [2023-04-29 11:37:27,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +38: [2023-04-29 11:37:27,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +51: [2023-04-29 11:37:27,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +38: [2023-04-29 11:37:27,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +38: [2023-04-29 11:37:27,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +38: [2023-04-29 11:37:27,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 8: [2023-04-29 11:37:27,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +20: [2023-04-29 11:37:27,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 4: [2023-04-29 11:37:27,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 4: [2023-04-29 11:37:27,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 4: [2023-04-29 11:37:27,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +41: [2023-04-29 11:37:27,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +60: [2023-04-29 11:37:27,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +14: [2023-04-29 11:37:27,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +14: [2023-04-29 11:37:27,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. + 8: [2023-04-29 11:37:27,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +20: [2023-04-29 11:37:27,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +53: [2023-04-29 11:37:27,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +53: [2023-04-29 11:37:27,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +53: [2023-04-29 11:37:27,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +14: [2023-04-29 11:37:27,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +29: [2023-04-29 11:37:27,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +29: [2023-04-29 11:37:27,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +14: [2023-04-29 11:37:27,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +38: [2023-04-29 11:37:27,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +27: [2023-04-29 11:37:27,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +29: [2023-04-29 11:37:27,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +29: [2023-04-29 11:37:27,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +41: [2023-04-29 11:37:27,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +60: [2023-04-29 11:37:27,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +38: [2023-04-29 11:37:27,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +38: [2023-04-29 11:37:27,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +38: [2023-04-29 11:37:27,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +21: [2023-04-29 11:37:27,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +21: [2023-04-29 11:37:27,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +21: [2023-04-29 11:37:27,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +15: [2023-04-29 11:37:27,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +15: [2023-04-29 11:37:27,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +15: [2023-04-29 11:37:27,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +41: [2023-04-29 11:37:27,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +15: [2023-04-29 11:37:27,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +27: [2023-04-29 11:37:27,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +20: [2023-04-29 11:37:27,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +60: [2023-04-29 11:37:27,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +27: [2023-04-29 11:37:27,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +41: [2023-04-29 11:37:27,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +51: [2023-04-29 11:37:27,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +29: [2023-04-29 11:37:27,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 4: [2023-04-29 11:37:27,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +29: [2023-04-29 11:37:27,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +11: [2023-04-29 11:37:27,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +11: [2023-04-29 11:37:27,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +11: [2023-04-29 11:37:27,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +27: [2023-04-29 11:37:27,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +36: [2023-04-29 11:37:27,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +36: [2023-04-29 11:37:27,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +29: [2023-04-29 11:37:27,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +11: [2023-04-29 11:37:27,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +60: [2023-04-29 11:37:27,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +29: [2023-04-29 11:37:27,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 0: [2023-04-29 11:37:27,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. + 0: [2023-04-29 11:37:27,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +53: [2023-04-29 11:37:27,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +36: [2023-04-29 11:37:27,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +36: [2023-04-29 11:37:27,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +10: [2023-04-29 11:37:27,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +12: [2023-04-29 11:37:27,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +12: [2023-04-29 11:37:27,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +10: [2023-04-29 11:37:27,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +10: [2023-04-29 11:37:27,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +37: [2023-04-29 11:37:27,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 2: [2023-04-29 11:37:27,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. + 2: [2023-04-29 11:37:27,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. + 0: [2023-04-29 11:37:27,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. + 0: [2023-04-29 11:37:27,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +12: [2023-04-29 11:37:27,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +21: [2023-04-29 11:37:27,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +12: [2023-04-29 11:37:27,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +45: [2023-04-29 11:37:27,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +51: [2023-04-29 11:37:27,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +20: [2023-04-29 11:37:27,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +59: [2023-04-29 11:37:27,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +36: [2023-04-29 11:37:27,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +36: [2023-04-29 11:37:27,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +51: [2023-04-29 11:37:27,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +41: [2023-04-29 11:37:27,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +21: [2023-04-29 11:37:27,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. + 2: [2023-04-29 11:37:27,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +10: [2023-04-29 11:37:27,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 2: [2023-04-29 11:37:27,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +45: [2023-04-29 11:37:27,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +37: [2023-04-29 11:37:27,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +37: [2023-04-29 11:37:27,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +37: [2023-04-29 11:37:27,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 7: [2023-04-29 11:37:27,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. + 7: [2023-04-29 11:37:27,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +59: [2023-04-29 11:37:27,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +59: [2023-04-29 11:37:27,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +36: [2023-04-29 11:37:27,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +36: [2023-04-29 11:37:27,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +59: [2023-04-29 11:37:27,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +21: [2023-04-29 11:37:27,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +21: [2023-04-29 11:37:27,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +51: [2023-04-29 11:37:27,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +39: [2023-04-29 11:37:27,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +39: [2023-04-29 11:37:27,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. + 7: [2023-04-29 11:37:27,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. + 7: [2023-04-29 11:37:27,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +21: [2023-04-29 11:37:27,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +39: [2023-04-29 11:37:27,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +39: [2023-04-29 11:37:27,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +43: [2023-04-29 11:37:27,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +43: [2023-04-29 11:37:27,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +43: [2023-04-29 11:37:27,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +20: [2023-04-29 11:37:27,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +43: [2023-04-29 11:37:27,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. + 8: [2023-04-29 11:37:27,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 8: [2023-04-29 11:37:27,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +39: [2023-04-29 11:37:27,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +14: [2023-04-29 11:37:27,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +39: [2023-04-29 11:37:27,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +20: [2023-04-29 11:37:27,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +61: [2023-04-29 11:37:27,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +61: [2023-04-29 11:37:27,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 4: [2023-04-29 11:37:27,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +47: [2023-04-29 11:37:27,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +41: [2023-04-29 11:37:27,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 4: [2023-04-29 11:37:27,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 4: [2023-04-29 11:37:27,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +61: [2023-04-29 11:37:27,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +36: [2023-04-29 11:37:27,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +39: [2023-04-29 11:37:27,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +39: [2023-04-29 11:37:27,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +14: [2023-04-29 11:37:27,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +14: [2023-04-29 11:37:27,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +14: [2023-04-29 11:37:27,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +61: [2023-04-29 11:37:27,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +47: [2023-04-29 11:37:27,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +39: [2023-04-29 11:37:27,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +14: [2023-04-29 11:37:27,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +14: [2023-04-29 11:37:27,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +14: [2023-04-29 11:37:27,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 7: [2023-04-29 11:37:27,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 7: [2023-04-29 11:37:27,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +63: [2023-04-29 11:37:27,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +63: [2023-04-29 11:37:27,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +63: [2023-04-29 11:37:27,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +14: [2023-04-29 11:37:27,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +20: [2023-04-29 11:37:27,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +45: [2023-04-29 11:37:27,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +53: [2023-04-29 11:37:27,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +63: [2023-04-29 11:37:27,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +53: [2023-04-29 11:37:27,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +39: [2023-04-29 11:37:27,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +53: [2023-04-29 11:37:27,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +45: [2023-04-29 11:37:27,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +21: [2023-04-29 11:37:27,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +15: [2023-04-29 11:37:27,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +15: [2023-04-29 11:37:27,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +36: [2023-04-29 11:37:27,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +56: [2023-04-29 11:37:27,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +56: [2023-04-29 11:37:27,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +56: [2023-04-29 11:37:27,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +56: [2023-04-29 11:37:27,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +39: [2023-04-29 11:37:27,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +36: [2023-04-29 11:37:27,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... + 7: [2023-04-29 11:37:27,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +53: [2023-04-29 11:37:27,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +56: [2023-04-29 11:37:27,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +56: [2023-04-29 11:37:27,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +63: [2023-04-29 11:37:27,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +63: [2023-04-29 11:37:27,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +26: [2023-04-29 11:37:27,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +26: [2023-04-29 11:37:27,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +26: [2023-04-29 11:37:27,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +26: [2023-04-29 11:37:27,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +15: [2023-04-29 11:37:27,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +15: [2023-04-29 11:37:27,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +60: [2023-04-29 11:37:27,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +60: [2023-04-29 11:37:27,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 2: [2023-04-29 11:37:27,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +21: [2023-04-29 11:37:27,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +16: [2023-04-29 11:37:27,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +16: [2023-04-29 11:37:27,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +61: [2023-04-29 11:37:27,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +63: [2023-04-29 11:37:27,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +63: [2023-04-29 11:37:27,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +14: [2023-04-29 11:37:27,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 2: [2023-04-29 11:37:27,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 2: [2023-04-29 11:37:27,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +53: [2023-04-29 11:37:27,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +53: [2023-04-29 11:37:27,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +11: [2023-04-29 11:37:27,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +11: [2023-04-29 11:37:27,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +11: [2023-04-29 11:37:27,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +16: [2023-04-29 11:37:27,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +39: [2023-04-29 11:37:27,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +14: [2023-04-29 11:37:27,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +16: [2023-04-29 11:37:27,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +16: [2023-04-29 11:37:27,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +16: [2023-04-29 11:37:27,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +16: [2023-04-29 11:37:27,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +61: [2023-04-29 11:37:27,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +41: [2023-04-29 11:37:27,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +41: [2023-04-29 11:37:27,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +12: [2023-04-29 11:37:27,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 0: [2023-04-29 11:37:27,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +16: [2023-04-29 11:37:27,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +61: [2023-04-29 11:37:27,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 0: [2023-04-29 11:37:27,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +12: [2023-04-29 11:37:27,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +10: [2023-04-29 11:37:27,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +12: [2023-04-29 11:37:27,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 0: [2023-04-29 11:37:27,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +14: [2023-04-29 11:37:27,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +36: [2023-04-29 11:37:27,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +14: [2023-04-29 11:37:27,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +47: [2023-04-29 11:37:27,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +47: [2023-04-29 11:37:27,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 2: [2023-04-29 11:37:27,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +21: [2023-04-29 11:37:27,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +56: [2023-04-29 11:37:27,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +10: [2023-04-29 11:37:27,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +10: [2023-04-29 11:37:27,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +56: [2023-04-29 11:37:27,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +20: [2023-04-29 11:37:27,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +45: [2023-04-29 11:37:27,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +31: [2023-04-29 11:37:27,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +31: [2023-04-29 11:37:27,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +31: [2023-04-29 11:37:27,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +11: [2023-04-29 11:37:27,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 0: [2023-04-29 11:37:27,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +31: [2023-04-29 11:37:27,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +45: [2023-04-29 11:37:27,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +56: [2023-04-29 11:37:27,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +56: [2023-04-29 11:37:27,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +61: [2023-04-29 11:37:27,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +56: [2023-04-29 11:37:27,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +61: [2023-04-29 11:37:27,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +45: [2023-04-29 11:37:27,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +56: [2023-04-29 11:37:27,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +12: [2023-04-29 11:37:27,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +60: [2023-04-29 11:37:27,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +45: [2023-04-29 11:37:27,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +16: [2023-04-29 11:37:27,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +16: [2023-04-29 11:37:27,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +56: [2023-04-29 11:37:27,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +56: [2023-04-29 11:37:27,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +53: [2023-04-29 11:37:27,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +21: [2023-04-29 11:37:27,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +10: [2023-04-29 11:37:27,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +47: [2023-04-29 11:37:27,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 7: [2023-04-29 11:37:27,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +45: [2023-04-29 11:37:27,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +53: [2023-04-29 11:37:27,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +53: [2023-04-29 11:37:27,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... + 7: [2023-04-29 11:37:27,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +60: [2023-04-29 11:37:27,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +37: [2023-04-29 11:37:27,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +37: [2023-04-29 11:37:27,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +56: [2023-04-29 11:37:27,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +56: [2023-04-29 11:37:27,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +31: [2023-04-29 11:37:27,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +45: [2023-04-29 11:37:27,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +47: [2023-04-29 11:37:27,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +31: [2023-04-29 11:37:27,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +21: [2023-04-29 11:37:27,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +31: [2023-04-29 11:37:27,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +31: [2023-04-29 11:37:27,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +45: [2023-04-29 11:37:27,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +37: [2023-04-29 11:37:27,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +45: [2023-04-29 11:37:27,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... + 6: [2023-04-29 11:37:27,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 6: [2023-04-29 11:37:27,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +21: [2023-04-29 11:37:27,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +16: [2023-04-29 11:37:27,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +59: [2023-04-29 11:37:27,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +61: [2023-04-29 11:37:27,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +61: [2023-04-29 11:37:27,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +53: [2023-04-29 11:37:27,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +16: [2023-04-29 11:37:27,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +39: [2023-04-29 11:37:27,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +16: [2023-04-29 11:37:27,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +61: [2023-04-29 11:37:27,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +36: [2023-04-29 11:37:27,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +61: [2023-04-29 11:37:27,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +43: [2023-04-29 11:37:27,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +43: [2023-04-29 11:37:27,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +59: [2023-04-29 11:37:27,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +16: [2023-04-29 11:37:27,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... +43: [2023-04-29 11:37:27,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +59: [2023-04-29 11:37:27,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +16: [2023-04-29 11:37:27,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt... +16: [2023-04-29 11:37:27,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt... + 6: [2023-04-29 11:37:27,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 6: [2023-04-29 11:37:27,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +47: [2023-04-29 11:37:27,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +52: [2023-04-29 11:37:27,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +52: [2023-04-29 11:37:27,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +52: [2023-04-29 11:37:27,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +52: [2023-04-29 11:37:27,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +47: [2023-04-29 11:37:27,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +47: [2023-04-29 11:37:27,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +47: [2023-04-29 11:37:27,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +43: [2023-04-29 11:37:27,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +39: [2023-04-29 11:37:27,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +59: [2023-04-29 11:37:27,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +36: [2023-04-29 11:37:27,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +45: [2023-04-29 11:37:27,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +53: [2023-04-29 11:37:27,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +38: [2023-04-29 11:37:27,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +21: [2023-04-29 11:37:27,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +39: [2023-04-29 11:37:27,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +52: [2023-04-29 11:37:27,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +11: [2023-04-29 11:37:27,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +47: [2023-04-29 11:37:27,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +52: [2023-04-29 11:37:27,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +47: [2023-04-29 11:37:27,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +52: [2023-04-29 11:37:27,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +11: [2023-04-29 11:37:27,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +52: [2023-04-29 11:37:27,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +36: [2023-04-29 11:37:27,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +45: [2023-04-29 11:37:27,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +63: [2023-04-29 11:37:27,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +63: [2023-04-29 11:37:27,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +39: [2023-04-29 11:37:27,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +10: [2023-04-29 11:37:27,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +38: [2023-04-29 11:37:27,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +38: [2023-04-29 11:37:27,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +47: [2023-04-29 11:37:27,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... + 3: [2023-04-29 11:37:27,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 3: [2023-04-29 11:37:27,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 3: [2023-04-29 11:37:27,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +47: [2023-04-29 11:37:27,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... + 3: [2023-04-29 11:37:27,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +63: [2023-04-29 11:37:27,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +63: [2023-04-29 11:37:27,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_29-model_01-model_states.pt. +61: [2023-04-29 11:37:27,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +45: [2023-04-29 11:37:27,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +61: [2023-04-29 11:37:27,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +26: [2023-04-29 11:37:27,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +61: [2023-04-29 11:37:27,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +45: [2023-04-29 11:37:27,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +38: [2023-04-29 11:37:27,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +36: [2023-04-29 11:37:27,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +10: [2023-04-29 11:37:27,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +38: [2023-04-29 11:37:27,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 3: [2023-04-29 11:37:27,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 3: [2023-04-29 11:37:27,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +38: [2023-04-29 11:37:27,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +11: [2023-04-29 11:37:27,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +38: [2023-04-29 11:37:27,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +59: [2023-04-29 11:37:27,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +26: [2023-04-29 11:37:27,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +26: [2023-04-29 11:37:27,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 3: [2023-04-29 11:37:27,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +26: [2023-04-29 11:37:27,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +47: [2023-04-29 11:37:27,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +10: [2023-04-29 11:37:27,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 3: [2023-04-29 11:37:27,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +29: [2023-04-29 11:37:27,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +60: [2023-04-29 11:37:27,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +47: [2023-04-29 11:37:27,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +60: [2023-04-29 11:37:27,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +10: [2023-04-29 11:37:27,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +10: [2023-04-29 11:37:27,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +59: [2023-04-29 11:37:27,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +59: [2023-04-29 11:37:27,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +15: [2023-04-29 11:37:27,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +15: [2023-04-29 11:37:27,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +15: [2023-04-29 11:37:27,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +15: [2023-04-29 11:37:27,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +18: [2023-04-29 11:37:27,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +18: [2023-04-29 11:37:27,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +18: [2023-04-29 11:37:27,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +18: [2023-04-29 11:37:27,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +18: [2023-04-29 11:37:27,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +18: [2023-04-29 11:37:27,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +18: [2023-04-29 11:37:27,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +18: [2023-04-29 11:37:27,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +59: [2023-04-29 11:37:27,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +24: [2023-04-29 11:37:27,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +24: [2023-04-29 11:37:27,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +24: [2023-04-29 11:37:27,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +24: [2023-04-29 11:37:27,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +10: [2023-04-29 11:37:27,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +24: [2023-04-29 11:37:27,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +24: [2023-04-29 11:37:27,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +38: [2023-04-29 11:37:27,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +24: [2023-04-29 11:37:27,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +24: [2023-04-29 11:37:27,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +57: [2023-04-29 11:37:27,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +57: [2023-04-29 11:37:27,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 6: [2023-04-29 11:37:27,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 6: [2023-04-29 11:37:27,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +38: [2023-04-29 11:37:27,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +55: [2023-04-29 11:37:27,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +55: [2023-04-29 11:37:27,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +18: [2023-04-29 11:37:27,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 1: [2023-04-29 11:37:27,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +42: [2023-04-29 11:37:27,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +42: [2023-04-29 11:37:27,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. + 1: [2023-04-29 11:37:27,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 1: [2023-04-29 11:37:27,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +60: [2023-04-29 11:37:27,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 1: [2023-04-29 11:37:27,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +59: [2023-04-29 11:37:27,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +18: [2023-04-29 11:37:27,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +18: [2023-04-29 11:37:27,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +15: [2023-04-29 11:37:27,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +57: [2023-04-29 11:37:27,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +57: [2023-04-29 11:37:27,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +15: [2023-04-29 11:37:27,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 5: [2023-04-29 11:37:27,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. + 5: [2023-04-29 11:37:27,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +15: [2023-04-29 11:37:27,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +57: [2023-04-29 11:37:27,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +57: [2023-04-29 11:37:27,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +57: [2023-04-29 11:37:27,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +57: [2023-04-29 11:37:27,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +15: [2023-04-29 11:37:27,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +10: [2023-04-29 11:37:27,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +38: [2023-04-29 11:37:27,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +24: [2023-04-29 11:37:27,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +24: [2023-04-29 11:37:27,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +24: [2023-04-29 11:37:27,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +38: [2023-04-29 11:37:27,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +24: [2023-04-29 11:37:27,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +59: [2023-04-29 11:37:27,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +55: [2023-04-29 11:37:27,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +55: [2023-04-29 11:37:27,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +55: [2023-04-29 11:37:27,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +55: [2023-04-29 11:37:27,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +55: [2023-04-29 11:37:27,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +55: [2023-04-29 11:37:27,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +59: [2023-04-29 11:37:27,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +36: [2023-04-29 11:37:27,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +36: [2023-04-29 11:37:27,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 6: [2023-04-29 11:37:27,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +24: [2023-04-29 11:37:27,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... + 6: [2023-04-29 11:37:27,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +24: [2023-04-29 11:37:27,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +18: [2023-04-29 11:37:27,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +18: [2023-04-29 11:37:27,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +10: [2023-04-29 11:37:27,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +38: [2023-04-29 11:37:27,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +24: [2023-04-29 11:37:27,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +60: [2023-04-29 11:37:27,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +42: [2023-04-29 11:37:27,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +11: [2023-04-29 11:37:27,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +24: [2023-04-29 11:37:27,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +18: [2023-04-29 11:37:27,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +60: [2023-04-29 11:37:27,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +57: [2023-04-29 11:37:27,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 5: [2023-04-29 11:37:27,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +60: [2023-04-29 11:37:27,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 5: [2023-04-29 11:37:27,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +57: [2023-04-29 11:37:27,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +18: [2023-04-29 11:37:27,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +17: [2023-04-29 11:37:27,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +17: [2023-04-29 11:37:27,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 1: [2023-04-29 11:37:27,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +17: [2023-04-29 11:37:27,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +17: [2023-04-29 11:37:27,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +17: [2023-04-29 11:37:27,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +17: [2023-04-29 11:37:27,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +17: [2023-04-29 11:37:27,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +17: [2023-04-29 11:37:27,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +60: [2023-04-29 11:37:27,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +29: [2023-04-29 11:37:27,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +29: [2023-04-29 11:37:27,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +29: [2023-04-29 11:37:27,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 1: [2023-04-29 11:37:27,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +11: [2023-04-29 11:37:27,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +18: [2023-04-29 11:37:27,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +57: [2023-04-29 11:37:27,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +57: [2023-04-29 11:37:27,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +59: [2023-04-29 11:37:27,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +60: [2023-04-29 11:37:27,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +55: [2023-04-29 11:37:27,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... + 1: [2023-04-29 11:37:27,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +55: [2023-04-29 11:37:27,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +55: [2023-04-29 11:37:27,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +57: [2023-04-29 11:37:27,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +57: [2023-04-29 11:37:27,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +57: [2023-04-29 11:37:27,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +55: [2023-04-29 11:37:27,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +55: [2023-04-29 11:37:27,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +57: [2023-04-29 11:37:27,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... + 1: [2023-04-29 11:37:27,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +22: [2023-04-29 11:37:27,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +22: [2023-04-29 11:37:27,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +22: [2023-04-29 11:37:27,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +23: [2023-04-29 11:37:27,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +23: [2023-04-29 11:37:27,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +22: [2023-04-29 11:37:27,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +55: [2023-04-29 11:37:27,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +17: [2023-04-29 11:37:27,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +55: [2023-04-29 11:37:27,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +11: [2023-04-29 11:37:27,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +63: [2023-04-29 11:37:27,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +49: [2023-04-29 11:37:27,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +49: [2023-04-29 11:37:27,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +55: [2023-04-29 11:37:27,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +49: [2023-04-29 11:37:27,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +38: [2023-04-29 11:37:27,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +17: [2023-04-29 11:37:27,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +49: [2023-04-29 11:37:27,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +32: [2023-04-29 11:37:27,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +32: [2023-04-29 11:37:27,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +23: [2023-04-29 11:37:27,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. + 1: [2023-04-29 11:37:27,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. + 1: [2023-04-29 11:37:27,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +23: [2023-04-29 11:37:27,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +17: [2023-04-29 11:37:27,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +17: [2023-04-29 11:37:27,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +63: [2023-04-29 11:37:27,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +17: [2023-04-29 11:37:27,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +17: [2023-04-29 11:37:27,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +17: [2023-04-29 11:37:27,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +60: [2023-04-29 11:37:27,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +14: [2023-04-29 11:37:27,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +60: [2023-04-29 11:37:27,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +17: [2023-04-29 11:37:27,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +60: [2023-04-29 11:37:27,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +32: [2023-04-29 11:37:27,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +48: [2023-04-29 11:37:27,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +48: [2023-04-29 11:37:27,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +32: [2023-04-29 11:37:27,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +60: [2023-04-29 11:37:27,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +22: [2023-04-29 11:37:27,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +22: [2023-04-29 11:37:27,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +22: [2023-04-29 11:37:27,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +36: [2023-04-29 11:37:27,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +22: [2023-04-29 11:37:27,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +11: [2023-04-29 11:37:27,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +48: [2023-04-29 11:37:27,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +48: [2023-04-29 11:37:27,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +63: [2023-04-29 11:37:27,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +63: [2023-04-29 11:37:27,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +48: [2023-04-29 11:37:27,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +48: [2023-04-29 11:37:27,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +48: [2023-04-29 11:37:27,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 1: [2023-04-29 11:37:27,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +48: [2023-04-29 11:37:27,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 1: [2023-04-29 11:37:27,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +34: [2023-04-29 11:37:27,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +34: [2023-04-29 11:37:27,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +29: [2023-04-29 11:37:27,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +43: [2023-04-29 11:37:27,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +43: [2023-04-29 11:37:27,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +14: [2023-04-29 11:37:27,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +43: [2023-04-29 11:37:27,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +43: [2023-04-29 11:37:27,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +42: [2023-04-29 11:37:27,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +34: [2023-04-29 11:37:27,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +34: [2023-04-29 11:37:27,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +34: [2023-04-29 11:37:27,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +34: [2023-04-29 11:37:27,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +34: [2023-04-29 11:37:27,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +48: [2023-04-29 11:37:27,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 3: [2023-04-29 11:37:27,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. + 3: [2023-04-29 11:37:27,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. + 3: [2023-04-29 11:37:27,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +34: [2023-04-29 11:37:27,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 3: [2023-04-29 11:37:27,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +48: [2023-04-29 11:37:27,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +48: [2023-04-29 11:37:27,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +48: [2023-04-29 11:37:27,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +48: [2023-04-29 11:37:27,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +43: [2023-04-29 11:37:27,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +43: [2023-04-29 11:37:27,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +43: [2023-04-29 11:37:27,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +36: [2023-04-29 11:37:27,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +48: [2023-04-29 11:37:27,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +48: [2023-04-29 11:37:27,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +50: [2023-04-29 11:37:27,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +50: [2023-04-29 11:37:27,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +50: [2023-04-29 11:37:27,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +48: [2023-04-29 11:37:27,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +34: [2023-04-29 11:37:27,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +34: [2023-04-29 11:37:27,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +43: [2023-04-29 11:37:27,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +50: [2023-04-29 11:37:27,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +39: [2023-04-29 11:37:27,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +21: [2023-04-29 11:37:27,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +28: [2023-04-29 11:37:27,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +28: [2023-04-29 11:37:27,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +28: [2023-04-29 11:37:27,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +28: [2023-04-29 11:37:27,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +28: [2023-04-29 11:37:27,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +28: [2023-04-29 11:37:27,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +28: [2023-04-29 11:37:27,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +28: [2023-04-29 11:37:27,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +14: [2023-04-29 11:37:27,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +14: [2023-04-29 11:37:27,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +58: [2023-04-29 11:37:27,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +58: [2023-04-29 11:37:27,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +58: [2023-04-29 11:37:27,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +34: [2023-04-29 11:37:27,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +34: [2023-04-29 11:37:27,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +58: [2023-04-29 11:37:27,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +15: [2023-04-29 11:37:27,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +40: [2023-04-29 11:37:27,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +40: [2023-04-29 11:37:27,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +40: [2023-04-29 11:37:27,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +63: [2023-04-29 11:37:27,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +40: [2023-04-29 11:37:27,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +56: [2023-04-29 11:37:27,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +56: [2023-04-29 11:37:27,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +14: [2023-04-29 11:37:27,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +42: [2023-04-29 11:37:27,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +39: [2023-04-29 11:37:27,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +39: [2023-04-29 11:37:27,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 5: [2023-04-29 11:37:27,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +42: [2023-04-29 11:37:27,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +42: [2023-04-29 11:37:27,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 0: [2023-04-29 11:37:27,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 9: [2023-04-29 11:37:27,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. + 9: [2023-04-29 11:37:27,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +38: [2023-04-29 11:37:27,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 9: [2023-04-29 11:37:27,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +36: [2023-04-29 11:37:27,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +36: [2023-04-29 11:37:27,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +21: [2023-04-29 11:37:27,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... + 9: [2023-04-29 11:37:27,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +61: [2023-04-29 11:37:27,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +61: [2023-04-29 11:37:27,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +38: [2023-04-29 11:37:27,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +38: [2023-04-29 11:37:27,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +34: [2023-04-29 11:37:27,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +28: [2023-04-29 11:37:27,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +28: [2023-04-29 11:37:27,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +28: [2023-04-29 11:37:27,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +34: [2023-04-29 11:37:27,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +14: [2023-04-29 11:37:27,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 0: [2023-04-29 11:37:27,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 0: [2023-04-29 11:37:27,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 5: [2023-04-29 11:37:27,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +28: [2023-04-29 11:37:27,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +28: [2023-04-29 11:37:27,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +28: [2023-04-29 11:37:27,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +28: [2023-04-29 11:37:27,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +34: [2023-04-29 11:37:27,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +40: [2023-04-29 11:37:27,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +34: [2023-04-29 11:37:27,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt... +40: [2023-04-29 11:37:27,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +28: [2023-04-29 11:37:27,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +14: [2023-04-29 11:37:27,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +14: [2023-04-29 11:37:27,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +15: [2023-04-29 11:37:27,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +40: [2023-04-29 11:37:27,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +40: [2023-04-29 11:37:27,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +15: [2023-04-29 11:37:27,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +14: [2023-04-29 11:37:27,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... + 0: [2023-04-29 11:37:27,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +11: [2023-04-29 11:37:27,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +52: [2023-04-29 11:37:27,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 0: [2023-04-29 11:37:27,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +61: [2023-04-29 11:37:27,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +14: [2023-04-29 11:37:27,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +14: [2023-04-29 11:37:27,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +29: [2023-04-29 11:37:27,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +63: [2023-04-29 11:37:27,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 5: [2023-04-29 11:37:27,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 5: [2023-04-29 11:37:27,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +29: [2023-04-29 11:37:27,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +31: [2023-04-29 11:37:27,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +29: [2023-04-29 11:37:27,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +15: [2023-04-29 11:37:27,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +15: [2023-04-29 11:37:27,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +13: [2023-04-29 11:37:27,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 1: [2023-04-29 11:37:27,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 7: [2023-04-29 11:37:27,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 7: [2023-04-29 11:37:27,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +13: [2023-04-29 11:37:27,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +13: [2023-04-29 11:37:27,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +54: [2023-04-29 11:37:27,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +54: [2023-04-29 11:37:27,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +11: [2023-04-29 11:37:27,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +11: [2023-04-29 11:37:27,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +13: [2023-04-29 11:37:27,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +13: [2023-04-29 11:37:27,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +13: [2023-04-29 11:37:27,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +13: [2023-04-29 11:37:27,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +56: [2023-04-29 11:37:27,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +13: [2023-04-29 11:37:27,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +14: [2023-04-29 11:37:27,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +32: [2023-04-29 11:37:27,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 0: [2023-04-29 11:37:27,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... + 0: [2023-04-29 11:37:27,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +49: [2023-04-29 11:37:27,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +44: [2023-04-29 11:37:27,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +44: [2023-04-29 11:37:27,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +35: [2023-04-29 11:37:27,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +35: [2023-04-29 11:37:27,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +21: [2023-04-29 11:37:27,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +23: [2023-04-29 11:37:27,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +35: [2023-04-29 11:37:27,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +23: [2023-04-29 11:37:27,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +35: [2023-04-29 11:37:27,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +15: [2023-04-29 11:37:27,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +61: [2023-04-29 11:37:27,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +54: [2023-04-29 11:37:27,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +56: [2023-04-29 11:37:27,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +54: [2023-04-29 11:37:27,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +49: [2023-04-29 11:37:27,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 0: [2023-04-29 11:37:27,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +54: [2023-04-29 11:37:27,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +54: [2023-04-29 11:37:27,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +54: [2023-04-29 11:37:27,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +54: [2023-04-29 11:37:27,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +39: [2023-04-29 11:37:27,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +44: [2023-04-29 11:37:27,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +44: [2023-04-29 11:37:27,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +25: [2023-04-29 11:37:27,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +25: [2023-04-29 11:37:27,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +32: [2023-04-29 11:37:27,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +15: [2023-04-29 11:37:27,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +13: [2023-04-29 11:37:27,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +13: [2023-04-29 11:37:27,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +13: [2023-04-29 11:37:27,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +15: [2023-04-29 11:37:27,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +31: [2023-04-29 11:37:27,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +31: [2023-04-29 11:37:27,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +31: [2023-04-29 11:37:27,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +23: [2023-04-29 11:37:27,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +23: [2023-04-29 11:37:27,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 7: [2023-04-29 11:37:27,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +11: [2023-04-29 11:37:27,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +11: [2023-04-29 11:37:27,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... + 7: [2023-04-29 11:37:27,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 7: [2023-04-29 11:37:27,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +49: [2023-04-29 11:37:27,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 1: [2023-04-29 11:37:27,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 1: [2023-04-29 11:37:27,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 1: [2023-04-29 11:37:27,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +32: [2023-04-29 11:37:27,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +21: [2023-04-29 11:37:27,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +32: [2023-04-29 11:37:27,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +49: [2023-04-29 11:37:27,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +36: [2023-04-29 11:37:27,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +25: [2023-04-29 11:37:27,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +13: [2023-04-29 11:37:27,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +54: [2023-04-29 11:37:27,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +43: [2023-04-29 11:37:27,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +54: [2023-04-29 11:37:27,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +25: [2023-04-29 11:37:27,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +25: [2023-04-29 11:37:27,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +25: [2023-04-29 11:37:27,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +25: [2023-04-29 11:37:27,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 7: [2023-04-29 11:37:27,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... + 7: [2023-04-29 11:37:27,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +54: [2023-04-29 11:37:27,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +13: [2023-04-29 11:37:27,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +25: [2023-04-29 11:37:27,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +54: [2023-04-29 11:37:27,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +54: [2023-04-29 11:37:27,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +54: [2023-04-29 11:37:27,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +63: [2023-04-29 11:37:27,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +39: [2023-04-29 11:37:27,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +13: [2023-04-29 11:37:27,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +13: [2023-04-29 11:37:27,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +13: [2023-04-29 11:37:27,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +25: [2023-04-29 11:37:27,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +43: [2023-04-29 11:37:27,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +21: [2023-04-29 11:37:27,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +54: [2023-04-29 11:37:27,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 3: [2023-04-29 11:37:27,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 3: [2023-04-29 11:37:27,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +25: [2023-04-29 11:37:27,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... + 3: [2023-04-29 11:37:27,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +52: [2023-04-29 11:37:27,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +54: [2023-04-29 11:37:27,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... + 3: [2023-04-29 11:37:27,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +11: [2023-04-29 11:37:27,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +52: [2023-04-29 11:37:27,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +52: [2023-04-29 11:37:27,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +42: [2023-04-29 11:37:27,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +16: [2023-04-29 11:37:27,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +16: [2023-04-29 11:37:27,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +16: [2023-04-29 11:37:27,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. +25: [2023-04-29 11:37:27,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +43: [2023-04-29 11:37:27,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +25: [2023-04-29 11:37:27,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +25: [2023-04-29 11:37:27,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +50: [2023-04-29 11:37:27,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +21: [2023-04-29 11:37:27,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +11: [2023-04-29 11:37:27,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +25: [2023-04-29 11:37:27,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +43: [2023-04-29 11:37:27,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +63: [2023-04-29 11:37:27,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 7: [2023-04-29 11:37:27,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +43: [2023-04-29 11:37:27,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +43: [2023-04-29 11:37:27,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +25: [2023-04-29 11:37:27,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +63: [2023-04-29 11:37:27,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +25: [2023-04-29 11:37:27,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +36: [2023-04-29 11:37:27,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +58: [2023-04-29 11:37:27,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +11: [2023-04-29 11:37:27,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +19: [2023-04-29 11:37:27,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +19: [2023-04-29 11:37:27,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +58: [2023-04-29 11:37:27,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +39: [2023-04-29 11:37:27,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +19: [2023-04-29 11:37:27,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +58: [2023-04-29 11:37:27,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +19: [2023-04-29 11:37:27,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +50: [2023-04-29 11:37:27,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +39: [2023-04-29 11:37:27,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +16: [2023-04-29 11:37:27,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_00-model_states.pt. + 9: [2023-04-29 11:37:27,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +58: [2023-04-29 11:37:27,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +50: [2023-04-29 11:37:27,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +21: [2023-04-29 11:37:27,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +11: [2023-04-29 11:37:27,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +56: [2023-04-29 11:37:27,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 9: [2023-04-29 11:37:27,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +52: [2023-04-29 11:37:27,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +31: [2023-04-29 11:37:27,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 9: [2023-04-29 11:37:27,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 3: [2023-04-29 11:37:27,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +46: [2023-04-29 11:37:27,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +46: [2023-04-29 11:37:27,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 7: [2023-04-29 11:37:27,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... + 9: [2023-04-29 11:37:27,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +56: [2023-04-29 11:37:27,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +43: [2023-04-29 11:37:27,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +43: [2023-04-29 11:37:27,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +46: [2023-04-29 11:37:27,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +46: [2023-04-29 11:37:27,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +46: [2023-04-29 11:37:27,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +46: [2023-04-29 11:37:27,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +46: [2023-04-29 11:37:27,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +46: [2023-04-29 11:37:27,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +50: [2023-04-29 11:37:27,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +21: [2023-04-29 11:37:27,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... + 3: [2023-04-29 11:37:27,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +39: [2023-04-29 11:37:27,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +18: [2023-04-29 11:37:27,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +50: [2023-04-29 11:37:27,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +50: [2023-04-29 11:37:27,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +61: [2023-04-29 11:37:27,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +50: [2023-04-29 11:37:27,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +24: [2023-04-29 11:37:27,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +14: [2023-04-29 11:37:27,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +50: [2023-04-29 11:37:27,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 3: [2023-04-29 11:37:27,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +14: [2023-04-29 11:37:27,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +50: [2023-04-29 11:37:27,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +39: [2023-04-29 11:37:27,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +57: [2023-04-29 11:37:27,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +14: [2023-04-29 11:37:27,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +24: [2023-04-29 11:37:27,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +24: [2023-04-29 11:37:27,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +39: [2023-04-29 11:37:27,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +14: [2023-04-29 11:37:27,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +63: [2023-04-29 11:37:27,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 3: [2023-04-29 11:37:27,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +46: [2023-04-29 11:37:27,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +46: [2023-04-29 11:37:27,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +46: [2023-04-29 11:37:27,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +46: [2023-04-29 11:37:27,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +46: [2023-04-29 11:37:27,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +46: [2023-04-29 11:37:27,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +24: [2023-04-29 11:37:27,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +39: [2023-04-29 11:37:27,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +44: [2023-04-29 11:37:27,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +55: [2023-04-29 11:37:27,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +44: [2023-04-29 11:37:27,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +44: [2023-04-29 11:37:27,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +46: [2023-04-29 11:37:27,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +46: [2023-04-29 11:37:27,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +39: [2023-04-29 11:37:27,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +12: [2023-04-29 11:37:27,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +35: [2023-04-29 11:37:27,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +12: [2023-04-29 11:37:27,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +39: [2023-04-29 11:37:27,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +35: [2023-04-29 11:37:27,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +61: [2023-04-29 11:37:27,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +12: [2023-04-29 11:37:27,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +12: [2023-04-29 11:37:27,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +44: [2023-04-29 11:37:27,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +35: [2023-04-29 11:37:27,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +12: [2023-04-29 11:37:27,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +12: [2023-04-29 11:37:27,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +12: [2023-04-29 11:37:27,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +12: [2023-04-29 11:37:27,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +50: [2023-04-29 11:37:27,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +15: [2023-04-29 11:37:27,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +15: [2023-04-29 11:37:27,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +15: [2023-04-29 11:37:27,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +35: [2023-04-29 11:37:27,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +57: [2023-04-29 11:37:27,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +57: [2023-04-29 11:37:27,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +56: [2023-04-29 11:37:27,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +57: [2023-04-29 11:37:27,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +50: [2023-04-29 11:37:27,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +39: [2023-04-29 11:37:27,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +56: [2023-04-29 11:37:27,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +17: [2023-04-29 11:37:27,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +23: [2023-04-29 11:37:27,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +23: [2023-04-29 11:37:27,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +63: [2023-04-29 11:37:27,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +39: [2023-04-29 11:37:27,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +61: [2023-04-29 11:37:27,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +50: [2023-04-29 11:37:27,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +15: [2023-04-29 11:37:27,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +31: [2023-04-29 11:37:27,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +55: [2023-04-29 11:37:27,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +52: [2023-04-29 11:37:27,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +12: [2023-04-29 11:37:27,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +12: [2023-04-29 11:37:27,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +31: [2023-04-29 11:37:27,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +31: [2023-04-29 11:37:27,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +55: [2023-04-29 11:37:27,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +52: [2023-04-29 11:37:27,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +52: [2023-04-29 11:37:27,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +12: [2023-04-29 11:37:27,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 6: [2023-04-29 11:37:27,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. + 6: [2023-04-29 11:37:27,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +31: [2023-04-29 11:37:27,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +31: [2023-04-29 11:37:27,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +31: [2023-04-29 11:37:27,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +39: [2023-04-29 11:37:27,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +18: [2023-04-29 11:37:27,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +18: [2023-04-29 11:37:27,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +23: [2023-04-29 11:37:27,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +23: [2023-04-29 11:37:27,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 6: [2023-04-29 11:37:27,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. + 6: [2023-04-29 11:37:27,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. + 1: [2023-04-29 11:37:27,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +31: [2023-04-29 11:37:27,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +12: [2023-04-29 11:37:27,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +12: [2023-04-29 11:37:27,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +23: [2023-04-29 11:37:27,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +12: [2023-04-29 11:37:27,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +48: [2023-04-29 11:37:27,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +61: [2023-04-29 11:37:27,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +18: [2023-04-29 11:37:27,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +23: [2023-04-29 11:37:27,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +12: [2023-04-29 11:37:27,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +17: [2023-04-29 11:37:27,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +17: [2023-04-29 11:37:27,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +12: [2023-04-29 11:37:27,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +17: [2023-04-29 11:37:27,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +55: [2023-04-29 11:37:27,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +23: [2023-04-29 11:37:27,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +23: [2023-04-29 11:37:27,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +19: [2023-04-29 11:37:27,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +22: [2023-04-29 11:37:27,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 1: [2023-04-29 11:37:27,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +16: [2023-04-29 11:37:27,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +16: [2023-04-29 11:37:27,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +43: [2023-04-29 11:37:27,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +18: [2023-04-29 11:37:27,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +63: [2023-04-29 11:37:27,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +34: [2023-04-29 11:37:27,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +24: [2023-04-29 11:37:27,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 2: [2023-04-29 11:37:27,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 2: [2023-04-29 11:37:27,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 2: [2023-04-29 11:37:27,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +29: [2023-04-29 11:37:27,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +29: [2023-04-29 11:37:27,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +29: [2023-04-29 11:37:27,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. + 2: [2023-04-29 11:37:27,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 2: [2023-04-29 11:37:27,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +29: [2023-04-29 11:37:27,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. + 2: [2023-04-29 11:37:27,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 2: [2023-04-29 11:37:27,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 1: [2023-04-29 11:37:27,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +48: [2023-04-29 11:37:27,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 2: [2023-04-29 11:37:27,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 1: [2023-04-29 11:37:27,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +16: [2023-04-29 11:37:27,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +57: [2023-04-29 11:37:27,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +34: [2023-04-29 11:37:27,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +48: [2023-04-29 11:37:27,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +48: [2023-04-29 11:37:27,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 3: [2023-04-29 11:37:27,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 3: [2023-04-29 11:37:27,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 7: [2023-04-29 11:37:27,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +24: [2023-04-29 11:37:27,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +19: [2023-04-29 11:37:27,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +33: [2023-04-29 11:37:27,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +33: [2023-04-29 11:37:27,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +16: [2023-04-29 11:37:27,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +55: [2023-04-29 11:37:27,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +22: [2023-04-29 11:37:27,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +22: [2023-04-29 11:37:27,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +22: [2023-04-29 11:37:27,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +19: [2023-04-29 11:37:27,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +26: [2023-04-29 11:37:27,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +33: [2023-04-29 11:37:27,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +33: [2023-04-29 11:37:27,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +26: [2023-04-29 11:37:27,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 9: [2023-04-29 11:37:27,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 9: [2023-04-29 11:37:27,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +26: [2023-04-29 11:37:27,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +26: [2023-04-29 11:37:27,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +26: [2023-04-29 11:37:27,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +26: [2023-04-29 11:37:27,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 9: [2023-04-29 11:37:27,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +26: [2023-04-29 11:37:27,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +33: [2023-04-29 11:37:27,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +33: [2023-04-29 11:37:27,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +33: [2023-04-29 11:37:27,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +26: [2023-04-29 11:37:27,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +33: [2023-04-29 11:37:27,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +24: [2023-04-29 11:37:27,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 9: [2023-04-29 11:37:27,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +28: [2023-04-29 11:37:27,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +24: [2023-04-29 11:37:27,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +19: [2023-04-29 11:37:27,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +40: [2023-04-29 11:37:27,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +63: [2023-04-29 11:37:27,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +43: [2023-04-29 11:37:27,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +33: [2023-04-29 11:37:27,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +33: [2023-04-29 11:37:27,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +63: [2023-04-29 11:37:27,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 2: [2023-04-29 11:37:27,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... + 2: [2023-04-29 11:37:27,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 3: [2023-04-29 11:37:27,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 3: [2023-04-29 11:37:27,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +33: [2023-04-29 11:37:27,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +26: [2023-04-29 11:37:27,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +62: [2023-04-29 11:37:27,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +62: [2023-04-29 11:37:27,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +33: [2023-04-29 11:37:27,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 2: [2023-04-29 11:37:27,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +62: [2023-04-29 11:37:27,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +33: [2023-04-29 11:37:27,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +62: [2023-04-29 11:37:27,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +26: [2023-04-29 11:37:27,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +28: [2023-04-29 11:37:27,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +28: [2023-04-29 11:37:27,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +43: [2023-04-29 11:37:27,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +26: [2023-04-29 11:37:27,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 2: [2023-04-29 11:37:27,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 2: [2023-04-29 11:37:27,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +32: [2023-04-29 11:37:27,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +32: [2023-04-29 11:37:27,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 9: [2023-04-29 11:37:27,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +32: [2023-04-29 11:37:27,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 2: [2023-04-29 11:37:27,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +32: [2023-04-29 11:37:27,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +26: [2023-04-29 11:37:27,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 2: [2023-04-29 11:37:27,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +33: [2023-04-29 11:37:27,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +26: [2023-04-29 11:37:27,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +57: [2023-04-29 11:37:27,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +57: [2023-04-29 11:37:27,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 9: [2023-04-29 11:37:27,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +26: [2023-04-29 11:37:27,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 2: [2023-04-29 11:37:27,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +26: [2023-04-29 11:37:27,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +33: [2023-04-29 11:37:27,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +26: [2023-04-29 11:37:27,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +33: [2023-04-29 11:37:27,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +34: [2023-04-29 11:37:27,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 9: [2023-04-29 11:37:27,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +22: [2023-04-29 11:37:27,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +57: [2023-04-29 11:37:27,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 9: [2023-04-29 11:37:27,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +55: [2023-04-29 11:37:27,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +22: [2023-04-29 11:37:27,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +17: [2023-04-29 11:37:27,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +43: [2023-04-29 11:37:27,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. + 1: [2023-04-29 11:37:27,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +62: [2023-04-29 11:37:27,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +28: [2023-04-29 11:37:27,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +63: [2023-04-29 11:37:27,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +22: [2023-04-29 11:37:27,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +62: [2023-04-29 11:37:27,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +15: [2023-04-29 11:37:27,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +40: [2023-04-29 11:37:27,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +40: [2023-04-29 11:37:27,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +40: [2023-04-29 11:37:27,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +15: [2023-04-29 11:37:27,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +15: [2023-04-29 11:37:27,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +15: [2023-04-29 11:37:27,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +34: [2023-04-29 11:37:27,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +23: [2023-04-29 11:37:27,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +62: [2023-04-29 11:37:27,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +55: [2023-04-29 11:37:27,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +13: [2023-04-29 11:37:27,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +13: [2023-04-29 11:37:27,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +32: [2023-04-29 11:37:27,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +32: [2023-04-29 11:37:27,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +63: [2023-04-29 11:37:27,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +63: [2023-04-29 11:37:27,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +62: [2023-04-29 11:37:27,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +32: [2023-04-29 11:37:27,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +48: [2023-04-29 11:37:27,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +63: [2023-04-29 11:37:27,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_00-model_states.pt. +31: [2023-04-29 11:37:27,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +22: [2023-04-29 11:37:27,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +31: [2023-04-29 11:37:27,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +32: [2023-04-29 11:37:27,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +55: [2023-04-29 11:37:27,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +43: [2023-04-29 11:37:27,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +22: [2023-04-29 11:37:27,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +31: [2023-04-29 11:37:27,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +18: [2023-04-29 11:37:27,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +63: [2023-04-29 11:37:27,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... +23: [2023-04-29 11:37:27,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +54: [2023-04-29 11:37:27,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +54: [2023-04-29 11:37:27,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +31: [2023-04-29 11:37:27,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 6: [2023-04-29 11:37:27,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 6: [2023-04-29 11:37:27,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 6: [2023-04-29 11:37:27,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +18: [2023-04-29 11:37:27,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +17: [2023-04-29 11:37:27,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +25: [2023-04-29 11:37:27,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +17: [2023-04-29 11:37:27,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 6: [2023-04-29 11:37:27,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +29: [2023-04-29 11:37:27,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +63: [2023-04-29 11:37:27,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt... + 1: [2023-04-29 11:37:27,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +34: [2023-04-29 11:37:27,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +29: [2023-04-29 11:37:27,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +18: [2023-04-29 11:37:27,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +17: [2023-04-29 11:37:27,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +23: [2023-04-29 11:37:27,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 1: [2023-04-29 11:37:27,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +13: [2023-04-29 11:37:27,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +37: [2023-04-29 11:37:27,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +37: [2023-04-29 11:37:27,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +37: [2023-04-29 11:37:27,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +37: [2023-04-29 11:37:27,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +34: [2023-04-29 11:37:27,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +48: [2023-04-29 11:37:27,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +29: [2023-04-29 11:37:27,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +48: [2023-04-29 11:37:27,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +32: [2023-04-29 11:37:27,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +32: [2023-04-29 11:37:27,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +54: [2023-04-29 11:37:27,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +54: [2023-04-29 11:37:27,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +50: [2023-04-29 11:37:27,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +32: [2023-04-29 11:37:27,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +29: [2023-04-29 11:37:27,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +13: [2023-04-29 11:37:27,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +40: [2023-04-29 11:37:27,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +48: [2023-04-29 11:37:27,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +23: [2023-04-29 11:37:27,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +42: [2023-04-29 11:37:27,931] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +42: [2023-04-29 11:37:27,931] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +42: [2023-04-29 11:37:27,931] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 1: [2023-04-29 11:37:27,931] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 1: [2023-04-29 11:37:27,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 1: [2023-04-29 11:37:27,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +25: [2023-04-29 11:37:27,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +32: [2023-04-29 11:37:27,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +28: [2023-04-29 11:37:27,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +50: [2023-04-29 11:37:27,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +22: [2023-04-29 11:37:27,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +42: [2023-04-29 11:37:27,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +42: [2023-04-29 11:37:27,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +42: [2023-04-29 11:37:27,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +42: [2023-04-29 11:37:27,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 3: [2023-04-29 11:37:27,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +32: [2023-04-29 11:37:27,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +23: [2023-04-29 11:37:27,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +32: [2023-04-29 11:37:27,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +32: [2023-04-29 11:37:27,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... + 1: [2023-04-29 11:37:27,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +50: [2023-04-29 11:37:27,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 1: [2023-04-29 11:37:27,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... + 3: [2023-04-29 11:37:27,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +28: [2023-04-29 11:37:27,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +28: [2023-04-29 11:37:27,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +43: [2023-04-29 11:37:27,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +42: [2023-04-29 11:37:27,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +42: [2023-04-29 11:37:27,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +42: [2023-04-29 11:37:27,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +23: [2023-04-29 11:37:27,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +25: [2023-04-29 11:37:27,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +25: [2023-04-29 11:37:27,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +42: [2023-04-29 11:37:27,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +50: [2023-04-29 11:37:27,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +22: [2023-04-29 11:37:27,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 1: [2023-04-29 11:37:27,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +22: [2023-04-29 11:37:27,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +32: [2023-04-29 11:37:27,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +46: [2023-04-29 11:37:27,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 3: [2023-04-29 11:37:27,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +42: [2023-04-29 11:37:27,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 3: [2023-04-29 11:37:27,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +43: [2023-04-29 11:37:27,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +43: [2023-04-29 11:37:27,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +50: [2023-04-29 11:37:27,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +23: [2023-04-29 11:37:27,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... + 3: [2023-04-29 11:37:27,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... + 1: [2023-04-29 11:37:27,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... + 3: [2023-04-29 11:37:27,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +22: [2023-04-29 11:37:27,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +42: [2023-04-29 11:37:27,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +42: [2023-04-29 11:37:27,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +34: [2023-04-29 11:37:27,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +28: [2023-04-29 11:37:27,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 1: [2023-04-29 11:37:27,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +13: [2023-04-29 11:37:27,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +42: [2023-04-29 11:37:27,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 3: [2023-04-29 11:37:27,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +22: [2023-04-29 11:37:27,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +23: [2023-04-29 11:37:27,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +22: [2023-04-29 11:37:27,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 3: [2023-04-29 11:37:27,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... + 9: [2023-04-29 11:37:27,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +13: [2023-04-29 11:37:27,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +25: [2023-04-29 11:37:27,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +40: [2023-04-29 11:37:27,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +34: [2023-04-29 11:37:27,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +42: [2023-04-29 11:37:27,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... + 9: [2023-04-29 11:37:27,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 9: [2023-04-29 11:37:27,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 9: [2023-04-29 11:37:27,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +40: [2023-04-29 11:37:27,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +46: [2023-04-29 11:37:27,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +46: [2023-04-29 11:37:27,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +46: [2023-04-29 11:37:27,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +22: [2023-04-29 11:37:27,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 1: [2023-04-29 11:37:27,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +51: [2023-04-29 11:37:27,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +51: [2023-04-29 11:37:27,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +51: [2023-04-29 11:37:27,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +40: [2023-04-29 11:37:27,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +51: [2023-04-29 11:37:27,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +54: [2023-04-29 11:37:27,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +54: [2023-04-29 11:37:27,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 9: [2023-04-29 11:37:27,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +13: [2023-04-29 11:37:27,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +37: [2023-04-29 11:37:27,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 9: [2023-04-29 11:37:27,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... + 9: [2023-04-29 11:37:27,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +12: [2023-04-29 11:37:27,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +49: [2023-04-29 11:37:27,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +49: [2023-04-29 11:37:27,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +49: [2023-04-29 11:37:27,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 9: [2023-04-29 11:37:27,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +49: [2023-04-29 11:37:27,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +49: [2023-04-29 11:37:27,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +49: [2023-04-29 11:37:27,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +49: [2023-04-29 11:37:27,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +49: [2023-04-29 11:37:27,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +54: [2023-04-29 11:37:27,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +54: [2023-04-29 11:37:27,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +13: [2023-04-29 11:37:27,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +37: [2023-04-29 11:37:27,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +37: [2023-04-29 11:37:27,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +23: [2023-04-29 11:37:27,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +37: [2023-04-29 11:37:27,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +12: [2023-04-29 11:37:27,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +12: [2023-04-29 11:37:27,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +12: [2023-04-29 11:37:27,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +25: [2023-04-29 11:37:27,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +40: [2023-04-29 11:37:27,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +40: [2023-04-29 11:37:27,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +49: [2023-04-29 11:37:27,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +49: [2023-04-29 11:37:27,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +49: [2023-04-29 11:37:27,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +50: [2023-04-29 11:37:27,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +40: [2023-04-29 11:37:27,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +40: [2023-04-29 11:37:27,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +50: [2023-04-29 11:37:27,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +23: [2023-04-29 11:37:27,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +49: [2023-04-29 11:37:27,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +49: [2023-04-29 11:37:27,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +33: [2023-04-29 11:37:27,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +49: [2023-04-29 11:37:27,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +49: [2023-04-29 11:37:27,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +49: [2023-04-29 11:37:27,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +50: [2023-04-29 11:37:27,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +23: [2023-04-29 11:37:27,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +23: [2023-04-29 11:37:27,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +46: [2023-04-29 11:37:27,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +25: [2023-04-29 11:37:27,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +25: [2023-04-29 11:37:27,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +50: [2023-04-29 11:37:27,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +30: [2023-04-29 11:37:27,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +30: [2023-04-29 11:37:27,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +30: [2023-04-29 11:37:27,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +30: [2023-04-29 11:37:27,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +50: [2023-04-29 11:37:27,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +50: [2023-04-29 11:37:27,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +26: [2023-04-29 11:37:27,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +62: [2023-04-29 11:37:27,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +62: [2023-04-29 11:37:27,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +62: [2023-04-29 11:37:27,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +62: [2023-04-29 11:37:27,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +26: [2023-04-29 11:37:27,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +35: [2023-04-29 11:37:27,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +35: [2023-04-29 11:37:27,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +35: [2023-04-29 11:37:27,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +35: [2023-04-29 11:37:27,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +35: [2023-04-29 11:37:27,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +35: [2023-04-29 11:37:27,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +35: [2023-04-29 11:37:27,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +35: [2023-04-29 11:37:27,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +62: [2023-04-29 11:37:27,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +50: [2023-04-29 11:37:27,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +50: [2023-04-29 11:37:27,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +53: [2023-04-29 11:37:27,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +53: [2023-04-29 11:37:27,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +53: [2023-04-29 11:37:27,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +53: [2023-04-29 11:37:27,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +46: [2023-04-29 11:37:27,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +33: [2023-04-29 11:37:27,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +33: [2023-04-29 11:37:27,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +33: [2023-04-29 11:37:27,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +46: [2023-04-29 11:37:27,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +46: [2023-04-29 11:37:27,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +26: [2023-04-29 11:37:27,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +26: [2023-04-29 11:37:27,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 2: [2023-04-29 11:37:27,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 2: [2023-04-29 11:37:27,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 2: [2023-04-29 11:37:27,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +35: [2023-04-29 11:37:27,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +35: [2023-04-29 11:37:27,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +29: [2023-04-29 11:37:27,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +35: [2023-04-29 11:37:27,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +53: [2023-04-29 11:37:27,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 9: [2023-04-29 11:37:27,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +41: [2023-04-29 11:37:27,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +41: [2023-04-29 11:37:27,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +32: [2023-04-29 11:37:27,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +51: [2023-04-29 11:37:27,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +35: [2023-04-29 11:37:27,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +51: [2023-04-29 11:37:27,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +41: [2023-04-29 11:37:27,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 6: [2023-04-29 11:37:27,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +41: [2023-04-29 11:37:27,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +35: [2023-04-29 11:37:27,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +62: [2023-04-29 11:37:27,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +62: [2023-04-29 11:37:27,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +19: [2023-04-29 11:37:27,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +19: [2023-04-29 11:37:27,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +19: [2023-04-29 11:37:27,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +19: [2023-04-29 11:37:27,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +19: [2023-04-29 11:37:27,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +19: [2023-04-29 11:37:27,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +19: [2023-04-29 11:37:27,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +19: [2023-04-29 11:37:27,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +23: [2023-04-29 11:37:27,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +53: [2023-04-29 11:37:27,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +53: [2023-04-29 11:37:27,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +53: [2023-04-29 11:37:27,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +29: [2023-04-29 11:37:27,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +35: [2023-04-29 11:37:27,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... + 2: [2023-04-29 11:37:27,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +31: [2023-04-29 11:37:27,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +35: [2023-04-29 11:37:27,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +51: [2023-04-29 11:37:27,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +51: [2023-04-29 11:37:27,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +35: [2023-04-29 11:37:27,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +12: [2023-04-29 11:37:27,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 9: [2023-04-29 11:37:27,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 9: [2023-04-29 11:37:27,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 9: [2023-04-29 11:37:27,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +12: [2023-04-29 11:37:27,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +12: [2023-04-29 11:37:27,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +40: [2023-04-29 11:37:27,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 6: [2023-04-29 11:37:27,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +41: [2023-04-29 11:37:27,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +40: [2023-04-29 11:37:27,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +32: [2023-04-29 11:37:27,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +41: [2023-04-29 11:37:27,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +41: [2023-04-29 11:37:27,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +19: [2023-04-29 11:37:27,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +19: [2023-04-29 11:37:27,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +44: [2023-04-29 11:37:27,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +44: [2023-04-29 11:37:27,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +44: [2023-04-29 11:37:27,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +44: [2023-04-29 11:37:27,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +44: [2023-04-29 11:37:27,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +44: [2023-04-29 11:37:27,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +44: [2023-04-29 11:37:27,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +32: [2023-04-29 11:37:27,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +44: [2023-04-29 11:37:27,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +51: [2023-04-29 11:37:27,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +51: [2023-04-29 11:37:27,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +51: [2023-04-29 11:37:27,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +51: [2023-04-29 11:37:27,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +23: [2023-04-29 11:37:27,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +40: [2023-04-29 11:37:27,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +19: [2023-04-29 11:37:27,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +33: [2023-04-29 11:37:27,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +19: [2023-04-29 11:37:27,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +40: [2023-04-29 11:37:27,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +37: [2023-04-29 11:37:27,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +31: [2023-04-29 11:37:27,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +31: [2023-04-29 11:37:27,992] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +31: [2023-04-29 11:37:27,992] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +41: [2023-04-29 11:37:27,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +31: [2023-04-29 11:37:27,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +12: [2023-04-29 11:37:27,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 6: [2023-04-29 11:37:27,992] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 6: [2023-04-29 11:37:27,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +29: [2023-04-29 11:37:27,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +19: [2023-04-29 11:37:27,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +19: [2023-04-29 11:37:27,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +19: [2023-04-29 11:37:27,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +19: [2023-04-29 11:37:27,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... + 6: [2023-04-29 11:37:27,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +44: [2023-04-29 11:37:27,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +44: [2023-04-29 11:37:27,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +44: [2023-04-29 11:37:27,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +44: [2023-04-29 11:37:27,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +44: [2023-04-29 11:37:27,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +44: [2023-04-29 11:37:27,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +44: [2023-04-29 11:37:27,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +26: [2023-04-29 11:37:27,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +23: [2023-04-29 11:37:27,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +23: [2023-04-29 11:37:27,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +44: [2023-04-29 11:37:27,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +37: [2023-04-29 11:37:27,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +29: [2023-04-29 11:37:27,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +29: [2023-04-29 11:37:27,999] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +31: [2023-04-29 11:37:27,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +31: [2023-04-29 11:37:27,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +31: [2023-04-29 11:37:27,999] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +30: [2023-04-29 11:37:27,999] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +30: [2023-04-29 11:37:27,999] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +37: [2023-04-29 11:37:27,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +37: [2023-04-29 11:37:27,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +37: [2023-04-29 11:37:27,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +30: [2023-04-29 11:37:27,999] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +51: [2023-04-29 11:37:28,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 6: [2023-04-29 11:37:28,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +29: [2023-04-29 11:37:28,000] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +51: [2023-04-29 11:37:28,001] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 6: [2023-04-29 11:37:28,001] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +30: [2023-04-29 11:37:28,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +22: [2023-04-29 11:37:28,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +26: [2023-04-29 11:37:28,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 6: [2023-04-29 11:37:28,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +32: [2023-04-29 11:37:28,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +51: [2023-04-29 11:37:28,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +29: [2023-04-29 11:37:28,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +51: [2023-04-29 11:37:28,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +58: [2023-04-29 11:37:28,003] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +58: [2023-04-29 11:37:28,003] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +58: [2023-04-29 11:37:28,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +58: [2023-04-29 11:37:28,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +58: [2023-04-29 11:37:28,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +58: [2023-04-29 11:37:28,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +58: [2023-04-29 11:37:28,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +50: [2023-04-29 11:37:28,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +58: [2023-04-29 11:37:28,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +42: [2023-04-29 11:37:28,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +42: [2023-04-29 11:37:28,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +42: [2023-04-29 11:37:28,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +62: [2023-04-29 11:37:28,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +29: [2023-04-29 11:37:28,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +33: [2023-04-29 11:37:28,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +37: [2023-04-29 11:37:28,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +22: [2023-04-29 11:37:28,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +45: [2023-04-29 11:37:28,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +45: [2023-04-29 11:37:28,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +45: [2023-04-29 11:37:28,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +37: [2023-04-29 11:37:28,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +33: [2023-04-29 11:37:28,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +37: [2023-04-29 11:37:28,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 9: [2023-04-29 11:37:28,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +33: [2023-04-29 11:37:28,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 5: [2023-04-29 11:37:28,009] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 5: [2023-04-29 11:37:28,010] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 5: [2023-04-29 11:37:28,010] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 5: [2023-04-29 11:37:28,010] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 5: [2023-04-29 11:37:28,010] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +26: [2023-04-29 11:37:28,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +26: [2023-04-29 11:37:28,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 5: [2023-04-29 11:37:28,010] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 5: [2023-04-29 11:37:28,010] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 5: [2023-04-29 11:37:28,010] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +45: [2023-04-29 11:37:28,010] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +32: [2023-04-29 11:37:28,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +62: [2023-04-29 11:37:28,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +58: [2023-04-29 11:37:28,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +58: [2023-04-29 11:37:28,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +22: [2023-04-29 11:37:28,011] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +58: [2023-04-29 11:37:28,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +58: [2023-04-29 11:37:28,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +58: [2023-04-29 11:37:28,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +45: [2023-04-29 11:37:28,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +58: [2023-04-29 11:37:28,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +58: [2023-04-29 11:37:28,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... + 2: [2023-04-29 11:37:28,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +58: [2023-04-29 11:37:28,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +42: [2023-04-29 11:37:28,012] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 2: [2023-04-29 11:37:28,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +45: [2023-04-29 11:37:28,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +50: [2023-04-29 11:37:28,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +50: [2023-04-29 11:37:28,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +45: [2023-04-29 11:37:28,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 2: [2023-04-29 11:37:28,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +22: [2023-04-29 11:37:28,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +22: [2023-04-29 11:37:28,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +45: [2023-04-29 11:37:28,016] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 5: [2023-04-29 11:37:28,016] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +62: [2023-04-29 11:37:28,016] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +62: [2023-04-29 11:37:28,016] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 5: [2023-04-29 11:37:28,016] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +62: [2023-04-29 11:37:28,016] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 5: [2023-04-29 11:37:28,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... + 5: [2023-04-29 11:37:28,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... + 2: [2023-04-29 11:37:28,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 9: [2023-04-29 11:37:28,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +32: [2023-04-29 11:37:28,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +32: [2023-04-29 11:37:28,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +22: [2023-04-29 11:37:28,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... + 5: [2023-04-29 11:37:28,019] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +37: [2023-04-29 11:37:28,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 5: [2023-04-29 11:37:28,019] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 9: [2023-04-29 11:37:28,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +62: [2023-04-29 11:37:28,019] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 5: [2023-04-29 11:37:28,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 9: [2023-04-29 11:37:28,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +22: [2023-04-29 11:37:28,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... + 5: [2023-04-29 11:37:28,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +22: [2023-04-29 11:37:28,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +16: [2023-04-29 11:37:28,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +16: [2023-04-29 11:37:28,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +49: [2023-04-29 11:37:28,022] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +62: [2023-04-29 11:37:28,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +37: [2023-04-29 11:37:28,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +16: [2023-04-29 11:37:28,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +62: [2023-04-29 11:37:28,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +16: [2023-04-29 11:37:28,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_06-model_01-model_states.pt. +53: [2023-04-29 11:37:28,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +32: [2023-04-29 11:37:28,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +47: [2023-04-29 11:37:28,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +47: [2023-04-29 11:37:28,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +47: [2023-04-29 11:37:28,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +47: [2023-04-29 11:37:28,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +42: [2023-04-29 11:37:28,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +42: [2023-04-29 11:37:28,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +49: [2023-04-29 11:37:28,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +49: [2023-04-29 11:37:28,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +49: [2023-04-29 11:37:28,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +42: [2023-04-29 11:37:28,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +47: [2023-04-29 11:37:28,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +47: [2023-04-29 11:37:28,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +47: [2023-04-29 11:37:28,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +51: [2023-04-29 11:37:28,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +47: [2023-04-29 11:37:28,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +42: [2023-04-29 11:37:28,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +35: [2023-04-29 11:37:28,044] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +51: [2023-04-29 11:37:28,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +60: [2023-04-29 11:37:28,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +60: [2023-04-29 11:37:28,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +16: [2023-04-29 11:37:28,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +16: [2023-04-29 11:37:28,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +49: [2023-04-29 11:37:28,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +60: [2023-04-29 11:37:28,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +60: [2023-04-29 11:37:28,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +37: [2023-04-29 11:37:28,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +37: [2023-04-29 11:37:28,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +37: [2023-04-29 11:37:28,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +41: [2023-04-29 11:37:28,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +53: [2023-04-29 11:37:28,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +40: [2023-04-29 11:37:28,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +19: [2023-04-29 11:37:28,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +19: [2023-04-29 11:37:28,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +53: [2023-04-29 11:37:28,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +53: [2023-04-29 11:37:28,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +53: [2023-04-29 11:37:28,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +60: [2023-04-29 11:37:28,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +60: [2023-04-29 11:37:28,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +19: [2023-04-29 11:37:28,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +60: [2023-04-29 11:37:28,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +51: [2023-04-29 11:37:28,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +40: [2023-04-29 11:37:28,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +16: [2023-04-29 11:37:28,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +60: [2023-04-29 11:37:28,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +59: [2023-04-29 11:37:28,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +59: [2023-04-29 11:37:28,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +19: [2023-04-29 11:37:28,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +59: [2023-04-29 11:37:28,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +59: [2023-04-29 11:37:28,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +37: [2023-04-29 11:37:28,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +37: [2023-04-29 11:37:28,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +40: [2023-04-29 11:37:28,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +37: [2023-04-29 11:37:28,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +40: [2023-04-29 11:37:28,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +62: [2023-04-29 11:37:28,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +44: [2023-04-29 11:37:28,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +16: [2023-04-29 11:37:28,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +51: [2023-04-29 11:37:28,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +35: [2023-04-29 11:37:28,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +35: [2023-04-29 11:37:28,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +35: [2023-04-29 11:37:28,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +37: [2023-04-29 11:37:28,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +41: [2023-04-29 11:37:28,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +40: [2023-04-29 11:37:28,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +41: [2023-04-29 11:37:28,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +59: [2023-04-29 11:37:28,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +59: [2023-04-29 11:37:28,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +59: [2023-04-29 11:37:28,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +44: [2023-04-29 11:37:28,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +59: [2023-04-29 11:37:28,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +40: [2023-04-29 11:37:28,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +44: [2023-04-29 11:37:28,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +41: [2023-04-29 11:37:28,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +35: [2023-04-29 11:37:28,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +49: [2023-04-29 11:37:28,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +49: [2023-04-29 11:37:28,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +44: [2023-04-29 11:37:28,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +49: [2023-04-29 11:37:28,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +45: [2023-04-29 11:37:28,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 4: [2023-04-29 11:37:28,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 4: [2023-04-29 11:37:28,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 4: [2023-04-29 11:37:28,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 4: [2023-04-29 11:37:28,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +40: [2023-04-29 11:37:28,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +51: [2023-04-29 11:37:28,075] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +41: [2023-04-29 11:37:28,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +45: [2023-04-29 11:37:28,076] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +41: [2023-04-29 11:37:28,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +41: [2023-04-29 11:37:28,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +40: [2023-04-29 11:37:28,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +58: [2023-04-29 11:37:28,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +58: [2023-04-29 11:37:28,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +19: [2023-04-29 11:37:28,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +19: [2023-04-29 11:37:28,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +58: [2023-04-29 11:37:28,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +58: [2023-04-29 11:37:28,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +41: [2023-04-29 11:37:28,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +51: [2023-04-29 11:37:28,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +37: [2023-04-29 11:37:28,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +41: [2023-04-29 11:37:28,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +53: [2023-04-29 11:37:28,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +53: [2023-04-29 11:37:28,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +19: [2023-04-29 11:37:28,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +51: [2023-04-29 11:37:28,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +53: [2023-04-29 11:37:28,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +38: [2023-04-29 11:37:28,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +38: [2023-04-29 11:37:28,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +51: [2023-04-29 11:37:28,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +52: [2023-04-29 11:37:28,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +52: [2023-04-29 11:37:28,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +52: [2023-04-29 11:37:28,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +45: [2023-04-29 11:37:28,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +52: [2023-04-29 11:37:28,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +38: [2023-04-29 11:37:28,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +38: [2023-04-29 11:37:28,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +44: [2023-04-29 11:37:28,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +19: [2023-04-29 11:37:28,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +27: [2023-04-29 11:37:28,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +27: [2023-04-29 11:37:28,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +27: [2023-04-29 11:37:28,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +27: [2023-04-29 11:37:28,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +45: [2023-04-29 11:37:28,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +44: [2023-04-29 11:37:28,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +51: [2023-04-29 11:37:28,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +56: [2023-04-29 11:37:28,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +56: [2023-04-29 11:37:28,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +56: [2023-04-29 11:37:28,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +38: [2023-04-29 11:37:28,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +56: [2023-04-29 11:37:28,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +38: [2023-04-29 11:37:28,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +38: [2023-04-29 11:37:28,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +35: [2023-04-29 11:37:28,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +63: [2023-04-29 11:37:28,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +63: [2023-04-29 11:37:28,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +44: [2023-04-29 11:37:28,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +35: [2023-04-29 11:37:28,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +35: [2023-04-29 11:37:28,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +39: [2023-04-29 11:37:28,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +37: [2023-04-29 11:37:28,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +63: [2023-04-29 11:37:28,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +39: [2023-04-29 11:37:28,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +39: [2023-04-29 11:37:28,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +37: [2023-04-29 11:37:28,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +63: [2023-04-29 11:37:28,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 4: [2023-04-29 11:37:28,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +39: [2023-04-29 11:37:28,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +51: [2023-04-29 11:37:28,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +38: [2023-04-29 11:37:28,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +44: [2023-04-29 11:37:28,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +45: [2023-04-29 11:37:28,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 0: [2023-04-29 11:37:28,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 0: [2023-04-29 11:37:28,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 5: [2023-04-29 11:37:28,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 5: [2023-04-29 11:37:28,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 5: [2023-04-29 11:37:28,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. + 0: [2023-04-29 11:37:28,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 4: [2023-04-29 11:37:28,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 0: [2023-04-29 11:37:28,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +56: [2023-04-29 11:37:28,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +56: [2023-04-29 11:37:28,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +56: [2023-04-29 11:37:28,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +62: [2023-04-29 11:37:28,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +56: [2023-04-29 11:37:28,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +37: [2023-04-29 11:37:28,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +63: [2023-04-29 11:37:28,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +39: [2023-04-29 11:37:28,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +63: [2023-04-29 11:37:28,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +63: [2023-04-29 11:37:28,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +63: [2023-04-29 11:37:28,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +62: [2023-04-29 11:37:28,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 0: [2023-04-29 11:37:28,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +41: [2023-04-29 11:37:28,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +41: [2023-04-29 11:37:28,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 5: [2023-04-29 11:37:28,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +39: [2023-04-29 11:37:28,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +39: [2023-04-29 11:37:28,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +39: [2023-04-29 11:37:28,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 0: [2023-04-29 11:37:28,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +38: [2023-04-29 11:37:28,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +38: [2023-04-29 11:37:28,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. + 0: [2023-04-29 11:37:28,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +45: [2023-04-29 11:37:28,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 0: [2023-04-29 11:37:28,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +41: [2023-04-29 11:37:28,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +38: [2023-04-29 11:37:28,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +38: [2023-04-29 11:37:28,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +62: [2023-04-29 11:37:28,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +47: [2023-04-29 11:37:28,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +36: [2023-04-29 11:37:28,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +36: [2023-04-29 11:37:28,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +36: [2023-04-29 11:37:28,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +36: [2023-04-29 11:37:28,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +41: [2023-04-29 11:37:28,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +47: [2023-04-29 11:37:28,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +51: [2023-04-29 11:37:28,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +62: [2023-04-29 11:37:28,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +51: [2023-04-29 11:37:28,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +58: [2023-04-29 11:37:28,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +52: [2023-04-29 11:37:28,111] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +58: [2023-04-29 11:37:28,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +52: [2023-04-29 11:37:28,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +52: [2023-04-29 11:37:28,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +58: [2023-04-29 11:37:28,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +58: [2023-04-29 11:37:28,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +52: [2023-04-29 11:37:28,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +41: [2023-04-29 11:37:28,114] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +52: [2023-04-29 11:37:28,114] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +55: [2023-04-29 11:37:28,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +55: [2023-04-29 11:37:28,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +55: [2023-04-29 11:37:28,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +55: [2023-04-29 11:37:28,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +45: [2023-04-29 11:37:28,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +61: [2023-04-29 11:37:28,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +61: [2023-04-29 11:37:28,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +47: [2023-04-29 11:37:28,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +27: [2023-04-29 11:37:28,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +27: [2023-04-29 11:37:28,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +56: [2023-04-29 11:37:28,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +56: [2023-04-29 11:37:28,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +56: [2023-04-29 11:37:28,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +56: [2023-04-29 11:37:28,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +27: [2023-04-29 11:37:28,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +27: [2023-04-29 11:37:28,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +41: [2023-04-29 11:37:28,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +47: [2023-04-29 11:37:28,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +41: [2023-04-29 11:37:28,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +52: [2023-04-29 11:37:28,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +52: [2023-04-29 11:37:28,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +60: [2023-04-29 11:37:28,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +52: [2023-04-29 11:37:28,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +52: [2023-04-29 11:37:28,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +51: [2023-04-29 11:37:28,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +52: [2023-04-29 11:37:28,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +59: [2023-04-29 11:37:28,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +62: [2023-04-29 11:37:28,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +62: [2023-04-29 11:37:28,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +45: [2023-04-29 11:37:28,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +61: [2023-04-29 11:37:28,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +61: [2023-04-29 11:37:28,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +60: [2023-04-29 11:37:28,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +51: [2023-04-29 11:37:28,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +52: [2023-04-29 11:37:28,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +52: [2023-04-29 11:37:28,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +37: [2023-04-29 11:37:28,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +60: [2023-04-29 11:37:28,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +60: [2023-04-29 11:37:28,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +59: [2023-04-29 11:37:28,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +59: [2023-04-29 11:37:28,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +62: [2023-04-29 11:37:28,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +62: [2023-04-29 11:37:28,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +37: [2023-04-29 11:37:28,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +47: [2023-04-29 11:37:28,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +47: [2023-04-29 11:37:28,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +47: [2023-04-29 11:37:28,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +36: [2023-04-29 11:37:28,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +47: [2023-04-29 11:37:28,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +59: [2023-04-29 11:37:28,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +47: [2023-04-29 11:37:28,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +38: [2023-04-29 11:37:28,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +38: [2023-04-29 11:37:28,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +37: [2023-04-29 11:37:28,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +47: [2023-04-29 11:37:28,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +36: [2023-04-29 11:37:28,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +36: [2023-04-29 11:37:28,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +36: [2023-04-29 11:37:28,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +16: [2023-04-29 11:37:28,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +16: [2023-04-29 11:37:28,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +36: [2023-04-29 11:37:28,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +36: [2023-04-29 11:37:28,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +38: [2023-04-29 11:37:28,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +16: [2023-04-29 11:37:28,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +16: [2023-04-29 11:37:28,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +16: [2023-04-29 11:37:28,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +16: [2023-04-29 11:37:28,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +16: [2023-04-29 11:37:28,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +16: [2023-04-29 11:37:28,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +56: [2023-04-29 11:37:28,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +56: [2023-04-29 11:37:28,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 5: [2023-04-29 11:37:28,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +38: [2023-04-29 11:37:28,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +55: [2023-04-29 11:37:28,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +55: [2023-04-29 11:37:28,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +55: [2023-04-29 11:37:28,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +55: [2023-04-29 11:37:28,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 5: [2023-04-29 11:37:28,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 5: [2023-04-29 11:37:28,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 8: [2023-04-29 11:37:28,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 8: [2023-04-29 11:37:28,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 8: [2023-04-29 11:37:28,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 8: [2023-04-29 11:37:28,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +36: [2023-04-29 11:37:28,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +56: [2023-04-29 11:37:28,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +36: [2023-04-29 11:37:28,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +56: [2023-04-29 11:37:28,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +16: [2023-04-29 11:37:28,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +47: [2023-04-29 11:37:28,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +16: [2023-04-29 11:37:28,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +51: [2023-04-29 11:37:28,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +51: [2023-04-29 11:37:28,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +36: [2023-04-29 11:37:28,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +36: [2023-04-29 11:37:28,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +60: [2023-04-29 11:37:28,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +47: [2023-04-29 11:37:28,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +60: [2023-04-29 11:37:28,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 5: [2023-04-29 11:37:28,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +38: [2023-04-29 11:37:28,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +61: [2023-04-29 11:37:28,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +36: [2023-04-29 11:37:28,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +61: [2023-04-29 11:37:28,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +16: [2023-04-29 11:37:28,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +39: [2023-04-29 11:37:28,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +59: [2023-04-29 11:37:28,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +16: [2023-04-29 11:37:28,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt... +36: [2023-04-29 11:37:28,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +16: [2023-04-29 11:37:28,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +16: [2023-04-29 11:37:28,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +16: [2023-04-29 11:37:28,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... +60: [2023-04-29 11:37:28,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +16: [2023-04-29 11:37:28,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt... + 0: [2023-04-29 11:37:28,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +60: [2023-04-29 11:37:28,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +61: [2023-04-29 11:37:28,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +61: [2023-04-29 11:37:28,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +47: [2023-04-29 11:37:28,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +47: [2023-04-29 11:37:28,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +63: [2023-04-29 11:37:28,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +60: [2023-04-29 11:37:28,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +60: [2023-04-29 11:37:28,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +59: [2023-04-29 11:37:28,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +60: [2023-04-29 11:37:28,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +60: [2023-04-29 11:37:28,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +47: [2023-04-29 11:37:28,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +47: [2023-04-29 11:37:28,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +52: [2023-04-29 11:37:28,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +41: [2023-04-29 11:37:28,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +63: [2023-04-29 11:37:28,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 8: [2023-04-29 11:37:28,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +42: [2023-04-29 11:37:28,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +42: [2023-04-29 11:37:28,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +59: [2023-04-29 11:37:28,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +45: [2023-04-29 11:37:28,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +45: [2023-04-29 11:37:28,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +42: [2023-04-29 11:37:28,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +42: [2023-04-29 11:37:28,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +45: [2023-04-29 11:37:28,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +45: [2023-04-29 11:37:28,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +56: [2023-04-29 11:37:28,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +56: [2023-04-29 11:37:28,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +56: [2023-04-29 11:37:28,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +59: [2023-04-29 11:37:28,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +41: [2023-04-29 11:37:28,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +63: [2023-04-29 11:37:28,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +63: [2023-04-29 11:37:28,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +39: [2023-04-29 11:37:28,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +39: [2023-04-29 11:37:28,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 0: [2023-04-29 11:37:28,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 0: [2023-04-29 11:37:28,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 0: [2023-04-29 11:37:28,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +38: [2023-04-29 11:37:28,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +39: [2023-04-29 11:37:28,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 8: [2023-04-29 11:37:28,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +57: [2023-04-29 11:37:28,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +57: [2023-04-29 11:37:28,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +56: [2023-04-29 11:37:28,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +54: [2023-04-29 11:37:28,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +54: [2023-04-29 11:37:28,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +54: [2023-04-29 11:37:28,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +54: [2023-04-29 11:37:28,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +39: [2023-04-29 11:37:28,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 8: [2023-04-29 11:37:28,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +52: [2023-04-29 11:37:28,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +38: [2023-04-29 11:37:28,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +57: [2023-04-29 11:37:28,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 8: [2023-04-29 11:37:28,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +57: [2023-04-29 11:37:28,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +57: [2023-04-29 11:37:28,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +57: [2023-04-29 11:37:28,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +41: [2023-04-29 11:37:28,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +34: [2023-04-29 11:37:28,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +34: [2023-04-29 11:37:28,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +34: [2023-04-29 11:37:28,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +52: [2023-04-29 11:37:28,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +38: [2023-04-29 11:37:28,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +38: [2023-04-29 11:37:28,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +57: [2023-04-29 11:37:28,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +34: [2023-04-29 11:37:28,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 0: [2023-04-29 11:37:28,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +57: [2023-04-29 11:37:28,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +32: [2023-04-29 11:37:28,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +32: [2023-04-29 11:37:28,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +32: [2023-04-29 11:37:28,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +32: [2023-04-29 11:37:28,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +40: [2023-04-29 11:37:28,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +40: [2023-04-29 11:37:28,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +40: [2023-04-29 11:37:28,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +40: [2023-04-29 11:37:28,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +52: [2023-04-29 11:37:28,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +41: [2023-04-29 11:37:28,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +63: [2023-04-29 11:37:28,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +34: [2023-04-29 11:37:28,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +34: [2023-04-29 11:37:28,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +41: [2023-04-29 11:37:28,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +20: [2023-04-29 11:37:28,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +20: [2023-04-29 11:37:28,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +20: [2023-04-29 11:37:28,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +34: [2023-04-29 11:37:28,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +20: [2023-04-29 11:37:28,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +40: [2023-04-29 11:37:28,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +41: [2023-04-29 11:37:28,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +52: [2023-04-29 11:37:28,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +52: [2023-04-29 11:37:28,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +60: [2023-04-29 11:37:28,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +34: [2023-04-29 11:37:28,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +40: [2023-04-29 11:37:28,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +40: [2023-04-29 11:37:28,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +40: [2023-04-29 11:37:28,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +60: [2023-04-29 11:37:28,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +41: [2023-04-29 11:37:28,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +55: [2023-04-29 11:37:28,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +55: [2023-04-29 11:37:28,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +63: [2023-04-29 11:37:28,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +55: [2023-04-29 11:37:28,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +55: [2023-04-29 11:37:28,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +52: [2023-04-29 11:37:28,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +52: [2023-04-29 11:37:28,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +60: [2023-04-29 11:37:28,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +56: [2023-04-29 11:37:28,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +56: [2023-04-29 11:37:28,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +42: [2023-04-29 11:37:28,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +60: [2023-04-29 11:37:28,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +41: [2023-04-29 11:37:28,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +56: [2023-04-29 11:37:28,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +42: [2023-04-29 11:37:28,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +50: [2023-04-29 11:37:28,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +50: [2023-04-29 11:37:28,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +42: [2023-04-29 11:37:28,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +45: [2023-04-29 11:37:28,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +39: [2023-04-29 11:37:28,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +39: [2023-04-29 11:37:28,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +50: [2023-04-29 11:37:28,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +50: [2023-04-29 11:37:28,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +63: [2023-04-29 11:37:28,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +36: [2023-04-29 11:37:28,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +55: [2023-04-29 11:37:28,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +30: [2023-04-29 11:37:28,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +30: [2023-04-29 11:37:28,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +30: [2023-04-29 11:37:28,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +30: [2023-04-29 11:37:28,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +30: [2023-04-29 11:37:28,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +30: [2023-04-29 11:37:28,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +30: [2023-04-29 11:37:28,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +39: [2023-04-29 11:37:28,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +55: [2023-04-29 11:37:28,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +55: [2023-04-29 11:37:28,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +30: [2023-04-29 11:37:28,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +46: [2023-04-29 11:37:28,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +46: [2023-04-29 11:37:28,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +55: [2023-04-29 11:37:28,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +45: [2023-04-29 11:37:28,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +45: [2023-04-29 11:37:28,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +46: [2023-04-29 11:37:28,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +45: [2023-04-29 11:37:28,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +46: [2023-04-29 11:37:28,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +52: [2023-04-29 11:37:28,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +63: [2023-04-29 11:37:28,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 0: [2023-04-29 11:37:28,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 0: [2023-04-29 11:37:28,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +52: [2023-04-29 11:37:28,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +56: [2023-04-29 11:37:28,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +52: [2023-04-29 11:37:28,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +36: [2023-04-29 11:37:28,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +42: [2023-04-29 11:37:28,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +30: [2023-04-29 11:37:28,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +30: [2023-04-29 11:37:28,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +36: [2023-04-29 11:37:28,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +54: [2023-04-29 11:37:28,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +30: [2023-04-29 11:37:28,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +52: [2023-04-29 11:37:28,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +54: [2023-04-29 11:37:28,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 0: [2023-04-29 11:37:28,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +30: [2023-04-29 11:37:28,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +61: [2023-04-29 11:37:28,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +61: [2023-04-29 11:37:28,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +54: [2023-04-29 11:37:28,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +30: [2023-04-29 11:37:28,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +61: [2023-04-29 11:37:28,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +30: [2023-04-29 11:37:28,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +61: [2023-04-29 11:37:28,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +30: [2023-04-29 11:37:28,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +34: [2023-04-29 11:37:28,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +34: [2023-04-29 11:37:28,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +43: [2023-04-29 11:37:28,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +43: [2023-04-29 11:37:28,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +30: [2023-04-29 11:37:28,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +43: [2023-04-29 11:37:28,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +43: [2023-04-29 11:37:28,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +54: [2023-04-29 11:37:28,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +36: [2023-04-29 11:37:28,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +32: [2023-04-29 11:37:28,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 6: [2023-04-29 11:37:28,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 6: [2023-04-29 11:37:28,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 6: [2023-04-29 11:37:28,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 6: [2023-04-29 11:37:28,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +38: [2023-04-29 11:37:28,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +61: [2023-04-29 11:37:28,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +56: [2023-04-29 11:37:28,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +56: [2023-04-29 11:37:28,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 8: [2023-04-29 11:37:28,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +43: [2023-04-29 11:37:28,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 8: [2023-04-29 11:37:28,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +52: [2023-04-29 11:37:28,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +36: [2023-04-29 11:37:28,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 8: [2023-04-29 11:37:28,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 8: [2023-04-29 11:37:28,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +43: [2023-04-29 11:37:28,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +55: [2023-04-29 11:37:28,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +55: [2023-04-29 11:37:28,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +38: [2023-04-29 11:37:28,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +38: [2023-04-29 11:37:28,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +34: [2023-04-29 11:37:28,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +32: [2023-04-29 11:37:28,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +43: [2023-04-29 11:37:28,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +43: [2023-04-29 11:37:28,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +36: [2023-04-29 11:37:28,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +32: [2023-04-29 11:37:28,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +32: [2023-04-29 11:37:28,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +61: [2023-04-29 11:37:28,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +61: [2023-04-29 11:37:28,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +34: [2023-04-29 11:37:28,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. + 6: [2023-04-29 11:37:28,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 6: [2023-04-29 11:37:28,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 6: [2023-04-29 11:37:28,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 6: [2023-04-29 11:37:28,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +61: [2023-04-29 11:37:28,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +36: [2023-04-29 11:37:28,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +36: [2023-04-29 11:37:28,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +47: [2023-04-29 11:37:28,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +38: [2023-04-29 11:37:28,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +38: [2023-04-29 11:37:28,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 8: [2023-04-29 11:37:28,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +52: [2023-04-29 11:37:28,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +52: [2023-04-29 11:37:28,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 8: [2023-04-29 11:37:28,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +56: [2023-04-29 11:37:28,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +56: [2023-04-29 11:37:28,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +55: [2023-04-29 11:37:28,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +20: [2023-04-29 11:37:28,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +20: [2023-04-29 11:37:28,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +21: [2023-04-29 11:37:28,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +21: [2023-04-29 11:37:28,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +21: [2023-04-29 11:37:28,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +55: [2023-04-29 11:37:28,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +55: [2023-04-29 11:37:28,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +21: [2023-04-29 11:37:28,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +20: [2023-04-29 11:37:28,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +36: [2023-04-29 11:37:28,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +36: [2023-04-29 11:37:28,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... + 8: [2023-04-29 11:37:28,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 8: [2023-04-29 11:37:28,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +47: [2023-04-29 11:37:28,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +20: [2023-04-29 11:37:28,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +56: [2023-04-29 11:37:28,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +55: [2023-04-29 11:37:28,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +21: [2023-04-29 11:37:28,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +38: [2023-04-29 11:37:28,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +38: [2023-04-29 11:37:28,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +46: [2023-04-29 11:37:28,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +21: [2023-04-29 11:37:28,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +21: [2023-04-29 11:37:28,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +55: [2023-04-29 11:37:28,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +21: [2023-04-29 11:37:28,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +50: [2023-04-29 11:37:28,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +50: [2023-04-29 11:37:28,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +33: [2023-04-29 11:37:28,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +33: [2023-04-29 11:37:28,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +33: [2023-04-29 11:37:28,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +56: [2023-04-29 11:37:28,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +33: [2023-04-29 11:37:28,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +38: [2023-04-29 11:37:28,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +50: [2023-04-29 11:37:28,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +36: [2023-04-29 11:37:28,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +50: [2023-04-29 11:37:28,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +16: [2023-04-29 11:37:28,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +16: [2023-04-29 11:37:28,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +16: [2023-04-29 11:37:28,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +57: [2023-04-29 11:37:28,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +57: [2023-04-29 11:37:28,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +38: [2023-04-29 11:37:28,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +56: [2023-04-29 11:37:28,229] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +50: [2023-04-29 11:37:28,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +57: [2023-04-29 11:37:28,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +57: [2023-04-29 11:37:28,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +50: [2023-04-29 11:37:28,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +47: [2023-04-29 11:37:28,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +46: [2023-04-29 11:37:28,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +55: [2023-04-29 11:37:28,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +56: [2023-04-29 11:37:28,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +50: [2023-04-29 11:37:28,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +46: [2023-04-29 11:37:28,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +52: [2023-04-29 11:37:28,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +16: [2023-04-29 11:37:28,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_00-model_states.pt. +61: [2023-04-29 11:37:28,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +61: [2023-04-29 11:37:28,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +47: [2023-04-29 11:37:28,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +61: [2023-04-29 11:37:28,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +38: [2023-04-29 11:37:28,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +43: [2023-04-29 11:37:28,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +43: [2023-04-29 11:37:28,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +36: [2023-04-29 11:37:28,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +46: [2023-04-29 11:37:28,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +18: [2023-04-29 11:37:28,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +18: [2023-04-29 11:37:28,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 8: [2023-04-29 11:37:28,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +34: [2023-04-29 11:37:28,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +50: [2023-04-29 11:37:28,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +50: [2023-04-29 11:37:28,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +18: [2023-04-29 11:37:28,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +18: [2023-04-29 11:37:28,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +50: [2023-04-29 11:37:28,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +38: [2023-04-29 11:37:28,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +43: [2023-04-29 11:37:28,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +43: [2023-04-29 11:37:28,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +50: [2023-04-29 11:37:28,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +35: [2023-04-29 11:37:28,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +35: [2023-04-29 11:37:28,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +35: [2023-04-29 11:37:28,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +35: [2023-04-29 11:37:28,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +47: [2023-04-29 11:37:28,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +47: [2023-04-29 11:37:28,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +34: [2023-04-29 11:37:28,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +50: [2023-04-29 11:37:28,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +32: [2023-04-29 11:37:28,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +32: [2023-04-29 11:37:28,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +34: [2023-04-29 11:37:28,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +61: [2023-04-29 11:37:28,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +61: [2023-04-29 11:37:28,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +61: [2023-04-29 11:37:28,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... + 8: [2023-04-29 11:37:28,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +61: [2023-04-29 11:37:28,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +32: [2023-04-29 11:37:28,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +32: [2023-04-29 11:37:28,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +36: [2023-04-29 11:37:28,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +36: [2023-04-29 11:37:28,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +47: [2023-04-29 11:37:28,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +47: [2023-04-29 11:37:28,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +32: [2023-04-29 11:37:28,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +32: [2023-04-29 11:37:28,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +36: [2023-04-29 11:37:28,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +34: [2023-04-29 11:37:28,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +61: [2023-04-29 11:37:28,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +32: [2023-04-29 11:37:28,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +57: [2023-04-29 11:37:28,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +57: [2023-04-29 11:37:28,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +33: [2023-04-29 11:37:28,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +59: [2023-04-29 11:37:28,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +59: [2023-04-29 11:37:28,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +40: [2023-04-29 11:37:28,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +32: [2023-04-29 11:37:28,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +40: [2023-04-29 11:37:28,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +40: [2023-04-29 11:37:28,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +60: [2023-04-29 11:37:28,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +16: [2023-04-29 11:37:28,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +57: [2023-04-29 11:37:28,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +57: [2023-04-29 11:37:28,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +57: [2023-04-29 11:37:28,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +57: [2023-04-29 11:37:28,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +16: [2023-04-29 11:37:28,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 8: [2023-04-29 11:37:28,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +33: [2023-04-29 11:37:28,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +34: [2023-04-29 11:37:28,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +34: [2023-04-29 11:37:28,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +60: [2023-04-29 11:37:28,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 8: [2023-04-29 11:37:28,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +33: [2023-04-29 11:37:28,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +59: [2023-04-29 11:37:28,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +33: [2023-04-29 11:37:28,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +59: [2023-04-29 11:37:28,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +30: [2023-04-29 11:37:28,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +40: [2023-04-29 11:37:28,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +16: [2023-04-29 11:37:28,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +40: [2023-04-29 11:37:28,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +57: [2023-04-29 11:37:28,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 8: [2023-04-29 11:37:28,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +55: [2023-04-29 11:37:28,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +60: [2023-04-29 11:37:28,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +18: [2023-04-29 11:37:28,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +17: [2023-04-29 11:37:28,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +17: [2023-04-29 11:37:28,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +17: [2023-04-29 11:37:28,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +18: [2023-04-29 11:37:28,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +43: [2023-04-29 11:37:28,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +60: [2023-04-29 11:37:28,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +17: [2023-04-29 11:37:28,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +60: [2023-04-29 11:37:28,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +36: [2023-04-29 11:37:28,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +18: [2023-04-29 11:37:28,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +18: [2023-04-29 11:37:28,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +43: [2023-04-29 11:37:28,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 8: [2023-04-29 11:37:28,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... + 8: [2023-04-29 11:37:28,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +16: [2023-04-29 11:37:28,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +55: [2023-04-29 11:37:28,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +49: [2023-04-29 11:37:28,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +49: [2023-04-29 11:37:28,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +61: [2023-04-29 11:37:28,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +60: [2023-04-29 11:37:28,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +45: [2023-04-29 11:37:28,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +35: [2023-04-29 11:37:28,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +30: [2023-04-29 11:37:28,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +35: [2023-04-29 11:37:28,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +43: [2023-04-29 11:37:28,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +43: [2023-04-29 11:37:28,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +43: [2023-04-29 11:37:28,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +49: [2023-04-29 11:37:28,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +49: [2023-04-29 11:37:28,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. + 8: [2023-04-29 11:37:28,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +62: [2023-04-29 11:37:28,272] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +62: [2023-04-29 11:37:28,272] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +35: [2023-04-29 11:37:28,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +35: [2023-04-29 11:37:28,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +62: [2023-04-29 11:37:28,272] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +60: [2023-04-29 11:37:28,272] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +62: [2023-04-29 11:37:28,272] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +57: [2023-04-29 11:37:28,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +55: [2023-04-29 11:37:28,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +39: [2023-04-29 11:37:28,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +39: [2023-04-29 11:37:28,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +45: [2023-04-29 11:37:28,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +45: [2023-04-29 11:37:28,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +32: [2023-04-29 11:37:28,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +62: [2023-04-29 11:37:28,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +45: [2023-04-29 11:37:28,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +30: [2023-04-29 11:37:28,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +30: [2023-04-29 11:37:28,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +57: [2023-04-29 11:37:28,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +40: [2023-04-29 11:37:28,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +40: [2023-04-29 11:37:28,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +57: [2023-04-29 11:37:28,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +40: [2023-04-29 11:37:28,278] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +39: [2023-04-29 11:37:28,278] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +60: [2023-04-29 11:37:28,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +39: [2023-04-29 11:37:28,278] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +62: [2023-04-29 11:37:28,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +62: [2023-04-29 11:37:28,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +34: [2023-04-29 11:37:28,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +45: [2023-04-29 11:37:28,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +62: [2023-04-29 11:37:28,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +55: [2023-04-29 11:37:28,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +32: [2023-04-29 11:37:28,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +40: [2023-04-29 11:37:28,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +45: [2023-04-29 11:37:28,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +34: [2023-04-29 11:37:28,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 8: [2023-04-29 11:37:28,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 6: [2023-04-29 11:37:28,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 6: [2023-04-29 11:37:28,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +40: [2023-04-29 11:37:28,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +59: [2023-04-29 11:37:28,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +45: [2023-04-29 11:37:28,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +40: [2023-04-29 11:37:28,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +59: [2023-04-29 11:37:28,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 8: [2023-04-29 11:37:28,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +21: [2023-04-29 11:37:28,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +34: [2023-04-29 11:37:28,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +34: [2023-04-29 11:37:28,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +55: [2023-04-29 11:37:28,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +51: [2023-04-29 11:37:28,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +51: [2023-04-29 11:37:28,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +51: [2023-04-29 11:37:28,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +51: [2023-04-29 11:37:28,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +45: [2023-04-29 11:37:28,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +50: [2023-04-29 11:37:28,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +44: [2023-04-29 11:37:28,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +44: [2023-04-29 11:37:28,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. + 6: [2023-04-29 11:37:28,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 6: [2023-04-29 11:37:28,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +17: [2023-04-29 11:37:28,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +30: [2023-04-29 11:37:28,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +44: [2023-04-29 11:37:28,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +44: [2023-04-29 11:37:28,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +61: [2023-04-29 11:37:28,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +57: [2023-04-29 11:37:28,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +61: [2023-04-29 11:37:28,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +17: [2023-04-29 11:37:28,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +50: [2023-04-29 11:37:28,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +53: [2023-04-29 11:37:28,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +53: [2023-04-29 11:37:28,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +32: [2023-04-29 11:37:28,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +61: [2023-04-29 11:37:28,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +43: [2023-04-29 11:37:28,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +17: [2023-04-29 11:37:28,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +32: [2023-04-29 11:37:28,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +32: [2023-04-29 11:37:28,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +40: [2023-04-29 11:37:28,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +53: [2023-04-29 11:37:28,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +53: [2023-04-29 11:37:28,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +40: [2023-04-29 11:37:28,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +17: [2023-04-29 11:37:28,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +59: [2023-04-29 11:37:28,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +58: [2023-04-29 11:37:28,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +58: [2023-04-29 11:37:28,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +58: [2023-04-29 11:37:28,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +61: [2023-04-29 11:37:28,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +58: [2023-04-29 11:37:28,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +49: [2023-04-29 11:37:28,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +55: [2023-04-29 11:37:28,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +30: [2023-04-29 11:37:28,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +21: [2023-04-29 11:37:28,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +21: [2023-04-29 11:37:28,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +21: [2023-04-29 11:37:28,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +50: [2023-04-29 11:37:28,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +49: [2023-04-29 11:37:28,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +43: [2023-04-29 11:37:28,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +49: [2023-04-29 11:37:28,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +53: [2023-04-29 11:37:28,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +53: [2023-04-29 11:37:28,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +53: [2023-04-29 11:37:28,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +53: [2023-04-29 11:37:28,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +59: [2023-04-29 11:37:28,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +63: [2023-04-29 11:37:28,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +63: [2023-04-29 11:37:28,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +63: [2023-04-29 11:37:28,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +32: [2023-04-29 11:37:28,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +63: [2023-04-29 11:37:28,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_30-model_01-model_states.pt. +32: [2023-04-29 11:37:28,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +43: [2023-04-29 11:37:28,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +49: [2023-04-29 11:37:28,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +32: [2023-04-29 11:37:28,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +50: [2023-04-29 11:37:28,301] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 8: [2023-04-29 11:37:28,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +57: [2023-04-29 11:37:28,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 8: [2023-04-29 11:37:28,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +29: [2023-04-29 11:37:28,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +29: [2023-04-29 11:37:28,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +29: [2023-04-29 11:37:28,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +53: [2023-04-29 11:37:28,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +50: [2023-04-29 11:37:28,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +34: [2023-04-29 11:37:28,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +53: [2023-04-29 11:37:28,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +53: [2023-04-29 11:37:28,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +53: [2023-04-29 11:37:28,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +29: [2023-04-29 11:37:28,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +54: [2023-04-29 11:37:28,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +54: [2023-04-29 11:37:28,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +54: [2023-04-29 11:37:28,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +54: [2023-04-29 11:37:28,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +54: [2023-04-29 11:37:28,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +54: [2023-04-29 11:37:28,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +54: [2023-04-29 11:37:28,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +54: [2023-04-29 11:37:28,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +30: [2023-04-29 11:37:28,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +55: [2023-04-29 11:37:28,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +14: [2023-04-29 11:37:28,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +14: [2023-04-29 11:37:28,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +48: [2023-04-29 11:37:28,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +48: [2023-04-29 11:37:28,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +30: [2023-04-29 11:37:28,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +14: [2023-04-29 11:37:28,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +29: [2023-04-29 11:37:28,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +20: [2023-04-29 11:37:28,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +20: [2023-04-29 11:37:28,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +34: [2023-04-29 11:37:28,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +14: [2023-04-29 11:37:28,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 8: [2023-04-29 11:37:28,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 6: [2023-04-29 11:37:28,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +29: [2023-04-29 11:37:28,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +10: [2023-04-29 11:37:28,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +20: [2023-04-29 11:37:28,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +10: [2023-04-29 11:37:28,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +20: [2023-04-29 11:37:28,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +20: [2023-04-29 11:37:28,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 8: [2023-04-29 11:37:28,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +10: [2023-04-29 11:37:28,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +20: [2023-04-29 11:37:28,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +55: [2023-04-29 11:37:28,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +20: [2023-04-29 11:37:28,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +43: [2023-04-29 11:37:28,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +20: [2023-04-29 11:37:28,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +10: [2023-04-29 11:37:28,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +29: [2023-04-29 11:37:28,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +54: [2023-04-29 11:37:28,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +39: [2023-04-29 11:37:28,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +48: [2023-04-29 11:37:28,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +48: [2023-04-29 11:37:28,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +34: [2023-04-29 11:37:28,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +48: [2023-04-29 11:37:28,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +29: [2023-04-29 11:37:28,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +54: [2023-04-29 11:37:28,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +48: [2023-04-29 11:37:28,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +21: [2023-04-29 11:37:28,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +54: [2023-04-29 11:37:28,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +54: [2023-04-29 11:37:28,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... + 6: [2023-04-29 11:37:28,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +50: [2023-04-29 11:37:28,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +54: [2023-04-29 11:37:28,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +54: [2023-04-29 11:37:28,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +40: [2023-04-29 11:37:28,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +54: [2023-04-29 11:37:28,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +48: [2023-04-29 11:37:28,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +39: [2023-04-29 11:37:28,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +39: [2023-04-29 11:37:28,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +48: [2023-04-29 11:37:28,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +39: [2023-04-29 11:37:28,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +54: [2023-04-29 11:37:28,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +44: [2023-04-29 11:37:28,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +46: [2023-04-29 11:37:28,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +46: [2023-04-29 11:37:28,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +20: [2023-04-29 11:37:28,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +51: [2023-04-29 11:37:28,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +51: [2023-04-29 11:37:28,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +48: [2023-04-29 11:37:28,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +11: [2023-04-29 11:37:28,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +44: [2023-04-29 11:37:28,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +11: [2023-04-29 11:37:28,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +11: [2023-04-29 11:37:28,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +44: [2023-04-29 11:37:28,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +34: [2023-04-29 11:37:28,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +48: [2023-04-29 11:37:28,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. + 6: [2023-04-29 11:37:28,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +20: [2023-04-29 11:37:28,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +11: [2023-04-29 11:37:28,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +20: [2023-04-29 11:37:28,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 4: [2023-04-29 11:37:28,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +40: [2023-04-29 11:37:28,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +44: [2023-04-29 11:37:28,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 4: [2023-04-29 11:37:28,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 4: [2023-04-29 11:37:28,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 4: [2023-04-29 11:37:28,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +40: [2023-04-29 11:37:28,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +46: [2023-04-29 11:37:28,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +46: [2023-04-29 11:37:28,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +48: [2023-04-29 11:37:28,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +46: [2023-04-29 11:37:28,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +46: [2023-04-29 11:37:28,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +46: [2023-04-29 11:37:28,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +46: [2023-04-29 11:37:28,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +34: [2023-04-29 11:37:28,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +20: [2023-04-29 11:37:28,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +20: [2023-04-29 11:37:28,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... + 6: [2023-04-29 11:37:28,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +37: [2023-04-29 11:37:28,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +37: [2023-04-29 11:37:28,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +37: [2023-04-29 11:37:28,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +20: [2023-04-29 11:37:28,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +20: [2023-04-29 11:37:28,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +37: [2023-04-29 11:37:28,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +32: [2023-04-29 11:37:28,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +51: [2023-04-29 11:37:28,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +20: [2023-04-29 11:37:28,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +31: [2023-04-29 11:37:28,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +31: [2023-04-29 11:37:28,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +31: [2023-04-29 11:37:28,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +48: [2023-04-29 11:37:28,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +11: [2023-04-29 11:37:28,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +61: [2023-04-29 11:37:28,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +46: [2023-04-29 11:37:28,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +11: [2023-04-29 11:37:28,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +31: [2023-04-29 11:37:28,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +51: [2023-04-29 11:37:28,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +11: [2023-04-29 11:37:28,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +11: [2023-04-29 11:37:28,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... + 4: [2023-04-29 11:37:28,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... + 4: [2023-04-29 11:37:28,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +46: [2023-04-29 11:37:28,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +43: [2023-04-29 11:37:28,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +46: [2023-04-29 11:37:28,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +46: [2023-04-29 11:37:28,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +46: [2023-04-29 11:37:28,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +32: [2023-04-29 11:37:28,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +46: [2023-04-29 11:37:28,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +34: [2023-04-29 11:37:28,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +46: [2023-04-29 11:37:28,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +46: [2023-04-29 11:37:28,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +61: [2023-04-29 11:37:28,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +34: [2023-04-29 11:37:28,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 4: [2023-04-29 11:37:28,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +58: [2023-04-29 11:37:28,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... + 4: [2023-04-29 11:37:28,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +31: [2023-04-29 11:37:28,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +53: [2023-04-29 11:37:28,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +53: [2023-04-29 11:37:28,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +32: [2023-04-29 11:37:28,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +50: [2023-04-29 11:37:28,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +31: [2023-04-29 11:37:28,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +31: [2023-04-29 11:37:28,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +42: [2023-04-29 11:37:28,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +63: [2023-04-29 11:37:28,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +63: [2023-04-29 11:37:28,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +42: [2023-04-29 11:37:28,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +42: [2023-04-29 11:37:28,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +42: [2023-04-29 11:37:28,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +42: [2023-04-29 11:37:28,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +42: [2023-04-29 11:37:28,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +50: [2023-04-29 11:37:28,326] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +63: [2023-04-29 11:37:28,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +42: [2023-04-29 11:37:28,326] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +42: [2023-04-29 11:37:28,326] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +31: [2023-04-29 11:37:28,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +21: [2023-04-29 11:37:28,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +63: [2023-04-29 11:37:28,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +58: [2023-04-29 11:37:28,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +58: [2023-04-29 11:37:28,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +21: [2023-04-29 11:37:28,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +58: [2023-04-29 11:37:28,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +61: [2023-04-29 11:37:28,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +32: [2023-04-29 11:37:28,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +43: [2023-04-29 11:37:28,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +53: [2023-04-29 11:37:28,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +34: [2023-04-29 11:37:28,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +50: [2023-04-29 11:37:28,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +21: [2023-04-29 11:37:28,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +34: [2023-04-29 11:37:28,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +42: [2023-04-29 11:37:28,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +14: [2023-04-29 11:37:28,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +53: [2023-04-29 11:37:28,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt... +42: [2023-04-29 11:37:28,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +42: [2023-04-29 11:37:28,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +50: [2023-04-29 11:37:28,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +42: [2023-04-29 11:37:28,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +50: [2023-04-29 11:37:28,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 8: [2023-04-29 11:37:28,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 8: [2023-04-29 11:37:28,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +57: [2023-04-29 11:37:28,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +42: [2023-04-29 11:37:28,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +14: [2023-04-29 11:37:28,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +49: [2023-04-29 11:37:28,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +49: [2023-04-29 11:37:28,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +14: [2023-04-29 11:37:28,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +34: [2023-04-29 11:37:28,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +42: [2023-04-29 11:37:28,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +14: [2023-04-29 11:37:28,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +49: [2023-04-29 11:37:28,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +49: [2023-04-29 11:37:28,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +42: [2023-04-29 11:37:28,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +42: [2023-04-29 11:37:28,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +10: [2023-04-29 11:37:28,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +10: [2023-04-29 11:37:28,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +10: [2023-04-29 11:37:28,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +50: [2023-04-29 11:37:28,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +57: [2023-04-29 11:37:28,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +48: [2023-04-29 11:37:28,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +10: [2023-04-29 11:37:28,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +57: [2023-04-29 11:37:28,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +57: [2023-04-29 11:37:28,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +57: [2023-04-29 11:37:28,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +62: [2023-04-29 11:37:28,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +43: [2023-04-29 11:37:28,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +48: [2023-04-29 11:37:28,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +49: [2023-04-29 11:37:28,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +17: [2023-04-29 11:37:28,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +17: [2023-04-29 11:37:28,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +17: [2023-04-29 11:37:28,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +17: [2023-04-29 11:37:28,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +62: [2023-04-29 11:37:28,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +62: [2023-04-29 11:37:28,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +49: [2023-04-29 11:37:28,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +49: [2023-04-29 11:37:28,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +59: [2023-04-29 11:37:28,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +37: [2023-04-29 11:37:28,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +50: [2023-04-29 11:37:28,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +49: [2023-04-29 11:37:28,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +37: [2023-04-29 11:37:28,345] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +48: [2023-04-29 11:37:28,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +43: [2023-04-29 11:37:28,345] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +50: [2023-04-29 11:37:28,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +62: [2023-04-29 11:37:28,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +62: [2023-04-29 11:37:28,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +62: [2023-04-29 11:37:28,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +43: [2023-04-29 11:37:28,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +62: [2023-04-29 11:37:28,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +37: [2023-04-29 11:37:28,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +37: [2023-04-29 11:37:28,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +37: [2023-04-29 11:37:28,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +14: [2023-04-29 11:37:28,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +14: [2023-04-29 11:37:28,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +14: [2023-04-29 11:37:28,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +17: [2023-04-29 11:37:28,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +14: [2023-04-29 11:37:28,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +57: [2023-04-29 11:37:28,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +57: [2023-04-29 11:37:28,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +59: [2023-04-29 11:37:28,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +57: [2023-04-29 11:37:28,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +48: [2023-04-29 11:37:28,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +17: [2023-04-29 11:37:28,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +32: [2023-04-29 11:37:28,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +17: [2023-04-29 11:37:28,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +37: [2023-04-29 11:37:28,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +17: [2023-04-29 11:37:28,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 7: [2023-04-29 11:37:28,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 7: [2023-04-29 11:37:28,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +49: [2023-04-29 11:37:28,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. + 7: [2023-04-29 11:37:28,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 7: [2023-04-29 11:37:28,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +32: [2023-04-29 11:37:28,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +17: [2023-04-29 11:37:28,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +43: [2023-04-29 11:37:28,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +43: [2023-04-29 11:37:28,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +40: [2023-04-29 11:37:28,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +40: [2023-04-29 11:37:28,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +14: [2023-04-29 11:37:28,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +14: [2023-04-29 11:37:28,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +32: [2023-04-29 11:37:28,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +49: [2023-04-29 11:37:28,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +59: [2023-04-29 11:37:28,354] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +37: [2023-04-29 11:37:28,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +27: [2023-04-29 11:37:28,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +27: [2023-04-29 11:37:28,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +27: [2023-04-29 11:37:28,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +27: [2023-04-29 11:37:28,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +27: [2023-04-29 11:37:28,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +27: [2023-04-29 11:37:28,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +27: [2023-04-29 11:37:28,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +37: [2023-04-29 11:37:28,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +27: [2023-04-29 11:37:28,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +14: [2023-04-29 11:37:28,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +14: [2023-04-29 11:37:28,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +37: [2023-04-29 11:37:28,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +17: [2023-04-29 11:37:28,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +37: [2023-04-29 11:37:28,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +37: [2023-04-29 11:37:28,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 7: [2023-04-29 11:37:28,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +59: [2023-04-29 11:37:28,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 7: [2023-04-29 11:37:28,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +37: [2023-04-29 11:37:28,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +12: [2023-04-29 11:37:28,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +12: [2023-04-29 11:37:28,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +12: [2023-04-29 11:37:28,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 7: [2023-04-29 11:37:28,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +12: [2023-04-29 11:37:28,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +43: [2023-04-29 11:37:28,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +43: [2023-04-29 11:37:28,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +40: [2023-04-29 11:37:28,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +40: [2023-04-29 11:37:28,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +59: [2023-04-29 11:37:28,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +27: [2023-04-29 11:37:28,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +27: [2023-04-29 11:37:28,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +32: [2023-04-29 11:37:28,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +27: [2023-04-29 11:37:28,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +27: [2023-04-29 11:37:28,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +27: [2023-04-29 11:37:28,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +50: [2023-04-29 11:37:28,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +27: [2023-04-29 11:37:28,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +27: [2023-04-29 11:37:28,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +27: [2023-04-29 11:37:28,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 7: [2023-04-29 11:37:28,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +59: [2023-04-29 11:37:28,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +43: [2023-04-29 11:37:28,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... + 0: [2023-04-29 11:37:28,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 0: [2023-04-29 11:37:28,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 0: [2023-04-29 11:37:28,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +43: [2023-04-29 11:37:28,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... + 0: [2023-04-29 11:37:28,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +41: [2023-04-29 11:37:28,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +41: [2023-04-29 11:37:28,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +41: [2023-04-29 11:37:28,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +41: [2023-04-29 11:37:28,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +15: [2023-04-29 11:37:28,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +15: [2023-04-29 11:37:28,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +15: [2023-04-29 11:37:28,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +15: [2023-04-29 11:37:28,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +10: [2023-04-29 11:37:28,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +10: [2023-04-29 11:37:28,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +17: [2023-04-29 11:37:28,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +17: [2023-04-29 11:37:28,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +17: [2023-04-29 11:37:28,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +50: [2023-04-29 11:37:28,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +24: [2023-04-29 11:37:28,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +24: [2023-04-29 11:37:28,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +24: [2023-04-29 11:37:28,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +24: [2023-04-29 11:37:28,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +29: [2023-04-29 11:37:28,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +53: [2023-04-29 11:37:28,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +29: [2023-04-29 11:37:28,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +10: [2023-04-29 11:37:28,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +59: [2023-04-29 11:37:28,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +10: [2023-04-29 11:37:28,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +62: [2023-04-29 11:37:28,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +62: [2023-04-29 11:37:28,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +11: [2023-04-29 11:37:28,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +11: [2023-04-29 11:37:28,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +11: [2023-04-29 11:37:28,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +41: [2023-04-29 11:37:28,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +11: [2023-04-29 11:37:28,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +54: [2023-04-29 11:37:28,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +49: [2023-04-29 11:37:28,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +49: [2023-04-29 11:37:28,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +10: [2023-04-29 11:37:28,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +33: [2023-04-29 11:37:28,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +33: [2023-04-29 11:37:28,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +10: [2023-04-29 11:37:28,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +17: [2023-04-29 11:37:28,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +41: [2023-04-29 11:37:28,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +41: [2023-04-29 11:37:28,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +33: [2023-04-29 11:37:28,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +33: [2023-04-29 11:37:28,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +41: [2023-04-29 11:37:28,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +49: [2023-04-29 11:37:28,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +17: [2023-04-29 11:37:28,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +33: [2023-04-29 11:37:28,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +33: [2023-04-29 11:37:28,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +33: [2023-04-29 11:37:28,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +33: [2023-04-29 11:37:28,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +54: [2023-04-29 11:37:28,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +20: [2023-04-29 11:37:28,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +40: [2023-04-29 11:37:28,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +10: [2023-04-29 11:37:28,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +49: [2023-04-29 11:37:28,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +10: [2023-04-29 11:37:28,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +17: [2023-04-29 11:37:28,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +49: [2023-04-29 11:37:28,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +59: [2023-04-29 11:37:28,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +62: [2023-04-29 11:37:28,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +35: [2023-04-29 11:37:28,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +35: [2023-04-29 11:37:28,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +33: [2023-04-29 11:37:28,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +40: [2023-04-29 11:37:28,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 4: [2023-04-29 11:37:28,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +54: [2023-04-29 11:37:28,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +54: [2023-04-29 11:37:28,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +33: [2023-04-29 11:37:28,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +33: [2023-04-29 11:37:28,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +11: [2023-04-29 11:37:28,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +49: [2023-04-29 11:37:28,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +33: [2023-04-29 11:37:28,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +35: [2023-04-29 11:37:28,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +35: [2023-04-29 11:37:28,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +35: [2023-04-29 11:37:28,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +35: [2023-04-29 11:37:28,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +35: [2023-04-29 11:37:28,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +35: [2023-04-29 11:37:28,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +33: [2023-04-29 11:37:28,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +48: [2023-04-29 11:37:28,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +20: [2023-04-29 11:37:28,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +33: [2023-04-29 11:37:28,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +12: [2023-04-29 11:37:28,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +20: [2023-04-29 11:37:28,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +33: [2023-04-29 11:37:28,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +33: [2023-04-29 11:37:28,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +40: [2023-04-29 11:37:28,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +11: [2023-04-29 11:37:28,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +20: [2023-04-29 11:37:28,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +62: [2023-04-29 11:37:28,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +62: [2023-04-29 11:37:28,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +25: [2023-04-29 11:37:28,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +25: [2023-04-29 11:37:28,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +25: [2023-04-29 11:37:28,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +25: [2023-04-29 11:37:28,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +39: [2023-04-29 11:37:28,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +53: [2023-04-29 11:37:28,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +53: [2023-04-29 11:37:28,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +53: [2023-04-29 11:37:28,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +29: [2023-04-29 11:37:28,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +29: [2023-04-29 11:37:28,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +12: [2023-04-29 11:37:28,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +40: [2023-04-29 11:37:28,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +12: [2023-04-29 11:37:28,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +39: [2023-04-29 11:37:28,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +39: [2023-04-29 11:37:28,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +12: [2023-04-29 11:37:28,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +35: [2023-04-29 11:37:28,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +46: [2023-04-29 11:37:28,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +46: [2023-04-29 11:37:28,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +31: [2023-04-29 11:37:28,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +35: [2023-04-29 11:37:28,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +45: [2023-04-29 11:37:28,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +35: [2023-04-29 11:37:28,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +39: [2023-04-29 11:37:28,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +35: [2023-04-29 11:37:28,389] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +45: [2023-04-29 11:37:28,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +45: [2023-04-29 11:37:28,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +62: [2023-04-29 11:37:28,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +62: [2023-04-29 11:37:28,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +39: [2023-04-29 11:37:28,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +35: [2023-04-29 11:37:28,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +53: [2023-04-29 11:37:28,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +63: [2023-04-29 11:37:28,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +45: [2023-04-29 11:37:28,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +62: [2023-04-29 11:37:28,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +35: [2023-04-29 11:37:28,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +11: [2023-04-29 11:37:28,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +48: [2023-04-29 11:37:28,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +48: [2023-04-29 11:37:28,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +35: [2023-04-29 11:37:28,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +31: [2023-04-29 11:37:28,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +15: [2023-04-29 11:37:28,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +15: [2023-04-29 11:37:28,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 0: [2023-04-29 11:37:28,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +46: [2023-04-29 11:37:28,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +46: [2023-04-29 11:37:28,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +35: [2023-04-29 11:37:28,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +39: [2023-04-29 11:37:28,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +39: [2023-04-29 11:37:28,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... + 0: [2023-04-29 11:37:28,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +63: [2023-04-29 11:37:28,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +45: [2023-04-29 11:37:28,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +14: [2023-04-29 11:37:28,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 0: [2023-04-29 11:37:28,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +45: [2023-04-29 11:37:28,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 0: [2023-04-29 11:37:28,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +29: [2023-04-29 11:37:28,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 4: [2023-04-29 11:37:28,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +15: [2023-04-29 11:37:28,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +15: [2023-04-29 11:37:28,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +29: [2023-04-29 11:37:28,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +24: [2023-04-29 11:37:28,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +63: [2023-04-29 11:37:28,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +45: [2023-04-29 11:37:28,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +45: [2023-04-29 11:37:28,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +53: [2023-04-29 11:37:28,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +63: [2023-04-29 11:37:28,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +39: [2023-04-29 11:37:28,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +24: [2023-04-29 11:37:28,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +24: [2023-04-29 11:37:28,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +24: [2023-04-29 11:37:28,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 3: [2023-04-29 11:37:28,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 3: [2023-04-29 11:37:28,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 3: [2023-04-29 11:37:28,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 3: [2023-04-29 11:37:28,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +14: [2023-04-29 11:37:28,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +20: [2023-04-29 11:37:28,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +63: [2023-04-29 11:37:28,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +63: [2023-04-29 11:37:28,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +42: [2023-04-29 11:37:28,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +42: [2023-04-29 11:37:28,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +42: [2023-04-29 11:37:28,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +53: [2023-04-29 11:37:28,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +63: [2023-04-29 11:37:28,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +54: [2023-04-29 11:37:28,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +10: [2023-04-29 11:37:28,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +53: [2023-04-29 11:37:28,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. + 3: [2023-04-29 11:37:28,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 3: [2023-04-29 11:37:28,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 3: [2023-04-29 11:37:28,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +11: [2023-04-29 11:37:28,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +11: [2023-04-29 11:37:28,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +31: [2023-04-29 11:37:28,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +37: [2023-04-29 11:37:28,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. + 4: [2023-04-29 11:37:28,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +54: [2023-04-29 11:37:28,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +42: [2023-04-29 11:37:28,405] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 3: [2023-04-29 11:37:28,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +53: [2023-04-29 11:37:28,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +11: [2023-04-29 11:37:28,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +10: [2023-04-29 11:37:28,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +63: [2023-04-29 11:37:28,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +13: [2023-04-29 11:37:28,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +13: [2023-04-29 11:37:28,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +13: [2023-04-29 11:37:28,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +10: [2023-04-29 11:37:28,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +49: [2023-04-29 11:37:28,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +13: [2023-04-29 11:37:28,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +48: [2023-04-29 11:37:28,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +62: [2023-04-29 11:37:28,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +53: [2023-04-29 11:37:28,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +11: [2023-04-29 11:37:28,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +54: [2023-04-29 11:37:28,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +53: [2023-04-29 11:37:28,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +11: [2023-04-29 11:37:28,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +11: [2023-04-29 11:37:28,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +10: [2023-04-29 11:37:28,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +20: [2023-04-29 11:37:28,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +37: [2023-04-29 11:37:28,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +25: [2023-04-29 11:37:28,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +25: [2023-04-29 11:37:28,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +54: [2023-04-29 11:37:28,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +14: [2023-04-29 11:37:28,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +14: [2023-04-29 11:37:28,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +14: [2023-04-29 11:37:28,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +47: [2023-04-29 11:37:28,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +11: [2023-04-29 11:37:28,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +14: [2023-04-29 11:37:28,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +47: [2023-04-29 11:37:28,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +47: [2023-04-29 11:37:28,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +20: [2023-04-29 11:37:28,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +47: [2023-04-29 11:37:28,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +17: [2023-04-29 11:37:28,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +25: [2023-04-29 11:37:28,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +25: [2023-04-29 11:37:28,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +46: [2023-04-29 11:37:28,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +31: [2023-04-29 11:37:28,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +31: [2023-04-29 11:37:28,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +28: [2023-04-29 11:37:28,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +28: [2023-04-29 11:37:28,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +51: [2023-04-29 11:37:28,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +51: [2023-04-29 11:37:28,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +51: [2023-04-29 11:37:28,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +48: [2023-04-29 11:37:28,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +51: [2023-04-29 11:37:28,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +51: [2023-04-29 11:37:28,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +51: [2023-04-29 11:37:28,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +20: [2023-04-29 11:37:28,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +51: [2023-04-29 11:37:28,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +51: [2023-04-29 11:37:28,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +37: [2023-04-29 11:37:28,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +28: [2023-04-29 11:37:28,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +28: [2023-04-29 11:37:28,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +17: [2023-04-29 11:37:28,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +53: [2023-04-29 11:37:28,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +29: [2023-04-29 11:37:28,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +29: [2023-04-29 11:37:28,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +48: [2023-04-29 11:37:28,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +31: [2023-04-29 11:37:28,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +53: [2023-04-29 11:37:28,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +46: [2023-04-29 11:37:28,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +47: [2023-04-29 11:37:28,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +44: [2023-04-29 11:37:28,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +44: [2023-04-29 11:37:28,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +10: [2023-04-29 11:37:28,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +47: [2023-04-29 11:37:28,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +47: [2023-04-29 11:37:28,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +47: [2023-04-29 11:37:28,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +49: [2023-04-29 11:37:28,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +49: [2023-04-29 11:37:28,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +49: [2023-04-29 11:37:28,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +14: [2023-04-29 11:37:28,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +14: [2023-04-29 11:37:28,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +22: [2023-04-29 11:37:28,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +53: [2023-04-29 11:37:28,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +14: [2023-04-29 11:37:28,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +22: [2023-04-29 11:37:28,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +22: [2023-04-29 11:37:28,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +22: [2023-04-29 11:37:28,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +44: [2023-04-29 11:37:28,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +44: [2023-04-29 11:37:28,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +44: [2023-04-29 11:37:28,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +28: [2023-04-29 11:37:28,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +44: [2023-04-29 11:37:28,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +44: [2023-04-29 11:37:28,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +28: [2023-04-29 11:37:28,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +10: [2023-04-29 11:37:28,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +44: [2023-04-29 11:37:28,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. + 7: [2023-04-29 11:37:28,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +51: [2023-04-29 11:37:28,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +51: [2023-04-29 11:37:28,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +46: [2023-04-29 11:37:28,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +19: [2023-04-29 11:37:28,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +19: [2023-04-29 11:37:28,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +48: [2023-04-29 11:37:28,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +48: [2023-04-29 11:37:28,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +19: [2023-04-29 11:37:28,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +48: [2023-04-29 11:37:28,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +28: [2023-04-29 11:37:28,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +19: [2023-04-29 11:37:28,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +44: [2023-04-29 11:37:28,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +11: [2023-04-29 11:37:28,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +52: [2023-04-29 11:37:28,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +52: [2023-04-29 11:37:28,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +27: [2023-04-29 11:37:28,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +46: [2023-04-29 11:37:28,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +28: [2023-04-29 11:37:28,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +22: [2023-04-29 11:37:28,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +44: [2023-04-29 11:37:28,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +22: [2023-04-29 11:37:28,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +22: [2023-04-29 11:37:28,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +44: [2023-04-29 11:37:28,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +10: [2023-04-29 11:37:28,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +44: [2023-04-29 11:37:28,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +22: [2023-04-29 11:37:28,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +48: [2023-04-29 11:37:28,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +44: [2023-04-29 11:37:28,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +44: [2023-04-29 11:37:28,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +51: [2023-04-29 11:37:28,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +44: [2023-04-29 11:37:28,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +44: [2023-04-29 11:37:28,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +17: [2023-04-29 11:37:28,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +53: [2023-04-29 11:37:28,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_00-model_states.pt. +17: [2023-04-29 11:37:28,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +52: [2023-04-29 11:37:28,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +52: [2023-04-29 11:37:28,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +51: [2023-04-29 11:37:28,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +10: [2023-04-29 11:37:28,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +51: [2023-04-29 11:37:28,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +37: [2023-04-29 11:37:28,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +51: [2023-04-29 11:37:28,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +42: [2023-04-29 11:37:28,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +51: [2023-04-29 11:37:28,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +51: [2023-04-29 11:37:28,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 7: [2023-04-29 11:37:28,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 7: [2023-04-29 11:37:28,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +48: [2023-04-29 11:37:28,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +14: [2023-04-29 11:37:28,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +27: [2023-04-29 11:37:28,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +14: [2023-04-29 11:37:28,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +14: [2023-04-29 11:37:28,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +41: [2023-04-29 11:37:28,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +41: [2023-04-29 11:37:28,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +48: [2023-04-29 11:37:28,432] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +13: [2023-04-29 11:37:28,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +31: [2023-04-29 11:37:28,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +41: [2023-04-29 11:37:28,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +41: [2023-04-29 11:37:28,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +42: [2023-04-29 11:37:28,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +42: [2023-04-29 11:37:28,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +49: [2023-04-29 11:37:28,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 7: [2023-04-29 11:37:28,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +53: [2023-04-29 11:37:28,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt... +42: [2023-04-29 11:37:28,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +27: [2023-04-29 11:37:28,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +27: [2023-04-29 11:37:28,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +13: [2023-04-29 11:37:28,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +13: [2023-04-29 11:37:28,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +13: [2023-04-29 11:37:28,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +48: [2023-04-29 11:37:28,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +39: [2023-04-29 11:37:28,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +39: [2023-04-29 11:37:28,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +39: [2023-04-29 11:37:28,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +11: [2023-04-29 11:37:28,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +39: [2023-04-29 11:37:28,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +26: [2023-04-29 11:37:28,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +26: [2023-04-29 11:37:28,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +48: [2023-04-29 11:37:28,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +31: [2023-04-29 11:37:28,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +26: [2023-04-29 11:37:28,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +26: [2023-04-29 11:37:28,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +39: [2023-04-29 11:37:28,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +17: [2023-04-29 11:37:28,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +41: [2023-04-29 11:37:28,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +39: [2023-04-29 11:37:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +26: [2023-04-29 11:37:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +39: [2023-04-29 11:37:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +26: [2023-04-29 11:37:28,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +48: [2023-04-29 11:37:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +39: [2023-04-29 11:37:28,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +14: [2023-04-29 11:37:28,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +38: [2023-04-29 11:37:28,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +38: [2023-04-29 11:37:28,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +38: [2023-04-29 11:37:28,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +38: [2023-04-29 11:37:28,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +48: [2023-04-29 11:37:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +26: [2023-04-29 11:37:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +17: [2023-04-29 11:37:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +26: [2023-04-29 11:37:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +37: [2023-04-29 11:37:28,447] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +33: [2023-04-29 11:37:28,448] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +33: [2023-04-29 11:37:28,448] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +33: [2023-04-29 11:37:28,448] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +27: [2023-04-29 11:37:28,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +38: [2023-04-29 11:37:28,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +38: [2023-04-29 11:37:28,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 0: [2023-04-29 11:37:28,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +49: [2023-04-29 11:37:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +49: [2023-04-29 11:37:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +10: [2023-04-29 11:37:28,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +37: [2023-04-29 11:37:28,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +10: [2023-04-29 11:37:28,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +10: [2023-04-29 11:37:28,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +37: [2023-04-29 11:37:28,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +49: [2023-04-29 11:37:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +58: [2023-04-29 11:37:28,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +58: [2023-04-29 11:37:28,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +58: [2023-04-29 11:37:28,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +58: [2023-04-29 11:37:28,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +58: [2023-04-29 11:37:28,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +58: [2023-04-29 11:37:28,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +58: [2023-04-29 11:37:28,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +58: [2023-04-29 11:37:28,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +35: [2023-04-29 11:37:28,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 7: [2023-04-29 11:37:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +10: [2023-04-29 11:37:28,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +37: [2023-04-29 11:37:28,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +37: [2023-04-29 11:37:28,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +24: [2023-04-29 11:37:28,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +24: [2023-04-29 11:37:28,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +37: [2023-04-29 11:37:28,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +38: [2023-04-29 11:37:28,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +38: [2023-04-29 11:37:28,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +33: [2023-04-29 11:37:28,453] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. + 0: [2023-04-29 11:37:28,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +18: [2023-04-29 11:37:28,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +24: [2023-04-29 11:37:28,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +18: [2023-04-29 11:37:28,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +18: [2023-04-29 11:37:28,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +38: [2023-04-29 11:37:28,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +18: [2023-04-29 11:37:28,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +18: [2023-04-29 11:37:28,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +18: [2023-04-29 11:37:28,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +18: [2023-04-29 11:37:28,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +24: [2023-04-29 11:37:28,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +38: [2023-04-29 11:37:28,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +18: [2023-04-29 11:37:28,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +38: [2023-04-29 11:37:28,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +37: [2023-04-29 11:37:28,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +52: [2023-04-29 11:37:28,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +19: [2023-04-29 11:37:28,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +19: [2023-04-29 11:37:28,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +19: [2023-04-29 11:37:28,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +41: [2023-04-29 11:37:28,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +38: [2023-04-29 11:37:28,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 3: [2023-04-29 11:37:28,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +52: [2023-04-29 11:37:28,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +60: [2023-04-29 11:37:28,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +60: [2023-04-29 11:37:28,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +17: [2023-04-29 11:37:28,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +17: [2023-04-29 11:37:28,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +58: [2023-04-29 11:37:28,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +19: [2023-04-29 11:37:28,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +24: [2023-04-29 11:37:28,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +52: [2023-04-29 11:37:28,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +24: [2023-04-29 11:37:28,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +58: [2023-04-29 11:37:28,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +58: [2023-04-29 11:37:28,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +58: [2023-04-29 11:37:28,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +58: [2023-04-29 11:37:28,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +58: [2023-04-29 11:37:28,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +58: [2023-04-29 11:37:28,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +58: [2023-04-29 11:37:28,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +18: [2023-04-29 11:37:28,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +24: [2023-04-29 11:37:28,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +41: [2023-04-29 11:37:28,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +18: [2023-04-29 11:37:28,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +18: [2023-04-29 11:37:28,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +14: [2023-04-29 11:37:28,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +45: [2023-04-29 11:37:28,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +14: [2023-04-29 11:37:28,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +24: [2023-04-29 11:37:28,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +41: [2023-04-29 11:37:28,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +41: [2023-04-29 11:37:28,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +27: [2023-04-29 11:37:28,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +37: [2023-04-29 11:37:28,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +60: [2023-04-29 11:37:28,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +60: [2023-04-29 11:37:28,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 7: [2023-04-29 11:37:28,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +37: [2023-04-29 11:37:28,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +60: [2023-04-29 11:37:28,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 7: [2023-04-29 11:37:28,462] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +60: [2023-04-29 11:37:28,462] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +52: [2023-04-29 11:37:28,462] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +41: [2023-04-29 11:37:28,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +18: [2023-04-29 11:37:28,463] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +14: [2023-04-29 11:37:28,463] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +35: [2023-04-29 11:37:28,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +18: [2023-04-29 11:37:28,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +18: [2023-04-29 11:37:28,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +27: [2023-04-29 11:37:28,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +27: [2023-04-29 11:37:28,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +18: [2023-04-29 11:37:28,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +45: [2023-04-29 11:37:28,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +18: [2023-04-29 11:37:28,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 0: [2023-04-29 11:37:28,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 0: [2023-04-29 11:37:28,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 0: [2023-04-29 11:37:28,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +60: [2023-04-29 11:37:28,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 7: [2023-04-29 11:37:28,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +60: [2023-04-29 11:37:28,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +35: [2023-04-29 11:37:28,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 3: [2023-04-29 11:37:28,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +62: [2023-04-29 11:37:28,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 3: [2023-04-29 11:37:28,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +24: [2023-04-29 11:37:28,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +45: [2023-04-29 11:37:28,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +41: [2023-04-29 11:37:28,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +45: [2023-04-29 11:37:28,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +62: [2023-04-29 11:37:28,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +41: [2023-04-29 11:37:28,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 3: [2023-04-29 11:37:28,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +24: [2023-04-29 11:37:28,473] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 0: [2023-04-29 11:37:28,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +35: [2023-04-29 11:37:28,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 0: [2023-04-29 11:37:28,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +59: [2023-04-29 11:37:28,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +59: [2023-04-29 11:37:28,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +59: [2023-04-29 11:37:28,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +59: [2023-04-29 11:37:28,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 0: [2023-04-29 11:37:28,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +23: [2023-04-29 11:37:28,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +44: [2023-04-29 11:37:28,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +62: [2023-04-29 11:37:28,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +23: [2023-04-29 11:37:28,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +36: [2023-04-29 11:37:28,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +36: [2023-04-29 11:37:28,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +36: [2023-04-29 11:37:28,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +36: [2023-04-29 11:37:28,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +41: [2023-04-29 11:37:28,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +23: [2023-04-29 11:37:28,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +23: [2023-04-29 11:37:28,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +23: [2023-04-29 11:37:28,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +23: [2023-04-29 11:37:28,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +33: [2023-04-29 11:37:28,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +24: [2023-04-29 11:37:28,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... + 2: [2023-04-29 11:37:28,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 2: [2023-04-29 11:37:28,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 2: [2023-04-29 11:37:28,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +24: [2023-04-29 11:37:28,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +11: [2023-04-29 11:37:28,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +28: [2023-04-29 11:37:28,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +28: [2023-04-29 11:37:28,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +11: [2023-04-29 11:37:28,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +38: [2023-04-29 11:37:28,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +38: [2023-04-29 11:37:28,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 6: [2023-04-29 11:37:28,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 6: [2023-04-29 11:37:28,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 2: [2023-04-29 11:37:28,479] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +10: [2023-04-29 11:37:28,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +24: [2023-04-29 11:37:28,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +10: [2023-04-29 11:37:28,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +10: [2023-04-29 11:37:28,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +31: [2023-04-29 11:37:28,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +31: [2023-04-29 11:37:28,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +55: [2023-04-29 11:37:28,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +55: [2023-04-29 11:37:28,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +10: [2023-04-29 11:37:28,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +55: [2023-04-29 11:37:28,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +59: [2023-04-29 11:37:28,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +55: [2023-04-29 11:37:28,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +35: [2023-04-29 11:37:28,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +31: [2023-04-29 11:37:28,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +59: [2023-04-29 11:37:28,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +33: [2023-04-29 11:37:28,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +33: [2023-04-29 11:37:28,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +23: [2023-04-29 11:37:28,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +23: [2023-04-29 11:37:28,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +59: [2023-04-29 11:37:28,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +59: [2023-04-29 11:37:28,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +33: [2023-04-29 11:37:28,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +31: [2023-04-29 11:37:28,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 3: [2023-04-29 11:37:28,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +23: [2023-04-29 11:37:28,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 6: [2023-04-29 11:37:28,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 6: [2023-04-29 11:37:28,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +47: [2023-04-29 11:37:28,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +28: [2023-04-29 11:37:28,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +23: [2023-04-29 11:37:28,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +62: [2023-04-29 11:37:28,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +28: [2023-04-29 11:37:28,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +23: [2023-04-29 11:37:28,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +23: [2023-04-29 11:37:28,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +11: [2023-04-29 11:37:28,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +11: [2023-04-29 11:37:28,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +45: [2023-04-29 11:37:28,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +24: [2023-04-29 11:37:28,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +24: [2023-04-29 11:37:28,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +62: [2023-04-29 11:37:28,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +11: [2023-04-29 11:37:28,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +11: [2023-04-29 11:37:28,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +62: [2023-04-29 11:37:28,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +28: [2023-04-29 11:37:28,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +28: [2023-04-29 11:37:28,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +37: [2023-04-29 11:37:28,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +37: [2023-04-29 11:37:28,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +12: [2023-04-29 11:37:28,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +12: [2023-04-29 11:37:28,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +12: [2023-04-29 11:37:28,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +12: [2023-04-29 11:37:28,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +12: [2023-04-29 11:37:28,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +12: [2023-04-29 11:37:28,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +12: [2023-04-29 11:37:28,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +12: [2023-04-29 11:37:28,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +63: [2023-04-29 11:37:28,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +22: [2023-04-29 11:37:28,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +22: [2023-04-29 11:37:28,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +63: [2023-04-29 11:37:28,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +63: [2023-04-29 11:37:28,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +22: [2023-04-29 11:37:28,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +63: [2023-04-29 11:37:28,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +26: [2023-04-29 11:37:28,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +26: [2023-04-29 11:37:28,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +21: [2023-04-29 11:37:28,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +21: [2023-04-29 11:37:28,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +21: [2023-04-29 11:37:28,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +37: [2023-04-29 11:37:28,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +62: [2023-04-29 11:37:28,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +26: [2023-04-29 11:37:28,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +26: [2023-04-29 11:37:28,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +22: [2023-04-29 11:37:28,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +38: [2023-04-29 11:37:28,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +47: [2023-04-29 11:37:28,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +62: [2023-04-29 11:37:28,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +22: [2023-04-29 11:37:28,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +24: [2023-04-29 11:37:28,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +11: [2023-04-29 11:37:28,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +35: [2023-04-29 11:37:28,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 7: [2023-04-29 11:37:28,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 7: [2023-04-29 11:37:28,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +11: [2023-04-29 11:37:28,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +45: [2023-04-29 11:37:28,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +21: [2023-04-29 11:37:28,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +12: [2023-04-29 11:37:28,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... + 1: [2023-04-29 11:37:28,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 1: [2023-04-29 11:37:28,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 1: [2023-04-29 11:37:28,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +47: [2023-04-29 11:37:28,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +63: [2023-04-29 11:37:28,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +28: [2023-04-29 11:37:28,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +41: [2023-04-29 11:37:28,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 7: [2023-04-29 11:37:28,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +38: [2023-04-29 11:37:28,493] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 7: [2023-04-29 11:37:28,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 1: [2023-04-29 11:37:28,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +28: [2023-04-29 11:37:28,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +12: [2023-04-29 11:37:28,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +63: [2023-04-29 11:37:28,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +44: [2023-04-29 11:37:28,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +44: [2023-04-29 11:37:28,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +44: [2023-04-29 11:37:28,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +63: [2023-04-29 11:37:28,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +63: [2023-04-29 11:37:28,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +12: [2023-04-29 11:37:28,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +12: [2023-04-29 11:37:28,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +12: [2023-04-29 11:37:28,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +47: [2023-04-29 11:37:28,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +12: [2023-04-29 11:37:28,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +45: [2023-04-29 11:37:28,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +22: [2023-04-29 11:37:28,497] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +22: [2023-04-29 11:37:28,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +22: [2023-04-29 11:37:28,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +12: [2023-04-29 11:37:28,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +12: [2023-04-29 11:37:28,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +41: [2023-04-29 11:37:28,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +41: [2023-04-29 11:37:28,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +51: [2023-04-29 11:37:28,499] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 3: [2023-04-29 11:37:28,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 3: [2023-04-29 11:37:28,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +45: [2023-04-29 11:37:28,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +35: [2023-04-29 11:37:28,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +36: [2023-04-29 11:37:28,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +23: [2023-04-29 11:37:28,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +23: [2023-04-29 11:37:28,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +39: [2023-04-29 11:37:28,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +36: [2023-04-29 11:37:28,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +35: [2023-04-29 11:37:28,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 3: [2023-04-29 11:37:28,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +44: [2023-04-29 11:37:28,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +29: [2023-04-29 11:37:28,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +29: [2023-04-29 11:37:28,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +29: [2023-04-29 11:37:28,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +29: [2023-04-29 11:37:28,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +55: [2023-04-29 11:37:28,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +36: [2023-04-29 11:37:28,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +28: [2023-04-29 11:37:28,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 6: [2023-04-29 11:37:28,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 6: [2023-04-29 11:37:28,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +56: [2023-04-29 11:37:28,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +56: [2023-04-29 11:37:28,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +56: [2023-04-29 11:37:28,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +56: [2023-04-29 11:37:28,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +36: [2023-04-29 11:37:28,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 6: [2023-04-29 11:37:28,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +47: [2023-04-29 11:37:28,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +31: [2023-04-29 11:37:28,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +55: [2023-04-29 11:37:28,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +55: [2023-04-29 11:37:28,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 2: [2023-04-29 11:37:28,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +31: [2023-04-29 11:37:28,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 2: [2023-04-29 11:37:28,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +56: [2023-04-29 11:37:28,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +56: [2023-04-29 11:37:28,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +51: [2023-04-29 11:37:28,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +51: [2023-04-29 11:37:28,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +51: [2023-04-29 11:37:28,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +31: [2023-04-29 11:37:28,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +31: [2023-04-29 11:37:28,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +23: [2023-04-29 11:37:28,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 2: [2023-04-29 11:37:28,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 2: [2023-04-29 11:37:28,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +21: [2023-04-29 11:37:28,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +28: [2023-04-29 11:37:28,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +28: [2023-04-29 11:37:28,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +55: [2023-04-29 11:37:28,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 6: [2023-04-29 11:37:28,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +56: [2023-04-29 11:37:28,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +52: [2023-04-29 11:37:28,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +56: [2023-04-29 11:37:28,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +60: [2023-04-29 11:37:28,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +60: [2023-04-29 11:37:28,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +28: [2023-04-29 11:37:28,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +39: [2023-04-29 11:37:28,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +39: [2023-04-29 11:37:28,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +56: [2023-04-29 11:37:28,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +56: [2023-04-29 11:37:28,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +28: [2023-04-29 11:37:28,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +21: [2023-04-29 11:37:28,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +39: [2023-04-29 11:37:28,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +23: [2023-04-29 11:37:28,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +60: [2023-04-29 11:37:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. + 1: [2023-04-29 11:37:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +61: [2023-04-29 11:37:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +61: [2023-04-29 11:37:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +60: [2023-04-29 11:37:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +36: [2023-04-29 11:37:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +36: [2023-04-29 11:37:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +47: [2023-04-29 11:37:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +52: [2023-04-29 11:37:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +22: [2023-04-29 11:37:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +28: [2023-04-29 11:37:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +47: [2023-04-29 11:37:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +26: [2023-04-29 11:37:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 1: [2023-04-29 11:37:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 7: [2023-04-29 11:37:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +47: [2023-04-29 11:37:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +26: [2023-04-29 11:37:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 1: [2023-04-29 11:37:28,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +18: [2023-04-29 11:37:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +56: [2023-04-29 11:37:28,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +61: [2023-04-29 11:37:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +47: [2023-04-29 11:37:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +56: [2023-04-29 11:37:28,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +47: [2023-04-29 11:37:28,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +61: [2023-04-29 11:37:28,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +36: [2023-04-29 11:37:28,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +36: [2023-04-29 11:37:28,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +21: [2023-04-29 11:37:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +47: [2023-04-29 11:37:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +22: [2023-04-29 11:37:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +24: [2023-04-29 11:37:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +24: [2023-04-29 11:37:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +25: [2023-04-29 11:37:28,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +52: [2023-04-29 11:37:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +25: [2023-04-29 11:37:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +25: [2023-04-29 11:37:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +25: [2023-04-29 11:37:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +25: [2023-04-29 11:37:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +25: [2023-04-29 11:37:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +25: [2023-04-29 11:37:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +26: [2023-04-29 11:37:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +25: [2023-04-29 11:37:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +22: [2023-04-29 11:37:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +22: [2023-04-29 11:37:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +22: [2023-04-29 11:37:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +26: [2023-04-29 11:37:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +26: [2023-04-29 11:37:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +57: [2023-04-29 11:37:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +21: [2023-04-29 11:37:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 7: [2023-04-29 11:37:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +57: [2023-04-29 11:37:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +44: [2023-04-29 11:37:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +26: [2023-04-29 11:37:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +44: [2023-04-29 11:37:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +58: [2023-04-29 11:37:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +58: [2023-04-29 11:37:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +57: [2023-04-29 11:37:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +38: [2023-04-29 11:37:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +60: [2023-04-29 11:37:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +52: [2023-04-29 11:37:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +52: [2023-04-29 11:37:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +57: [2023-04-29 11:37:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +36: [2023-04-29 11:37:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +52: [2023-04-29 11:37:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. + 1: [2023-04-29 11:37:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +52: [2023-04-29 11:37:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +36: [2023-04-29 11:37:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +44: [2023-04-29 11:37:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +24: [2023-04-29 11:37:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +28: [2023-04-29 11:37:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +25: [2023-04-29 11:37:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +25: [2023-04-29 11:37:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +47: [2023-04-29 11:37:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +28: [2023-04-29 11:37:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +25: [2023-04-29 11:37:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +25: [2023-04-29 11:37:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... + 7: [2023-04-29 11:37:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +25: [2023-04-29 11:37:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +58: [2023-04-29 11:37:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +58: [2023-04-29 11:37:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +52: [2023-04-29 11:37:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... + 7: [2023-04-29 11:37:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +57: [2023-04-29 11:37:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +52: [2023-04-29 11:37:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +57: [2023-04-29 11:37:28,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +51: [2023-04-29 11:37:28,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +57: [2023-04-29 11:37:28,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +26: [2023-04-29 11:37:28,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +39: [2023-04-29 11:37:28,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +26: [2023-04-29 11:37:28,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +52: [2023-04-29 11:37:28,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +45: [2023-04-29 11:37:28,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +45: [2023-04-29 11:37:28,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +52: [2023-04-29 11:37:28,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +25: [2023-04-29 11:37:28,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +24: [2023-04-29 11:37:28,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +25: [2023-04-29 11:37:28,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +45: [2023-04-29 11:37:28,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +57: [2023-04-29 11:37:28,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +45: [2023-04-29 11:37:28,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +25: [2023-04-29 11:37:28,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +36: [2023-04-29 11:37:28,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +36: [2023-04-29 11:37:28,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +22: [2023-04-29 11:37:28,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +29: [2023-04-29 11:37:28,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +52: [2023-04-29 11:37:28,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +22: [2023-04-29 11:37:28,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +22: [2023-04-29 11:37:28,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +29: [2023-04-29 11:37:28,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +18: [2023-04-29 11:37:28,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +18: [2023-04-29 11:37:28,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 5: [2023-04-29 11:37:28,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 5: [2023-04-29 11:37:28,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +29: [2023-04-29 11:37:28,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +56: [2023-04-29 11:37:28,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +56: [2023-04-29 11:37:28,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +60: [2023-04-29 11:37:28,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +18: [2023-04-29 11:37:28,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +41: [2023-04-29 11:37:28,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +41: [2023-04-29 11:37:28,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +29: [2023-04-29 11:37:28,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +38: [2023-04-29 11:37:28,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 1: [2023-04-29 11:37:28,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 1: [2023-04-29 11:37:28,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 1: [2023-04-29 11:37:28,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 1: [2023-04-29 11:37:28,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 5: [2023-04-29 11:37:28,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 5: [2023-04-29 11:37:28,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +38: [2023-04-29 11:37:28,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +38: [2023-04-29 11:37:28,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +52: [2023-04-29 11:37:28,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +56: [2023-04-29 11:37:28,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +56: [2023-04-29 11:37:28,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +18: [2023-04-29 11:37:28,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +60: [2023-04-29 11:37:28,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 9: [2023-04-29 11:37:28,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 9: [2023-04-29 11:37:28,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 9: [2023-04-29 11:37:28,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 9: [2023-04-29 11:37:28,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +60: [2023-04-29 11:37:28,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 1: [2023-04-29 11:37:28,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 1: [2023-04-29 11:37:28,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +41: [2023-04-29 11:37:28,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +41: [2023-04-29 11:37:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +60: [2023-04-29 11:37:28,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +38: [2023-04-29 11:37:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 1: [2023-04-29 11:37:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +60: [2023-04-29 11:37:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +47: [2023-04-29 11:37:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 1: [2023-04-29 11:37:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +52: [2023-04-29 11:37:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +51: [2023-04-29 11:37:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +39: [2023-04-29 11:37:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +34: [2023-04-29 11:37:28,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +34: [2023-04-29 11:37:28,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +47: [2023-04-29 11:37:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +39: [2023-04-29 11:37:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +52: [2023-04-29 11:37:28,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +34: [2023-04-29 11:37:28,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +24: [2023-04-29 11:37:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +34: [2023-04-29 11:37:28,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +59: [2023-04-29 11:37:28,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +59: [2023-04-29 11:37:28,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +60: [2023-04-29 11:37:28,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +39: [2023-04-29 11:37:28,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +23: [2023-04-29 11:37:28,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +24: [2023-04-29 11:37:28,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +55: [2023-04-29 11:37:28,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +55: [2023-04-29 11:37:28,551] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +26: [2023-04-29 11:37:28,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +24: [2023-04-29 11:37:28,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +55: [2023-04-29 11:37:28,551] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +55: [2023-04-29 11:37:28,551] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +61: [2023-04-29 11:37:28,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +51: [2023-04-29 11:37:28,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +51: [2023-04-29 11:37:28,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +47: [2023-04-29 11:37:28,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +59: [2023-04-29 11:37:28,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +59: [2023-04-29 11:37:28,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +47: [2023-04-29 11:37:28,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 3: [2023-04-29 11:37:28,551] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 3: [2023-04-29 11:37:28,551] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 3: [2023-04-29 11:37:28,551] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 3: [2023-04-29 11:37:28,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +60: [2023-04-29 11:37:28,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +41: [2023-04-29 11:37:28,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +13: [2023-04-29 11:37:28,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +13: [2023-04-29 11:37:28,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +13: [2023-04-29 11:37:28,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +26: [2023-04-29 11:37:28,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +13: [2023-04-29 11:37:28,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +13: [2023-04-29 11:37:28,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +13: [2023-04-29 11:37:28,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +13: [2023-04-29 11:37:28,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +58: [2023-04-29 11:37:28,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +58: [2023-04-29 11:37:28,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +13: [2023-04-29 11:37:28,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +52: [2023-04-29 11:37:28,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +61: [2023-04-29 11:37:28,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +41: [2023-04-29 11:37:28,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +63: [2023-04-29 11:37:28,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +55: [2023-04-29 11:37:28,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +60: [2023-04-29 11:37:28,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +43: [2023-04-29 11:37:28,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +43: [2023-04-29 11:37:28,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +55: [2023-04-29 11:37:28,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +55: [2023-04-29 11:37:28,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +43: [2023-04-29 11:37:28,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +24: [2023-04-29 11:37:28,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +55: [2023-04-29 11:37:28,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +45: [2023-04-29 11:37:28,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +38: [2023-04-29 11:37:28,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +38: [2023-04-29 11:37:28,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +45: [2023-04-29 11:37:28,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +43: [2023-04-29 11:37:28,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +61: [2023-04-29 11:37:28,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +13: [2023-04-29 11:37:28,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +13: [2023-04-29 11:37:28,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +13: [2023-04-29 11:37:28,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +58: [2023-04-29 11:37:28,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +58: [2023-04-29 11:37:28,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +15: [2023-04-29 11:37:28,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +15: [2023-04-29 11:37:28,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +15: [2023-04-29 11:37:28,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +15: [2023-04-29 11:37:28,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +15: [2023-04-29 11:37:28,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +15: [2023-04-29 11:37:28,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +15: [2023-04-29 11:37:28,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +61: [2023-04-29 11:37:28,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +15: [2023-04-29 11:37:28,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +12: [2023-04-29 11:37:28,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +45: [2023-04-29 11:37:28,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +45: [2023-04-29 11:37:28,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +41: [2023-04-29 11:37:28,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +12: [2023-04-29 11:37:28,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +26: [2023-04-29 11:37:28,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +13: [2023-04-29 11:37:28,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +32: [2023-04-29 11:37:28,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +32: [2023-04-29 11:37:28,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +43: [2023-04-29 11:37:28,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +43: [2023-04-29 11:37:28,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +43: [2023-04-29 11:37:28,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +43: [2023-04-29 11:37:28,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +13: [2023-04-29 11:37:28,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +13: [2023-04-29 11:37:28,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +13: [2023-04-29 11:37:28,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +12: [2023-04-29 11:37:28,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +12: [2023-04-29 11:37:28,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +13: [2023-04-29 11:37:28,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +41: [2023-04-29 11:37:28,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +18: [2023-04-29 11:37:28,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +26: [2023-04-29 11:37:28,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +23: [2023-04-29 11:37:28,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +32: [2023-04-29 11:37:28,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +32: [2023-04-29 11:37:28,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +63: [2023-04-29 11:37:28,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +18: [2023-04-29 11:37:28,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +38: [2023-04-29 11:37:28,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +63: [2023-04-29 11:37:28,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +15: [2023-04-29 11:37:28,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +15: [2023-04-29 11:37:28,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +15: [2023-04-29 11:37:28,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +63: [2023-04-29 11:37:28,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +15: [2023-04-29 11:37:28,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +15: [2023-04-29 11:37:28,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +15: [2023-04-29 11:37:28,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +15: [2023-04-29 11:37:28,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +15: [2023-04-29 11:37:28,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +38: [2023-04-29 11:37:28,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +38: [2023-04-29 11:37:28,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +57: [2023-04-29 11:37:28,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +57: [2023-04-29 11:37:28,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. + 9: [2023-04-29 11:37:28,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +57: [2023-04-29 11:37:28,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +57: [2023-04-29 11:37:28,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. + 6: [2023-04-29 11:37:28,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +60: [2023-04-29 11:37:28,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +38: [2023-04-29 11:37:28,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +36: [2023-04-29 11:37:28,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +38: [2023-04-29 11:37:28,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +18: [2023-04-29 11:37:28,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +23: [2023-04-29 11:37:28,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +23: [2023-04-29 11:37:28,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +31: [2023-04-29 11:37:28,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +60: [2023-04-29 11:37:28,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 6: [2023-04-29 11:37:28,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +34: [2023-04-29 11:37:28,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +34: [2023-04-29 11:37:28,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +60: [2023-04-29 11:37:28,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 6: [2023-04-29 11:37:28,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... + 9: [2023-04-29 11:37:28,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +23: [2023-04-29 11:37:28,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +25: [2023-04-29 11:37:28,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +21: [2023-04-29 11:37:28,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +36: [2023-04-29 11:37:28,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +34: [2023-04-29 11:37:28,577] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +34: [2023-04-29 11:37:28,577] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 9: [2023-04-29 11:37:28,577] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +38: [2023-04-29 11:37:28,577] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 9: [2023-04-29 11:37:28,577] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +55: [2023-04-29 11:37:28,577] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 9: [2023-04-29 11:37:28,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 6: [2023-04-29 11:37:28,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... + 9: [2023-04-29 11:37:28,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +31: [2023-04-29 11:37:28,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... + 9: [2023-04-29 11:37:28,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 9: [2023-04-29 11:37:28,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +59: [2023-04-29 11:37:28,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 5: [2023-04-29 11:37:28,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +56: [2023-04-29 11:37:28,579] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +59: [2023-04-29 11:37:28,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +34: [2023-04-29 11:37:28,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 6: [2023-04-29 11:37:28,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +25: [2023-04-29 11:37:28,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +23: [2023-04-29 11:37:28,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +23: [2023-04-29 11:37:28,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +21: [2023-04-29 11:37:28,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... + 3: [2023-04-29 11:37:28,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 3: [2023-04-29 11:37:28,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 3: [2023-04-29 11:37:28,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 3: [2023-04-29 11:37:28,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +50: [2023-04-29 11:37:28,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +50: [2023-04-29 11:37:28,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +63: [2023-04-29 11:37:28,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +34: [2023-04-29 11:37:28,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +59: [2023-04-29 11:37:28,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +59: [2023-04-29 11:37:28,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +50: [2023-04-29 11:37:28,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +28: [2023-04-29 11:37:28,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +28: [2023-04-29 11:37:28,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +28: [2023-04-29 11:37:28,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 5: [2023-04-29 11:37:28,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +50: [2023-04-29 11:37:28,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +34: [2023-04-29 11:37:28,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +56: [2023-04-29 11:37:28,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +34: [2023-04-29 11:37:28,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 2: [2023-04-29 11:37:28,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +36: [2023-04-29 11:37:28,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 2: [2023-04-29 11:37:28,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +38: [2023-04-29 11:37:28,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +31: [2023-04-29 11:37:28,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +31: [2023-04-29 11:37:28,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +31: [2023-04-29 11:37:28,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +21: [2023-04-29 11:37:28,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +55: [2023-04-29 11:37:28,584] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +59: [2023-04-29 11:37:28,584] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 2: [2023-04-29 11:37:28,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +59: [2023-04-29 11:37:28,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 2: [2023-04-29 11:37:28,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 2: [2023-04-29 11:37:28,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 2: [2023-04-29 11:37:28,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 2: [2023-04-29 11:37:28,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +38: [2023-04-29 11:37:28,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +22: [2023-04-29 11:37:28,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 9: [2023-04-29 11:37:28,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 2: [2023-04-29 11:37:28,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 5: [2023-04-29 11:37:28,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +28: [2023-04-29 11:37:28,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 9: [2023-04-29 11:37:28,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 7: [2023-04-29 11:37:28,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +19: [2023-04-29 11:37:28,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +19: [2023-04-29 11:37:28,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +19: [2023-04-29 11:37:28,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 6: [2023-04-29 11:37:28,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +19: [2023-04-29 11:37:28,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +19: [2023-04-29 11:37:28,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +19: [2023-04-29 11:37:28,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +19: [2023-04-29 11:37:28,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +19: [2023-04-29 11:37:28,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 9: [2023-04-29 11:37:28,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +36: [2023-04-29 11:37:28,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +50: [2023-04-29 11:37:28,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. + 9: [2023-04-29 11:37:28,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +50: [2023-04-29 11:37:28,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +50: [2023-04-29 11:37:28,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +34: [2023-04-29 11:37:28,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +34: [2023-04-29 11:37:28,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +43: [2023-04-29 11:37:28,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +43: [2023-04-29 11:37:28,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +43: [2023-04-29 11:37:28,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +43: [2023-04-29 11:37:28,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +36: [2023-04-29 11:37:28,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 1: [2023-04-29 11:37:28,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +23: [2023-04-29 11:37:28,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +23: [2023-04-29 11:37:28,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +59: [2023-04-29 11:37:28,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +55: [2023-04-29 11:37:28,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 6: [2023-04-29 11:37:28,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +55: [2023-04-29 11:37:28,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +59: [2023-04-29 11:37:28,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +28: [2023-04-29 11:37:28,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +28: [2023-04-29 11:37:28,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +28: [2023-04-29 11:37:28,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +22: [2023-04-29 11:37:28,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +21: [2023-04-29 11:37:28,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +55: [2023-04-29 11:37:28,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +42: [2023-04-29 11:37:28,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +42: [2023-04-29 11:37:28,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +50: [2023-04-29 11:37:28,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 2: [2023-04-29 11:37:28,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +32: [2023-04-29 11:37:28,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 2: [2023-04-29 11:37:28,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +31: [2023-04-29 11:37:28,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +31: [2023-04-29 11:37:28,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... + 7: [2023-04-29 11:37:28,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +36: [2023-04-29 11:37:28,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +50: [2023-04-29 11:37:28,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +31: [2023-04-29 11:37:28,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... + 2: [2023-04-29 11:37:28,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +32: [2023-04-29 11:37:28,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +22: [2023-04-29 11:37:28,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +38: [2023-04-29 11:37:28,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... + 7: [2023-04-29 11:37:28,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 2: [2023-04-29 11:37:28,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +28: [2023-04-29 11:37:28,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +19: [2023-04-29 11:37:28,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +19: [2023-04-29 11:37:28,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +32: [2023-04-29 11:37:28,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 2: [2023-04-29 11:37:28,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +21: [2023-04-29 11:37:28,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +50: [2023-04-29 11:37:28,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +42: [2023-04-29 11:37:28,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. + 2: [2023-04-29 11:37:28,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +42: [2023-04-29 11:37:28,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +32: [2023-04-29 11:37:28,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +16: [2023-04-29 11:37:28,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +16: [2023-04-29 11:37:28,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +23: [2023-04-29 11:37:28,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 2: [2023-04-29 11:37:28,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +21: [2023-04-29 11:37:28,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 5: [2023-04-29 11:37:28,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +52: [2023-04-29 11:37:28,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +12: [2023-04-29 11:37:28,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +19: [2023-04-29 11:37:28,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +19: [2023-04-29 11:37:28,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +12: [2023-04-29 11:37:28,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +12: [2023-04-29 11:37:28,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +22: [2023-04-29 11:37:28,594] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 2: [2023-04-29 11:37:28,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 1: [2023-04-29 11:37:28,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +19: [2023-04-29 11:37:28,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +63: [2023-04-29 11:37:28,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 1: [2023-04-29 11:37:28,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 1: [2023-04-29 11:37:28,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +22: [2023-04-29 11:37:28,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +19: [2023-04-29 11:37:28,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +16: [2023-04-29 11:37:28,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. +29: [2023-04-29 11:37:28,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 6: [2023-04-29 11:37:28,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +19: [2023-04-29 11:37:28,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +26: [2023-04-29 11:37:28,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +16: [2023-04-29 11:37:28,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_07-model_01-model_states.pt. + 1: [2023-04-29 11:37:28,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +36: [2023-04-29 11:37:28,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +36: [2023-04-29 11:37:28,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +36: [2023-04-29 11:37:28,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +55: [2023-04-29 11:37:28,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +34: [2023-04-29 11:37:28,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +55: [2023-04-29 11:37:28,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +55: [2023-04-29 11:37:28,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +26: [2023-04-29 11:37:28,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +34: [2023-04-29 11:37:28,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +12: [2023-04-29 11:37:28,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +19: [2023-04-29 11:37:28,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +50: [2023-04-29 11:37:28,597] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +26: [2023-04-29 11:37:28,597] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +63: [2023-04-29 11:37:28,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +63: [2023-04-29 11:37:28,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +36: [2023-04-29 11:37:28,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +50: [2023-04-29 11:37:28,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. + 7: [2023-04-29 11:37:28,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 7: [2023-04-29 11:37:28,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... + 7: [2023-04-29 11:37:28,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +22: [2023-04-29 11:37:28,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +25: [2023-04-29 11:37:28,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +21: [2023-04-29 11:37:28,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +56: [2023-04-29 11:37:28,600] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +22: [2023-04-29 11:37:28,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +57: [2023-04-29 11:37:28,601] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 1: [2023-04-29 11:37:28,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... + 1: [2023-04-29 11:37:28,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +22: [2023-04-29 11:37:28,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +26: [2023-04-29 11:37:28,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +23: [2023-04-29 11:37:28,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +26: [2023-04-29 11:37:28,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +56: [2023-04-29 11:37:28,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +52: [2023-04-29 11:37:28,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +52: [2023-04-29 11:37:28,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +29: [2023-04-29 11:37:28,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +25: [2023-04-29 11:37:28,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +25: [2023-04-29 11:37:28,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +21: [2023-04-29 11:37:28,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +26: [2023-04-29 11:37:28,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +57: [2023-04-29 11:37:28,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 1: [2023-04-29 11:37:28,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +23: [2023-04-29 11:37:28,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +57: [2023-04-29 11:37:28,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +23: [2023-04-29 11:37:28,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +57: [2023-04-29 11:37:28,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +52: [2023-04-29 11:37:28,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. + 7: [2023-04-29 11:37:28,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... + 7: [2023-04-29 11:37:28,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +23: [2023-04-29 11:37:28,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +35: [2023-04-29 11:37:28,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +35: [2023-04-29 11:37:28,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +29: [2023-04-29 11:37:28,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 1: [2023-04-29 11:37:28,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +57: [2023-04-29 11:37:28,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +57: [2023-04-29 11:37:28,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +56: [2023-04-29 11:37:28,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +56: [2023-04-29 11:37:28,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +25: [2023-04-29 11:37:28,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +29: [2023-04-29 11:37:28,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +56: [2023-04-29 11:37:28,607] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +35: [2023-04-29 11:37:28,608] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +61: [2023-04-29 11:37:28,608] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +61: [2023-04-29 11:37:28,608] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +35: [2023-04-29 11:37:28,608] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +61: [2023-04-29 11:37:28,608] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +61: [2023-04-29 11:37:28,608] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +26: [2023-04-29 11:37:28,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 1: [2023-04-29 11:37:28,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +36: [2023-04-29 11:37:28,610] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +29: [2023-04-29 11:37:28,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +23: [2023-04-29 11:37:28,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +29: [2023-04-29 11:37:28,611] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +56: [2023-04-29 11:37:28,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +56: [2023-04-29 11:37:28,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +29: [2023-04-29 11:37:28,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +23: [2023-04-29 11:37:28,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +59: [2023-04-29 11:37:28,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +59: [2023-04-29 11:37:28,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +56: [2023-04-29 11:37:28,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +47: [2023-04-29 11:37:28,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +50: [2023-04-29 11:37:28,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 1: [2023-04-29 11:37:28,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +61: [2023-04-29 11:37:28,614] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +61: [2023-04-29 11:37:28,614] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +26: [2023-04-29 11:37:28,614] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +36: [2023-04-29 11:37:28,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +40: [2023-04-29 11:37:28,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +40: [2023-04-29 11:37:28,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +40: [2023-04-29 11:37:28,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +40: [2023-04-29 11:37:28,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +40: [2023-04-29 11:37:28,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +40: [2023-04-29 11:37:28,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +60: [2023-04-29 11:37:28,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +61: [2023-04-29 11:37:28,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +50: [2023-04-29 11:37:28,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +40: [2023-04-29 11:37:28,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +40: [2023-04-29 11:37:28,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +61: [2023-04-29 11:37:28,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +56: [2023-04-29 11:37:28,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +56: [2023-04-29 11:37:28,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +42: [2023-04-29 11:37:28,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +55: [2023-04-29 11:37:28,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +43: [2023-04-29 11:37:28,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +43: [2023-04-29 11:37:28,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +57: [2023-04-29 11:37:28,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +60: [2023-04-29 11:37:28,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +29: [2023-04-29 11:37:28,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +13: [2023-04-29 11:37:28,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +47: [2023-04-29 11:37:28,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +42: [2023-04-29 11:37:28,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +16: [2023-04-29 11:37:28,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +43: [2023-04-29 11:37:28,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +43: [2023-04-29 11:37:28,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +60: [2023-04-29 11:37:28,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +47: [2023-04-29 11:37:28,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +16: [2023-04-29 11:37:28,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +40: [2023-04-29 11:37:28,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 1: [2023-04-29 11:37:28,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +60: [2023-04-29 11:37:28,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +40: [2023-04-29 11:37:28,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +40: [2023-04-29 11:37:28,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +60: [2023-04-29 11:37:28,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +42: [2023-04-29 11:37:28,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +52: [2023-04-29 11:37:28,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +56: [2023-04-29 11:37:28,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +56: [2023-04-29 11:37:28,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +53: [2023-04-29 11:37:28,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +53: [2023-04-29 11:37:28,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +36: [2023-04-29 11:37:28,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +59: [2023-04-29 11:37:28,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +47: [2023-04-29 11:37:28,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +36: [2023-04-29 11:37:28,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +59: [2023-04-29 11:37:28,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +40: [2023-04-29 11:37:28,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +39: [2023-04-29 11:37:28,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +53: [2023-04-29 11:37:28,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +39: [2023-04-29 11:37:28,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +55: [2023-04-29 11:37:28,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +13: [2023-04-29 11:37:28,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +13: [2023-04-29 11:37:28,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +53: [2023-04-29 11:37:28,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +47: [2023-04-29 11:37:28,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +47: [2023-04-29 11:37:28,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +39: [2023-04-29 11:37:28,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +39: [2023-04-29 11:37:28,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +57: [2023-04-29 11:37:28,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +57: [2023-04-29 11:37:28,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +45: [2023-04-29 11:37:28,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +16: [2023-04-29 11:37:28,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +45: [2023-04-29 11:37:28,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +57: [2023-04-29 11:37:28,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +61: [2023-04-29 11:37:28,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +42: [2023-04-29 11:37:28,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +60: [2023-04-29 11:37:28,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +60: [2023-04-29 11:37:28,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +43: [2023-04-29 11:37:28,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +56: [2023-04-29 11:37:28,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +56: [2023-04-29 11:37:28,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 1: [2023-04-29 11:37:28,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +15: [2023-04-29 11:37:28,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +16: [2023-04-29 11:37:28,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +55: [2023-04-29 11:37:28,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +61: [2023-04-29 11:37:28,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +61: [2023-04-29 11:37:28,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +45: [2023-04-29 11:37:28,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +47: [2023-04-29 11:37:28,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +52: [2023-04-29 11:37:28,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +52: [2023-04-29 11:37:28,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +25: [2023-04-29 11:37:28,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +25: [2023-04-29 11:37:28,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +35: [2023-04-29 11:37:28,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +47: [2023-04-29 11:37:28,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +50: [2023-04-29 11:37:28,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +50: [2023-04-29 11:37:28,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +61: [2023-04-29 11:37:28,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +55: [2023-04-29 11:37:28,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +45: [2023-04-29 11:37:28,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +45: [2023-04-29 11:37:28,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... + 9: [2023-04-29 11:37:28,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +35: [2023-04-29 11:37:28,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +35: [2023-04-29 11:37:28,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 5: [2023-04-29 11:37:28,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 5: [2023-04-29 11:37:28,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +35: [2023-04-29 11:37:28,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 5: [2023-04-29 11:37:28,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 5: [2023-04-29 11:37:28,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +45: [2023-04-29 11:37:28,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +60: [2023-04-29 11:37:28,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... + 1: [2023-04-29 11:37:28,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +52: [2023-04-29 11:37:28,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +45: [2023-04-29 11:37:28,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +15: [2023-04-29 11:37:28,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +15: [2023-04-29 11:37:28,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +15: [2023-04-29 11:37:28,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +34: [2023-04-29 11:37:28,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +34: [2023-04-29 11:37:28,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +61: [2023-04-29 11:37:28,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +61: [2023-04-29 11:37:28,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +61: [2023-04-29 11:37:28,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +16: [2023-04-29 11:37:28,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +16: [2023-04-29 11:37:28,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +16: [2023-04-29 11:37:28,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +16: [2023-04-29 11:37:28,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +13: [2023-04-29 11:37:28,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +63: [2023-04-29 11:37:28,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +63: [2023-04-29 11:37:28,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. + 9: [2023-04-29 11:37:28,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +63: [2023-04-29 11:37:28,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. +63: [2023-04-29 11:37:28,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_31-model_01-model_states.pt. + 1: [2023-04-29 11:37:28,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +55: [2023-04-29 11:37:28,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +40: [2023-04-29 11:37:28,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +40: [2023-04-29 11:37:28,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +45: [2023-04-29 11:37:28,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... + 3: [2023-04-29 11:37:28,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +43: [2023-04-29 11:37:28,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +34: [2023-04-29 11:37:28,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +34: [2023-04-29 11:37:28,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +36: [2023-04-29 11:37:28,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +36: [2023-04-29 11:37:28,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 5: [2023-04-29 11:37:28,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 5: [2023-04-29 11:37:28,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 5: [2023-04-29 11:37:28,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +40: [2023-04-29 11:37:28,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +57: [2023-04-29 11:37:28,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 3: [2023-04-29 11:37:28,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +43: [2023-04-29 11:37:28,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +43: [2023-04-29 11:37:28,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +34: [2023-04-29 11:37:28,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +61: [2023-04-29 11:37:28,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +13: [2023-04-29 11:37:28,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 5: [2023-04-29 11:37:28,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 3: [2023-04-29 11:37:28,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... + 3: [2023-04-29 11:37:28,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 3: [2023-04-29 11:37:28,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 9: [2023-04-29 11:37:28,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +16: [2023-04-29 11:37:28,650] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +40: [2023-04-29 11:37:28,650] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +34: [2023-04-29 11:37:28,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +16: [2023-04-29 11:37:28,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... +16: [2023-04-29 11:37:28,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 3: [2023-04-29 11:37:28,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... + 1: [2023-04-29 11:37:28,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +16: [2023-04-29 11:37:28,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt... + 9: [2023-04-29 11:37:28,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 2: [2023-04-29 11:37:28,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +43: [2023-04-29 11:37:28,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +13: [2023-04-29 11:37:28,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +13: [2023-04-29 11:37:28,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 3: [2023-04-29 11:37:28,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +53: [2023-04-29 11:37:28,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 3: [2023-04-29 11:37:28,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +39: [2023-04-29 11:37:28,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +53: [2023-04-29 11:37:28,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +34: [2023-04-29 11:37:28,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +53: [2023-04-29 11:37:28,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +55: [2023-04-29 11:37:28,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 9: [2023-04-29 11:37:28,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +19: [2023-04-29 11:37:28,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +53: [2023-04-29 11:37:28,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +50: [2023-04-29 11:37:28,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. + 5: [2023-04-29 11:37:28,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +39: [2023-04-29 11:37:28,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 9: [2023-04-29 11:37:28,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +57: [2023-04-29 11:37:28,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +34: [2023-04-29 11:37:28,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +39: [2023-04-29 11:37:28,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +39: [2023-04-29 11:37:28,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 9: [2023-04-29 11:37:28,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +51: [2023-04-29 11:37:28,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +51: [2023-04-29 11:37:28,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +19: [2023-04-29 11:37:28,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +51: [2023-04-29 11:37:28,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +51: [2023-04-29 11:37:28,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. + 9: [2023-04-29 11:37:28,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 5: [2023-04-29 11:37:28,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 2: [2023-04-29 11:37:28,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 2: [2023-04-29 11:37:28,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 2: [2023-04-29 11:37:28,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +62: [2023-04-29 11:37:28,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +62: [2023-04-29 11:37:28,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +62: [2023-04-29 11:37:28,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +19: [2023-04-29 11:37:28,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +62: [2023-04-29 11:37:28,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +19: [2023-04-29 11:37:28,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 9: [2023-04-29 11:37:28,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 9: [2023-04-29 11:37:28,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +55: [2023-04-29 11:37:28,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 9: [2023-04-29 11:37:28,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 9: [2023-04-29 11:37:28,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +34: [2023-04-29 11:37:28,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +15: [2023-04-29 11:37:28,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 5: [2023-04-29 11:37:28,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +55: [2023-04-29 11:37:28,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +62: [2023-04-29 11:37:28,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 5: [2023-04-29 11:37:28,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +62: [2023-04-29 11:37:28,667] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 5: [2023-04-29 11:37:28,667] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +62: [2023-04-29 11:37:28,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +34: [2023-04-29 11:37:28,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +15: [2023-04-29 11:37:28,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +48: [2023-04-29 11:37:28,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +48: [2023-04-29 11:37:28,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +62: [2023-04-29 11:37:28,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +13: [2023-04-29 11:37:28,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +34: [2023-04-29 11:37:28,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +63: [2023-04-29 11:37:28,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +63: [2023-04-29 11:37:28,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +48: [2023-04-29 11:37:28,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 5: [2023-04-29 11:37:28,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +48: [2023-04-29 11:37:28,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +15: [2023-04-29 11:37:28,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +15: [2023-04-29 11:37:28,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +63: [2023-04-29 11:37:28,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... +34: [2023-04-29 11:37:28,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +61: [2023-04-29 11:37:28,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +43: [2023-04-29 11:37:28,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +34: [2023-04-29 11:37:28,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +63: [2023-04-29 11:37:28,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt... + 5: [2023-04-29 11:37:28,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +48: [2023-04-29 11:37:28,678] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +48: [2023-04-29 11:37:28,678] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +48: [2023-04-29 11:37:28,678] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +57: [2023-04-29 11:37:28,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +48: [2023-04-29 11:37:28,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +43: [2023-04-29 11:37:28,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +59: [2023-04-29 11:37:28,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +59: [2023-04-29 11:37:28,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +43: [2023-04-29 11:37:28,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +50: [2023-04-29 11:37:28,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +34: [2023-04-29 11:37:28,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 2: [2023-04-29 11:37:28,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +32: [2023-04-29 11:37:28,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +32: [2023-04-29 11:37:28,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +32: [2023-04-29 11:37:28,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +32: [2023-04-29 11:37:28,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +32: [2023-04-29 11:37:28,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +32: [2023-04-29 11:37:28,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +32: [2023-04-29 11:37:28,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +32: [2023-04-29 11:37:28,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +61: [2023-04-29 11:37:28,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +50: [2023-04-29 11:37:28,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +50: [2023-04-29 11:37:28,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +57: [2023-04-29 11:37:28,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +19: [2023-04-29 11:37:28,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +16: [2023-04-29 11:37:28,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +53: [2023-04-29 11:37:28,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +53: [2023-04-29 11:37:28,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +51: [2023-04-29 11:37:28,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 5: [2023-04-29 11:37:28,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +53: [2023-04-29 11:37:28,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +53: [2023-04-29 11:37:28,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +32: [2023-04-29 11:37:28,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +51: [2023-04-29 11:37:28,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +32: [2023-04-29 11:37:28,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +57: [2023-04-29 11:37:28,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +57: [2023-04-29 11:37:28,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +57: [2023-04-29 11:37:28,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +32: [2023-04-29 11:37:28,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +50: [2023-04-29 11:37:28,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +32: [2023-04-29 11:37:28,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +61: [2023-04-29 11:37:28,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +16: [2023-04-29 11:37:28,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +59: [2023-04-29 11:37:28,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +19: [2023-04-29 11:37:28,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +59: [2023-04-29 11:37:28,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +59: [2023-04-29 11:37:28,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +19: [2023-04-29 11:37:28,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +40: [2023-04-29 11:37:28,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +50: [2023-04-29 11:37:28,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +19: [2023-04-29 11:37:28,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +51: [2023-04-29 11:37:28,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +32: [2023-04-29 11:37:28,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +32: [2023-04-29 11:37:28,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +16: [2023-04-29 11:37:28,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +53: [2023-04-29 11:37:28,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +50: [2023-04-29 11:37:28,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +32: [2023-04-29 11:37:28,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +53: [2023-04-29 11:37:28,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +53: [2023-04-29 11:37:28,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +51: [2023-04-29 11:37:28,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +50: [2023-04-29 11:37:28,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. + 2: [2023-04-29 11:37:28,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +16: [2023-04-29 11:37:28,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... + 9: [2023-04-29 11:37:28,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 2: [2023-04-29 11:37:28,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +50: [2023-04-29 11:37:28,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +32: [2023-04-29 11:37:28,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 2: [2023-04-29 11:37:28,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +57: [2023-04-29 11:37:28,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +53: [2023-04-29 11:37:28,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 9: [2023-04-29 11:37:28,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +59: [2023-04-29 11:37:28,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +57: [2023-04-29 11:37:28,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +57: [2023-04-29 11:37:28,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +59: [2023-04-29 11:37:28,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +43: [2023-04-29 11:37:28,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. + 9: [2023-04-29 11:37:28,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 9: [2023-04-29 11:37:28,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +61: [2023-04-29 11:37:28,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +43: [2023-04-29 11:37:28,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +59: [2023-04-29 11:37:28,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +34: [2023-04-29 11:37:28,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +61: [2023-04-29 11:37:28,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +49: [2023-04-29 11:37:28,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +49: [2023-04-29 11:37:28,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +49: [2023-04-29 11:37:28,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +49: [2023-04-29 11:37:28,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +43: [2023-04-29 11:37:28,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +43: [2023-04-29 11:37:28,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +49: [2023-04-29 11:37:28,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +43: [2023-04-29 11:37:28,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +43: [2023-04-29 11:37:28,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +49: [2023-04-29 11:37:28,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +49: [2023-04-29 11:37:28,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +49: [2023-04-29 11:37:28,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +61: [2023-04-29 11:37:28,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +34: [2023-04-29 11:37:28,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +40: [2023-04-29 11:37:28,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +40: [2023-04-29 11:37:28,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +43: [2023-04-29 11:37:28,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +40: [2023-04-29 11:37:28,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +43: [2023-04-29 11:37:28,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +50: [2023-04-29 11:37:28,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +40: [2023-04-29 11:37:28,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +40: [2023-04-29 11:37:28,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +16: [2023-04-29 11:37:28,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 5: [2023-04-29 11:37:28,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 5: [2023-04-29 11:37:28,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 5: [2023-04-29 11:37:28,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +40: [2023-04-29 11:37:28,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +40: [2023-04-29 11:37:28,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +40: [2023-04-29 11:37:28,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +40: [2023-04-29 11:37:28,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +39: [2023-04-29 11:37:28,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +16: [2023-04-29 11:37:28,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. + 5: [2023-04-29 11:37:28,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +61: [2023-04-29 11:37:28,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +37: [2023-04-29 11:37:28,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +37: [2023-04-29 11:37:28,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +37: [2023-04-29 11:37:28,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +53: [2023-04-29 11:37:28,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +37: [2023-04-29 11:37:28,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +50: [2023-04-29 11:37:28,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +50: [2023-04-29 11:37:28,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +50: [2023-04-29 11:37:28,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +39: [2023-04-29 11:37:28,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +39: [2023-04-29 11:37:28,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +40: [2023-04-29 11:37:28,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +53: [2023-04-29 11:37:28,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +53: [2023-04-29 11:37:28,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +16: [2023-04-29 11:37:28,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +61: [2023-04-29 11:37:28,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +50: [2023-04-29 11:37:28,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +39: [2023-04-29 11:37:28,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +37: [2023-04-29 11:37:28,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +62: [2023-04-29 11:37:28,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +37: [2023-04-29 11:37:28,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +62: [2023-04-29 11:37:28,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +62: [2023-04-29 11:37:28,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +37: [2023-04-29 11:37:28,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +37: [2023-04-29 11:37:28,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +53: [2023-04-29 11:37:28,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +16: [2023-04-29 11:37:28,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt... +53: [2023-04-29 11:37:28,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +53: [2023-04-29 11:37:28,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +53: [2023-04-29 11:37:28,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +50: [2023-04-29 11:37:28,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +39: [2023-04-29 11:37:28,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +50: [2023-04-29 11:37:28,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +16: [2023-04-29 11:37:28,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +16: [2023-04-29 11:37:28,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +16: [2023-04-29 11:37:28,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +39: [2023-04-29 11:37:28,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +63: [2023-04-29 11:37:28,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +39: [2023-04-29 11:37:28,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +16: [2023-04-29 11:37:28,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_00-model_states.pt. +53: [2023-04-29 11:37:28,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +32: [2023-04-29 11:37:28,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +63: [2023-04-29 11:37:28,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +63: [2023-04-29 11:37:28,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +48: [2023-04-29 11:37:28,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +63: [2023-04-29 11:37:28,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +48: [2023-04-29 11:37:28,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +39: [2023-04-29 11:37:28,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... + 0: [2023-04-29 11:37:28,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 0: [2023-04-29 11:37:28,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 0: [2023-04-29 11:37:28,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 0: [2023-04-29 11:37:28,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +30: [2023-04-29 11:37:28,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +30: [2023-04-29 11:37:28,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +30: [2023-04-29 11:37:28,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +48: [2023-04-29 11:37:28,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +30: [2023-04-29 11:37:28,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +63: [2023-04-29 11:37:28,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_00-model_states.pt. +62: [2023-04-29 11:37:28,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +62: [2023-04-29 11:37:28,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +63: [2023-04-29 11:37:28,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +63: [2023-04-29 11:37:28,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +62: [2023-04-29 11:37:28,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +42: [2023-04-29 11:37:28,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +42: [2023-04-29 11:37:28,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +42: [2023-04-29 11:37:28,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +42: [2023-04-29 11:37:28,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +42: [2023-04-29 11:37:28,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +42: [2023-04-29 11:37:28,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +42: [2023-04-29 11:37:28,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +62: [2023-04-29 11:37:28,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +42: [2023-04-29 11:37:28,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +40: [2023-04-29 11:37:28,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +48: [2023-04-29 11:37:28,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 0: [2023-04-29 11:37:28,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +30: [2023-04-29 11:37:28,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +30: [2023-04-29 11:37:28,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +30: [2023-04-29 11:37:28,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +42: [2023-04-29 11:37:28,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +30: [2023-04-29 11:37:28,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 0: [2023-04-29 11:37:28,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 0: [2023-04-29 11:37:28,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 0: [2023-04-29 11:37:28,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +63: [2023-04-29 11:37:28,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt... +62: [2023-04-29 11:37:28,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +40: [2023-04-29 11:37:28,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +32: [2023-04-29 11:37:28,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +40: [2023-04-29 11:37:28,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +53: [2023-04-29 11:37:28,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +40: [2023-04-29 11:37:28,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +42: [2023-04-29 11:37:28,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +42: [2023-04-29 11:37:28,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +42: [2023-04-29 11:37:28,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +42: [2023-04-29 11:37:28,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +62: [2023-04-29 11:37:28,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 5: [2023-04-29 11:37:28,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +40: [2023-04-29 11:37:28,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +42: [2023-04-29 11:37:28,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +42: [2023-04-29 11:37:28,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +42: [2023-04-29 11:37:28,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 5: [2023-04-29 11:37:28,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +32: [2023-04-29 11:37:28,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +62: [2023-04-29 11:37:28,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +32: [2023-04-29 11:37:28,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. + 5: [2023-04-29 11:37:28,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +53: [2023-04-29 11:37:28,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +62: [2023-04-29 11:37:28,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 5: [2023-04-29 11:37:28,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +49: [2023-04-29 11:37:28,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +32: [2023-04-29 11:37:28,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +48: [2023-04-29 11:37:28,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +53: [2023-04-29 11:37:28,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +53: [2023-04-29 11:37:28,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +48: [2023-04-29 11:37:28,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +16: [2023-04-29 11:37:28,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +52: [2023-04-29 11:37:28,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +52: [2023-04-29 11:37:28,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +52: [2023-04-29 11:37:28,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +52: [2023-04-29 11:37:28,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +16: [2023-04-29 11:37:28,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +48: [2023-04-29 11:37:28,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +16: [2023-04-29 11:37:28,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +49: [2023-04-29 11:37:28,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +49: [2023-04-29 11:37:28,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +49: [2023-04-29 11:37:28,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +48: [2023-04-29 11:37:28,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +41: [2023-04-29 11:37:28,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +41: [2023-04-29 11:37:28,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +16: [2023-04-29 11:37:28,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +53: [2023-04-29 11:37:28,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +41: [2023-04-29 11:37:28,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +41: [2023-04-29 11:37:28,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +33: [2023-04-29 11:37:28,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +33: [2023-04-29 11:37:28,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +33: [2023-04-29 11:37:28,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +33: [2023-04-29 11:37:28,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +32: [2023-04-29 11:37:28,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +62: [2023-04-29 11:37:28,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +33: [2023-04-29 11:37:28,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +33: [2023-04-29 11:37:28,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +62: [2023-04-29 11:37:28,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +33: [2023-04-29 11:37:28,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +33: [2023-04-29 11:37:28,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +62: [2023-04-29 11:37:28,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +41: [2023-04-29 11:37:28,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +41: [2023-04-29 11:37:28,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +37: [2023-04-29 11:37:28,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +32: [2023-04-29 11:37:28,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +62: [2023-04-29 11:37:28,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +62: [2023-04-29 11:37:28,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +49: [2023-04-29 11:37:28,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +41: [2023-04-29 11:37:28,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +53: [2023-04-29 11:37:28,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +41: [2023-04-29 11:37:28,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +32: [2023-04-29 11:37:28,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +52: [2023-04-29 11:37:28,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +41: [2023-04-29 11:37:28,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +41: [2023-04-29 11:37:28,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +41: [2023-04-29 11:37:28,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +37: [2023-04-29 11:37:28,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +37: [2023-04-29 11:37:28,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +37: [2023-04-29 11:37:28,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +41: [2023-04-29 11:37:28,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +53: [2023-04-29 11:37:28,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +53: [2023-04-29 11:37:28,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +52: [2023-04-29 11:37:28,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +41: [2023-04-29 11:37:28,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +52: [2023-04-29 11:37:28,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +49: [2023-04-29 11:37:28,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +49: [2023-04-29 11:37:28,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +49: [2023-04-29 11:37:28,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +41: [2023-04-29 11:37:28,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +30: [2023-04-29 11:37:28,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +52: [2023-04-29 11:37:28,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +46: [2023-04-29 11:37:28,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +46: [2023-04-29 11:37:28,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +46: [2023-04-29 11:37:28,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +46: [2023-04-29 11:37:28,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 0: [2023-04-29 11:37:28,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +30: [2023-04-29 11:37:28,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +41: [2023-04-29 11:37:28,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +41: [2023-04-29 11:37:28,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +30: [2023-04-29 11:37:28,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +30: [2023-04-29 11:37:28,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +37: [2023-04-29 11:37:28,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +46: [2023-04-29 11:37:28,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +46: [2023-04-29 11:37:28,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +46: [2023-04-29 11:37:28,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +46: [2023-04-29 11:37:28,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +54: [2023-04-29 11:37:28,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +54: [2023-04-29 11:37:28,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +38: [2023-04-29 11:37:28,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +38: [2023-04-29 11:37:28,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +36: [2023-04-29 11:37:28,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +36: [2023-04-29 11:37:28,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +54: [2023-04-29 11:37:28,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +54: [2023-04-29 11:37:28,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +36: [2023-04-29 11:37:28,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +36: [2023-04-29 11:37:28,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +38: [2023-04-29 11:37:28,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +42: [2023-04-29 11:37:28,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +42: [2023-04-29 11:37:28,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +42: [2023-04-29 11:37:28,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +38: [2023-04-29 11:37:28,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. + 0: [2023-04-29 11:37:28,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 0: [2023-04-29 11:37:28,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +42: [2023-04-29 11:37:28,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +51: [2023-04-29 11:37:28,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +51: [2023-04-29 11:37:28,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +51: [2023-04-29 11:37:28,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +51: [2023-04-29 11:37:28,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +51: [2023-04-29 11:37:28,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +51: [2023-04-29 11:37:28,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +51: [2023-04-29 11:37:28,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +51: [2023-04-29 11:37:28,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +54: [2023-04-29 11:37:28,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +54: [2023-04-29 11:37:28,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +54: [2023-04-29 11:37:28,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 0: [2023-04-29 11:37:28,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +54: [2023-04-29 11:37:28,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +51: [2023-04-29 11:37:28,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +51: [2023-04-29 11:37:28,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +30: [2023-04-29 11:37:28,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +51: [2023-04-29 11:37:28,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +47: [2023-04-29 11:37:28,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +47: [2023-04-29 11:37:28,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +47: [2023-04-29 11:37:28,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +47: [2023-04-29 11:37:28,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +51: [2023-04-29 11:37:28,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +51: [2023-04-29 11:37:28,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +51: [2023-04-29 11:37:28,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +51: [2023-04-29 11:37:28,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +37: [2023-04-29 11:37:28,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 6: [2023-04-29 11:37:28,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 6: [2023-04-29 11:37:28,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 6: [2023-04-29 11:37:28,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 6: [2023-04-29 11:37:28,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +51: [2023-04-29 11:37:28,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 0: [2023-04-29 11:37:28,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +37: [2023-04-29 11:37:28,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +30: [2023-04-29 11:37:28,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +45: [2023-04-29 11:37:28,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +45: [2023-04-29 11:37:28,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +55: [2023-04-29 11:37:28,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +55: [2023-04-29 11:37:28,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +55: [2023-04-29 11:37:28,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +37: [2023-04-29 11:37:28,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +55: [2023-04-29 11:37:28,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +30: [2023-04-29 11:37:28,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +30: [2023-04-29 11:37:28,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 6: [2023-04-29 11:37:28,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 6: [2023-04-29 11:37:28,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 6: [2023-04-29 11:37:28,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 6: [2023-04-29 11:37:28,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +45: [2023-04-29 11:37:28,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +45: [2023-04-29 11:37:28,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +60: [2023-04-29 11:37:28,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +60: [2023-04-29 11:37:28,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +33: [2023-04-29 11:37:28,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +33: [2023-04-29 11:37:28,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +36: [2023-04-29 11:37:28,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +44: [2023-04-29 11:37:28,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +44: [2023-04-29 11:37:28,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +60: [2023-04-29 11:37:28,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +60: [2023-04-29 11:37:28,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +44: [2023-04-29 11:37:28,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +38: [2023-04-29 11:37:28,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +38: [2023-04-29 11:37:28,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +44: [2023-04-29 11:37:28,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +36: [2023-04-29 11:37:28,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 0: [2023-04-29 11:37:28,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +42: [2023-04-29 11:37:28,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +36: [2023-04-29 11:37:28,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +44: [2023-04-29 11:37:28,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +44: [2023-04-29 11:37:28,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +44: [2023-04-29 11:37:28,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +38: [2023-04-29 11:37:28,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +38: [2023-04-29 11:37:28,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +44: [2023-04-29 11:37:28,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 4: [2023-04-29 11:37:28,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 4: [2023-04-29 11:37:28,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 4: [2023-04-29 11:37:28,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 0: [2023-04-29 11:37:28,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +42: [2023-04-29 11:37:28,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 0: [2023-04-29 11:37:28,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +21: [2023-04-29 11:37:28,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +21: [2023-04-29 11:37:28,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +42: [2023-04-29 11:37:28,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +21: [2023-04-29 11:37:28,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +36: [2023-04-29 11:37:28,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +21: [2023-04-29 11:37:28,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +42: [2023-04-29 11:37:28,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +47: [2023-04-29 11:37:28,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +29: [2023-04-29 11:37:28,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +29: [2023-04-29 11:37:28,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +29: [2023-04-29 11:37:28,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +29: [2023-04-29 11:37:28,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 4: [2023-04-29 11:37:28,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +21: [2023-04-29 11:37:28,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +39: [2023-04-29 11:37:28,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +39: [2023-04-29 11:37:28,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +47: [2023-04-29 11:37:28,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +33: [2023-04-29 11:37:28,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +21: [2023-04-29 11:37:28,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +21: [2023-04-29 11:37:28,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +21: [2023-04-29 11:37:28,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +47: [2023-04-29 11:37:28,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +47: [2023-04-29 11:37:28,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +29: [2023-04-29 11:37:28,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +39: [2023-04-29 11:37:28,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +39: [2023-04-29 11:37:28,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +20: [2023-04-29 11:37:28,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +20: [2023-04-29 11:37:28,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +20: [2023-04-29 11:37:28,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +20: [2023-04-29 11:37:28,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +29: [2023-04-29 11:37:28,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +29: [2023-04-29 11:37:28,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +29: [2023-04-29 11:37:28,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +33: [2023-04-29 11:37:28,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +17: [2023-04-29 11:37:28,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +17: [2023-04-29 11:37:28,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +17: [2023-04-29 11:37:28,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +17: [2023-04-29 11:37:28,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +62: [2023-04-29 11:37:28,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +62: [2023-04-29 11:37:28,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +62: [2023-04-29 11:37:28,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +39: [2023-04-29 11:37:28,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +39: [2023-04-29 11:37:28,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +60: [2023-04-29 11:37:28,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +60: [2023-04-29 11:37:28,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +60: [2023-04-29 11:37:28,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +39: [2023-04-29 11:37:28,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +55: [2023-04-29 11:37:28,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +20: [2023-04-29 11:37:28,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +20: [2023-04-29 11:37:28,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +45: [2023-04-29 11:37:28,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +55: [2023-04-29 11:37:28,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +55: [2023-04-29 11:37:28,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +55: [2023-04-29 11:37:28,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +33: [2023-04-29 11:37:28,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +45: [2023-04-29 11:37:28,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +41: [2023-04-29 11:37:28,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +20: [2023-04-29 11:37:28,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +20: [2023-04-29 11:37:28,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +45: [2023-04-29 11:37:28,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +60: [2023-04-29 11:37:28,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +52: [2023-04-29 11:37:28,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +39: [2023-04-29 11:37:28,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +45: [2023-04-29 11:37:28,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +52: [2023-04-29 11:37:28,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +47: [2023-04-29 11:37:28,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +47: [2023-04-29 11:37:28,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +47: [2023-04-29 11:37:28,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +47: [2023-04-29 11:37:28,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +60: [2023-04-29 11:37:28,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +60: [2023-04-29 11:37:28,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +33: [2023-04-29 11:37:28,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +62: [2023-04-29 11:37:28,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +62: [2023-04-29 11:37:28,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +62: [2023-04-29 11:37:28,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +62: [2023-04-29 11:37:28,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +41: [2023-04-29 11:37:28,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +41: [2023-04-29 11:37:28,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +18: [2023-04-29 11:37:28,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +18: [2023-04-29 11:37:28,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +18: [2023-04-29 11:37:28,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +18: [2023-04-29 11:37:28,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +60: [2023-04-29 11:37:28,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +47: [2023-04-29 11:37:28,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +60: [2023-04-29 11:37:28,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +60: [2023-04-29 11:37:28,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +46: [2023-04-29 11:37:28,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +60: [2023-04-29 11:37:28,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +41: [2023-04-29 11:37:28,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +47: [2023-04-29 11:37:28,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +60: [2023-04-29 11:37:28,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +52: [2023-04-29 11:37:28,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +52: [2023-04-29 11:37:28,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +60: [2023-04-29 11:37:28,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +47: [2023-04-29 11:37:28,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +27: [2023-04-29 11:37:28,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +27: [2023-04-29 11:37:28,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +27: [2023-04-29 11:37:28,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +27: [2023-04-29 11:37:28,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. + 4: [2023-04-29 11:37:28,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. + 4: [2023-04-29 11:37:28,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +47: [2023-04-29 11:37:28,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. + 4: [2023-04-29 11:37:28,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +62: [2023-04-29 11:37:28,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +41: [2023-04-29 11:37:28,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +52: [2023-04-29 11:37:28,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +52: [2023-04-29 11:37:28,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +46: [2023-04-29 11:37:28,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +46: [2023-04-29 11:37:28,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +46: [2023-04-29 11:37:28,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +59: [2023-04-29 11:37:28,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +59: [2023-04-29 11:37:28,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +59: [2023-04-29 11:37:28,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +59: [2023-04-29 11:37:28,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +33: [2023-04-29 11:37:28,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +41: [2023-04-29 11:37:28,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +41: [2023-04-29 11:37:28,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +41: [2023-04-29 11:37:28,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +54: [2023-04-29 11:37:28,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +54: [2023-04-29 11:37:28,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +52: [2023-04-29 11:37:28,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... + 8: [2023-04-29 11:37:28,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. + 8: [2023-04-29 11:37:28,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. + 8: [2023-04-29 11:37:28,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. + 8: [2023-04-29 11:37:28,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +61: [2023-04-29 11:37:28,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +61: [2023-04-29 11:37:28,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +33: [2023-04-29 11:37:28,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +17: [2023-04-29 11:37:28,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +59: [2023-04-29 11:37:28,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +59: [2023-04-29 11:37:28,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +52: [2023-04-29 11:37:28,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +59: [2023-04-29 11:37:28,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +59: [2023-04-29 11:37:28,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +54: [2023-04-29 11:37:28,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +61: [2023-04-29 11:37:28,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +61: [2023-04-29 11:37:28,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +56: [2023-04-29 11:37:28,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +56: [2023-04-29 11:37:28,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +17: [2023-04-29 11:37:28,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +54: [2023-04-29 11:37:28,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +51: [2023-04-29 11:37:28,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +34: [2023-04-29 11:37:28,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +17: [2023-04-29 11:37:28,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +34: [2023-04-29 11:37:28,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +34: [2023-04-29 11:37:28,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +56: [2023-04-29 11:37:28,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +34: [2023-04-29 11:37:28,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +56: [2023-04-29 11:37:28,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +17: [2023-04-29 11:37:28,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +41: [2023-04-29 11:37:28,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +11: [2023-04-29 11:37:28,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +11: [2023-04-29 11:37:28,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +11: [2023-04-29 11:37:28,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +11: [2023-04-29 11:37:28,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +35: [2023-04-29 11:37:28,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +35: [2023-04-29 11:37:28,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +46: [2023-04-29 11:37:28,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +18: [2023-04-29 11:37:28,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +18: [2023-04-29 11:37:28,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +11: [2023-04-29 11:37:28,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +18: [2023-04-29 11:37:28,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +18: [2023-04-29 11:37:28,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +35: [2023-04-29 11:37:28,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +35: [2023-04-29 11:37:28,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +35: [2023-04-29 11:37:28,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +35: [2023-04-29 11:37:28,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +35: [2023-04-29 11:37:28,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +11: [2023-04-29 11:37:28,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +11: [2023-04-29 11:37:28,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +35: [2023-04-29 11:37:28,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +11: [2023-04-29 11:37:28,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 6: [2023-04-29 11:37:28,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +41: [2023-04-29 11:37:28,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +31: [2023-04-29 11:37:28,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +31: [2023-04-29 11:37:28,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +31: [2023-04-29 11:37:28,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 4: [2023-04-29 11:37:28,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +31: [2023-04-29 11:37:28,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +51: [2023-04-29 11:37:28,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +41: [2023-04-29 11:37:28,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +41: [2023-04-29 11:37:28,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +35: [2023-04-29 11:37:28,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +35: [2023-04-29 11:37:28,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +35: [2023-04-29 11:37:28,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +35: [2023-04-29 11:37:28,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +59: [2023-04-29 11:37:28,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +59: [2023-04-29 11:37:28,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +31: [2023-04-29 11:37:28,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +38: [2023-04-29 11:37:28,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. + 6: [2023-04-29 11:37:28,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 6: [2023-04-29 11:37:28,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +38: [2023-04-29 11:37:28,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +38: [2023-04-29 11:37:28,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +38: [2023-04-29 11:37:28,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +56: [2023-04-29 11:37:28,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +56: [2023-04-29 11:37:28,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +56: [2023-04-29 11:37:28,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. + 6: [2023-04-29 11:37:28,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +14: [2023-04-29 11:37:28,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +14: [2023-04-29 11:37:28,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +14: [2023-04-29 11:37:28,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +35: [2023-04-29 11:37:28,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +14: [2023-04-29 11:37:28,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +27: [2023-04-29 11:37:28,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +27: [2023-04-29 11:37:28,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +27: [2023-04-29 11:37:28,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +35: [2023-04-29 11:37:28,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 8: [2023-04-29 11:37:28,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 8: [2023-04-29 11:37:28,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +31: [2023-04-29 11:37:28,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 8: [2023-04-29 11:37:28,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +31: [2023-04-29 11:37:28,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 8: [2023-04-29 11:37:28,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +31: [2023-04-29 11:37:28,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +44: [2023-04-29 11:37:28,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +44: [2023-04-29 11:37:28,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +35: [2023-04-29 11:37:28,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +35: [2023-04-29 11:37:28,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +36: [2023-04-29 11:37:28,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +36: [2023-04-29 11:37:28,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +46: [2023-04-29 11:37:28,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +56: [2023-04-29 11:37:28,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +38: [2023-04-29 11:37:28,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +44: [2023-04-29 11:37:28,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +46: [2023-04-29 11:37:28,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +41: [2023-04-29 11:37:28,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +14: [2023-04-29 11:37:28,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +36: [2023-04-29 11:37:28,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +27: [2023-04-29 11:37:28,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +36: [2023-04-29 11:37:28,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +36: [2023-04-29 11:37:28,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +36: [2023-04-29 11:37:28,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. + 8: [2023-04-29 11:37:28,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +56: [2023-04-29 11:37:28,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +56: [2023-04-29 11:37:28,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +58: [2023-04-29 11:37:28,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +58: [2023-04-29 11:37:28,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +56: [2023-04-29 11:37:28,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +58: [2023-04-29 11:37:28,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +38: [2023-04-29 11:37:28,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +38: [2023-04-29 11:37:28,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +59: [2023-04-29 11:37:28,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +58: [2023-04-29 11:37:28,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +46: [2023-04-29 11:37:28,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +14: [2023-04-29 11:37:28,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 8: [2023-04-29 11:37:28,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 8: [2023-04-29 11:37:28,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +51: [2023-04-29 11:37:28,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +38: [2023-04-29 11:37:28,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +14: [2023-04-29 11:37:28,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +59: [2023-04-29 11:37:28,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +44: [2023-04-29 11:37:28,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +56: [2023-04-29 11:37:28,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +51: [2023-04-29 11:37:28,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +54: [2023-04-29 11:37:28,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +14: [2023-04-29 11:37:28,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 8: [2023-04-29 11:37:28,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +34: [2023-04-29 11:37:28,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 8: [2023-04-29 11:37:28,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +63: [2023-04-29 11:37:28,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +63: [2023-04-29 11:37:28,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +36: [2023-04-29 11:37:28,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +36: [2023-04-29 11:37:28,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +34: [2023-04-29 11:37:28,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +36: [2023-04-29 11:37:28,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +36: [2023-04-29 11:37:28,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +36: [2023-04-29 11:37:28,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +54: [2023-04-29 11:37:28,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +63: [2023-04-29 11:37:28,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +54: [2023-04-29 11:37:28,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +34: [2023-04-29 11:37:28,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +58: [2023-04-29 11:37:28,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +56: [2023-04-29 11:37:28,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +56: [2023-04-29 11:37:28,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +63: [2023-04-29 11:37:28,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +41: [2023-04-29 11:37:28,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +58: [2023-04-29 11:37:28,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +58: [2023-04-29 11:37:28,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +58: [2023-04-29 11:37:28,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +56: [2023-04-29 11:37:28,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +56: [2023-04-29 11:37:28,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +17: [2023-04-29 11:37:28,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +17: [2023-04-29 11:37:28,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +36: [2023-04-29 11:37:28,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +46: [2023-04-29 11:37:28,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +46: [2023-04-29 11:37:28,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +17: [2023-04-29 11:37:28,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +41: [2023-04-29 11:37:28,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 8: [2023-04-29 11:37:28,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +61: [2023-04-29 11:37:28,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +38: [2023-04-29 11:37:28,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +38: [2023-04-29 11:37:28,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +17: [2023-04-29 11:37:28,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +54: [2023-04-29 11:37:28,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +29: [2023-04-29 11:37:28,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +36: [2023-04-29 11:37:28,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +46: [2023-04-29 11:37:28,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +21: [2023-04-29 11:37:28,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 8: [2023-04-29 11:37:28,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +46: [2023-04-29 11:37:28,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +51: [2023-04-29 11:37:28,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +41: [2023-04-29 11:37:28,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 8: [2023-04-29 11:37:28,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +63: [2023-04-29 11:37:28,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +63: [2023-04-29 11:37:28,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +63: [2023-04-29 11:37:28,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +36: [2023-04-29 11:37:28,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +63: [2023-04-29 11:37:28,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +61: [2023-04-29 11:37:28,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +61: [2023-04-29 11:37:28,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +34: [2023-04-29 11:37:28,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +38: [2023-04-29 11:37:28,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. + 6: [2023-04-29 11:37:28,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +52: [2023-04-29 11:37:28,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +52: [2023-04-29 11:37:28,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +20: [2023-04-29 11:37:28,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +17: [2023-04-29 11:37:28,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +17: [2023-04-29 11:37:28,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +17: [2023-04-29 11:37:28,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +17: [2023-04-29 11:37:28,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +47: [2023-04-29 11:37:28,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +52: [2023-04-29 11:37:28,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +38: [2023-04-29 11:37:28,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +38: [2023-04-29 11:37:28,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +52: [2023-04-29 11:37:28,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +61: [2023-04-29 11:37:28,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +36: [2023-04-29 11:37:28,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. + 0: [2023-04-29 11:37:28,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. + 0: [2023-04-29 11:37:28,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. + 0: [2023-04-29 11:37:28,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +20: [2023-04-29 11:37:28,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 0: [2023-04-29 11:37:28,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +38: [2023-04-29 11:37:28,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. + 4: [2023-04-29 11:37:28,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +21: [2023-04-29 11:37:28,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +21: [2023-04-29 11:37:28,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +52: [2023-04-29 11:37:28,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +52: [2023-04-29 11:37:28,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +20: [2023-04-29 11:37:28,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +20: [2023-04-29 11:37:28,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +21: [2023-04-29 11:37:28,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +29: [2023-04-29 11:37:28,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +29: [2023-04-29 11:37:28,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +29: [2023-04-29 11:37:28,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +52: [2023-04-29 11:37:28,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +47: [2023-04-29 11:37:28,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +47: [2023-04-29 11:37:28,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +38: [2023-04-29 11:37:28,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +39: [2023-04-29 11:37:28,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +39: [2023-04-29 11:37:28,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +45: [2023-04-29 11:37:28,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +45: [2023-04-29 11:37:28,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +47: [2023-04-29 11:37:28,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +51: [2023-04-29 11:37:28,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 6: [2023-04-29 11:37:28,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 6: [2023-04-29 11:37:28,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +45: [2023-04-29 11:37:28,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +45: [2023-04-29 11:37:28,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +52: [2023-04-29 11:37:28,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +59: [2023-04-29 11:37:28,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +59: [2023-04-29 11:37:28,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +47: [2023-04-29 11:37:28,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +36: [2023-04-29 11:37:28,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... + 6: [2023-04-29 11:37:28,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +10: [2023-04-29 11:37:28,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +10: [2023-04-29 11:37:28,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +10: [2023-04-29 11:37:28,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +45: [2023-04-29 11:37:28,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +38: [2023-04-29 11:37:28,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +39: [2023-04-29 11:37:28,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +39: [2023-04-29 11:37:28,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +10: [2023-04-29 11:37:28,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +45: [2023-04-29 11:37:28,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +45: [2023-04-29 11:37:28,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +44: [2023-04-29 11:37:28,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +43: [2023-04-29 11:37:28,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +43: [2023-04-29 11:37:28,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +45: [2023-04-29 11:37:28,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +44: [2023-04-29 11:37:28,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +47: [2023-04-29 11:37:28,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +60: [2023-04-29 11:37:28,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +45: [2023-04-29 11:37:28,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +45: [2023-04-29 11:37:28,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +45: [2023-04-29 11:37:28,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +43: [2023-04-29 11:37:28,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +43: [2023-04-29 11:37:28,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +39: [2023-04-29 11:37:28,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +39: [2023-04-29 11:37:28,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +47: [2023-04-29 11:37:28,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +44: [2023-04-29 11:37:28,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +44: [2023-04-29 11:37:28,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +60: [2023-04-29 11:37:28,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +57: [2023-04-29 11:37:28,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +57: [2023-04-29 11:37:28,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +47: [2023-04-29 11:37:28,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +60: [2023-04-29 11:37:28,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +60: [2023-04-29 11:37:28,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +60: [2023-04-29 11:37:28,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +60: [2023-04-29 11:37:28,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +60: [2023-04-29 11:37:28,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +34: [2023-04-29 11:37:28,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +34: [2023-04-29 11:37:28,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +29: [2023-04-29 11:37:28,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +45: [2023-04-29 11:37:28,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +45: [2023-04-29 11:37:28,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +45: [2023-04-29 11:37:28,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +57: [2023-04-29 11:37:28,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +47: [2023-04-29 11:37:28,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +14: [2023-04-29 11:37:28,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +14: [2023-04-29 11:37:28,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +57: [2023-04-29 11:37:28,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +45: [2023-04-29 11:37:28,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. + 4: [2023-04-29 11:37:28,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 4: [2023-04-29 11:37:28,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +14: [2023-04-29 11:37:28,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +14: [2023-04-29 11:37:28,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +59: [2023-04-29 11:37:28,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +59: [2023-04-29 11:37:28,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +34: [2023-04-29 11:37:28,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +34: [2023-04-29 11:37:28,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +34: [2023-04-29 11:37:28,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +21: [2023-04-29 11:37:28,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +34: [2023-04-29 11:37:28,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +46: [2023-04-29 11:37:28,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +46: [2023-04-29 11:37:28,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +46: [2023-04-29 11:37:28,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +39: [2023-04-29 11:37:28,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +60: [2023-04-29 11:37:28,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +51: [2023-04-29 11:37:28,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +60: [2023-04-29 11:37:28,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +60: [2023-04-29 11:37:28,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +22: [2023-04-29 11:37:28,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +22: [2023-04-29 11:37:28,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +22: [2023-04-29 11:37:28,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +22: [2023-04-29 11:37:28,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +51: [2023-04-29 11:37:28,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +47: [2023-04-29 11:37:28,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +60: [2023-04-29 11:37:28,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +39: [2023-04-29 11:37:28,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +57: [2023-04-29 11:37:28,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +57: [2023-04-29 11:37:28,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +45: [2023-04-29 11:37:28,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +46: [2023-04-29 11:37:28,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +53: [2023-04-29 11:37:28,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +53: [2023-04-29 11:37:28,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +17: [2023-04-29 11:37:28,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +22: [2023-04-29 11:37:28,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +22: [2023-04-29 11:37:28,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +34: [2023-04-29 11:37:28,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +50: [2023-04-29 11:37:28,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +50: [2023-04-29 11:37:28,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +22: [2023-04-29 11:37:28,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +20: [2023-04-29 11:37:28,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +20: [2023-04-29 11:37:28,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +22: [2023-04-29 11:37:28,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 0: [2023-04-29 11:37:28,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 0: [2023-04-29 11:37:28,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +47: [2023-04-29 11:37:28,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +57: [2023-04-29 11:37:28,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +57: [2023-04-29 11:37:28,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +34: [2023-04-29 11:37:28,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +50: [2023-04-29 11:37:28,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +57: [2023-04-29 11:37:28,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +50: [2023-04-29 11:37:28,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 0: [2023-04-29 11:37:28,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 0: [2023-04-29 11:37:28,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +29: [2023-04-29 11:37:28,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +39: [2023-04-29 11:37:28,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +53: [2023-04-29 11:37:28,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +53: [2023-04-29 11:37:28,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +17: [2023-04-29 11:37:28,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +60: [2023-04-29 11:37:28,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +47: [2023-04-29 11:37:28,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +47: [2023-04-29 11:37:28,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +11: [2023-04-29 11:37:28,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +21: [2023-04-29 11:37:28,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +43: [2023-04-29 11:37:28,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +29: [2023-04-29 11:37:28,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +29: [2023-04-29 11:37:28,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +43: [2023-04-29 11:37:28,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +57: [2023-04-29 11:37:28,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +43: [2023-04-29 11:37:28,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +39: [2023-04-29 11:37:28,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +43: [2023-04-29 11:37:28,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +50: [2023-04-29 11:37:28,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +20: [2023-04-29 11:37:28,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +20: [2023-04-29 11:37:28,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +50: [2023-04-29 11:37:28,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +10: [2023-04-29 11:37:28,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +10: [2023-04-29 11:37:28,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +21: [2023-04-29 11:37:28,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +21: [2023-04-29 11:37:28,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +50: [2023-04-29 11:37:28,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +11: [2023-04-29 11:37:28,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +57: [2023-04-29 11:37:28,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +17: [2023-04-29 11:37:28,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +11: [2023-04-29 11:37:28,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +60: [2023-04-29 11:37:28,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +10: [2023-04-29 11:37:28,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +35: [2023-04-29 11:37:28,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +39: [2023-04-29 11:37:28,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +50: [2023-04-29 11:37:28,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +59: [2023-04-29 11:37:28,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +59: [2023-04-29 11:37:28,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +17: [2023-04-29 11:37:28,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +11: [2023-04-29 11:37:28,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +57: [2023-04-29 11:37:28,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +39: [2023-04-29 11:37:28,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +10: [2023-04-29 11:37:28,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +63: [2023-04-29 11:37:28,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +63: [2023-04-29 11:37:28,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +47: [2023-04-29 11:37:28,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +63: [2023-04-29 11:37:28,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +63: [2023-04-29 11:37:28,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_32-model_01-model_states.pt. +59: [2023-04-29 11:37:28,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +59: [2023-04-29 11:37:28,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +35: [2023-04-29 11:37:28,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +60: [2023-04-29 11:37:28,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +31: [2023-04-29 11:37:28,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +60: [2023-04-29 11:37:28,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +39: [2023-04-29 11:37:28,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +14: [2023-04-29 11:37:28,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +17: [2023-04-29 11:37:28,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +43: [2023-04-29 11:37:28,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +39: [2023-04-29 11:37:28,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +38: [2023-04-29 11:37:28,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +34: [2023-04-29 11:37:28,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +43: [2023-04-29 11:37:28,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +56: [2023-04-29 11:37:28,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +60: [2023-04-29 11:37:28,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +17: [2023-04-29 11:37:28,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +57: [2023-04-29 11:37:28,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +57: [2023-04-29 11:37:28,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +17: [2023-04-29 11:37:28,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +43: [2023-04-29 11:37:28,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +57: [2023-04-29 11:37:28,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +12: [2023-04-29 11:37:28,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +12: [2023-04-29 11:37:28,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +12: [2023-04-29 11:37:28,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. + 8: [2023-04-29 11:37:28,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +27: [2023-04-29 11:37:28,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +27: [2023-04-29 11:37:28,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +36: [2023-04-29 11:37:28,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +27: [2023-04-29 11:37:28,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +27: [2023-04-29 11:37:28,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +43: [2023-04-29 11:37:28,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +12: [2023-04-29 11:37:28,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +27: [2023-04-29 11:37:28,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +27: [2023-04-29 11:37:28,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +18: [2023-04-29 11:37:28,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +18: [2023-04-29 11:37:28,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +18: [2023-04-29 11:37:28,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +18: [2023-04-29 11:37:28,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +18: [2023-04-29 11:37:28,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +28: [2023-04-29 11:37:28,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +61: [2023-04-29 11:37:28,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +61: [2023-04-29 11:37:28,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +61: [2023-04-29 11:37:28,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +61: [2023-04-29 11:37:28,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +18: [2023-04-29 11:37:28,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +18: [2023-04-29 11:37:28,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +28: [2023-04-29 11:37:28,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +28: [2023-04-29 11:37:28,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +14: [2023-04-29 11:37:28,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +14: [2023-04-29 11:37:28,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +18: [2023-04-29 11:37:28,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 4: [2023-04-29 11:37:28,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +28: [2023-04-29 11:37:28,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +27: [2023-04-29 11:37:28,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +27: [2023-04-29 11:37:28,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 4: [2023-04-29 11:37:28,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +35: [2023-04-29 11:37:28,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +34: [2023-04-29 11:37:28,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +57: [2023-04-29 11:37:28,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +14: [2023-04-29 11:37:28,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +43: [2023-04-29 11:37:28,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +43: [2023-04-29 11:37:28,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +38: [2023-04-29 11:37:28,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +17: [2023-04-29 11:37:28,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +61: [2023-04-29 11:37:28,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +18: [2023-04-29 11:37:28,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +43: [2023-04-29 11:37:28,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 8: [2023-04-29 11:37:28,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 8: [2023-04-29 11:37:28,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +31: [2023-04-29 11:37:28,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +31: [2023-04-29 11:37:28,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +31: [2023-04-29 11:37:28,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +61: [2023-04-29 11:37:28,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +27: [2023-04-29 11:37:28,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +18: [2023-04-29 11:37:28,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +18: [2023-04-29 11:37:28,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +61: [2023-04-29 11:37:28,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +28: [2023-04-29 11:37:28,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +28: [2023-04-29 11:37:28,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +27: [2023-04-29 11:37:28,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +56: [2023-04-29 11:37:28,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +56: [2023-04-29 11:37:28,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +56: [2023-04-29 11:37:28,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +28: [2023-04-29 11:37:28,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +27: [2023-04-29 11:37:28,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +61: [2023-04-29 11:37:28,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +61: [2023-04-29 11:37:28,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +43: [2023-04-29 11:37:28,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... + 4: [2023-04-29 11:37:28,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +27: [2023-04-29 11:37:28,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +36: [2023-04-29 11:37:28,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +36: [2023-04-29 11:37:28,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +38: [2023-04-29 11:37:28,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +27: [2023-04-29 11:37:28,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +27: [2023-04-29 11:37:28,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +28: [2023-04-29 11:37:28,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +38: [2023-04-29 11:37:28,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +18: [2023-04-29 11:37:28,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +27: [2023-04-29 11:37:28,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +63: [2023-04-29 11:37:28,992] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +11: [2023-04-29 11:37:28,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +39: [2023-04-29 11:37:28,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +61: [2023-04-29 11:37:28,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +27: [2023-04-29 11:37:28,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +58: [2023-04-29 11:37:28,992] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +53: [2023-04-29 11:37:28,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +18: [2023-04-29 11:37:28,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +18: [2023-04-29 11:37:28,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +35: [2023-04-29 11:37:28,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. + 8: [2023-04-29 11:37:28,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +34: [2023-04-29 11:37:28,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +18: [2023-04-29 11:37:28,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +39: [2023-04-29 11:37:28,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +18: [2023-04-29 11:37:28,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +34: [2023-04-29 11:37:28,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +58: [2023-04-29 11:37:28,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +58: [2023-04-29 11:37:28,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +47: [2023-04-29 11:37:28,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +11: [2023-04-29 11:37:28,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +14: [2023-04-29 11:37:28,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +22: [2023-04-29 11:37:28,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +22: [2023-04-29 11:37:28,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +22: [2023-04-29 11:37:28,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +14: [2023-04-29 11:37:28,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +22: [2023-04-29 11:37:28,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +56: [2023-04-29 11:37:28,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +56: [2023-04-29 11:37:28,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +53: [2023-04-29 11:37:28,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +53: [2023-04-29 11:37:28,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +63: [2023-04-29 11:37:28,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +53: [2023-04-29 11:37:28,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +47: [2023-04-29 11:37:28,999] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +58: [2023-04-29 11:37:28,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +34: [2023-04-29 11:37:29,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +34: [2023-04-29 11:37:29,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +14: [2023-04-29 11:37:29,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +52: [2023-04-29 11:37:29,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +11: [2023-04-29 11:37:29,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +56: [2023-04-29 11:37:29,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +56: [2023-04-29 11:37:29,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. + 6: [2023-04-29 11:37:29,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +23: [2023-04-29 11:37:29,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +23: [2023-04-29 11:37:29,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +23: [2023-04-29 11:37:29,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 6: [2023-04-29 11:37:29,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. + 6: [2023-04-29 11:37:29,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +23: [2023-04-29 11:37:29,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 6: [2023-04-29 11:37:29,003] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +45: [2023-04-29 11:37:29,003] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +35: [2023-04-29 11:37:29,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +56: [2023-04-29 11:37:29,004] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +38: [2023-04-29 11:37:29,004] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +40: [2023-04-29 11:37:29,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +40: [2023-04-29 11:37:29,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +40: [2023-04-29 11:37:29,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +35: [2023-04-29 11:37:29,004] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +56: [2023-04-29 11:37:29,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +40: [2023-04-29 11:37:29,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +36: [2023-04-29 11:37:29,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +61: [2023-04-29 11:37:29,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +11: [2023-04-29 11:37:29,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +17: [2023-04-29 11:37:29,006] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +52: [2023-04-29 11:37:29,006] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +52: [2023-04-29 11:37:29,006] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +52: [2023-04-29 11:37:29,006] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +12: [2023-04-29 11:37:29,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +63: [2023-04-29 11:37:29,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +17: [2023-04-29 11:37:29,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +17: [2023-04-29 11:37:29,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +23: [2023-04-29 11:37:29,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +23: [2023-04-29 11:37:29,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +63: [2023-04-29 11:37:29,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +14: [2023-04-29 11:37:29,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +23: [2023-04-29 11:37:29,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +23: [2023-04-29 11:37:29,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 8: [2023-04-29 11:37:29,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +63: [2023-04-29 11:37:29,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +63: [2023-04-29 11:37:29,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +17: [2023-04-29 11:37:29,009] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +56: [2023-04-29 11:37:29,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +56: [2023-04-29 11:37:29,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +61: [2023-04-29 11:37:29,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +31: [2023-04-29 11:37:29,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +61: [2023-04-29 11:37:29,009] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +59: [2023-04-29 11:37:29,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +59: [2023-04-29 11:37:29,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +59: [2023-04-29 11:37:29,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +40: [2023-04-29 11:37:29,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +56: [2023-04-29 11:37:29,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +59: [2023-04-29 11:37:29,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 8: [2023-04-29 11:37:29,010] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 8: [2023-04-29 11:37:29,010] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 8: [2023-04-29 11:37:29,010] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 8: [2023-04-29 11:37:29,010] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +40: [2023-04-29 11:37:29,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +40: [2023-04-29 11:37:29,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +40: [2023-04-29 11:37:29,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +34: [2023-04-29 11:37:29,012] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +12: [2023-04-29 11:37:29,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +12: [2023-04-29 11:37:29,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 8: [2023-04-29 11:37:29,012] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +61: [2023-04-29 11:37:29,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +12: [2023-04-29 11:37:29,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 4: [2023-04-29 11:37:29,013] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 4: [2023-04-29 11:37:29,013] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 8: [2023-04-29 11:37:29,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +36: [2023-04-29 11:37:29,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +59: [2023-04-29 11:37:29,013] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +61: [2023-04-29 11:37:29,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +34: [2023-04-29 11:37:29,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +59: [2023-04-29 11:37:29,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +45: [2023-04-29 11:37:29,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +61: [2023-04-29 11:37:29,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +46: [2023-04-29 11:37:29,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +35: [2023-04-29 11:37:29,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +55: [2023-04-29 11:37:29,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +55: [2023-04-29 11:37:29,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +55: [2023-04-29 11:37:29,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +55: [2023-04-29 11:37:29,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +55: [2023-04-29 11:37:29,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +55: [2023-04-29 11:37:29,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +55: [2023-04-29 11:37:29,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +55: [2023-04-29 11:37:29,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +38: [2023-04-29 11:37:29,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +31: [2023-04-29 11:37:29,019] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +45: [2023-04-29 11:37:29,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +63: [2023-04-29 11:37:29,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +31: [2023-04-29 11:37:29,019] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +63: [2023-04-29 11:37:29,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +13: [2023-04-29 11:37:29,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +13: [2023-04-29 11:37:29,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +45: [2023-04-29 11:37:29,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +13: [2023-04-29 11:37:29,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +63: [2023-04-29 11:37:29,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +36: [2023-04-29 11:37:29,019] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +36: [2023-04-29 11:37:29,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 4: [2023-04-29 11:37:29,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... + 4: [2023-04-29 11:37:29,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +22: [2023-04-29 11:37:29,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +59: [2023-04-29 11:37:29,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... + 8: [2023-04-29 11:37:29,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +56: [2023-04-29 11:37:29,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +56: [2023-04-29 11:37:29,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +46: [2023-04-29 11:37:29,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +38: [2023-04-29 11:37:29,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +59: [2023-04-29 11:37:29,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +10: [2023-04-29 11:37:29,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +10: [2023-04-29 11:37:29,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 8: [2023-04-29 11:37:29,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +38: [2023-04-29 11:37:29,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +31: [2023-04-29 11:37:29,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +63: [2023-04-29 11:37:29,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +13: [2023-04-29 11:37:29,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +34: [2023-04-29 11:37:29,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +55: [2023-04-29 11:37:29,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +10: [2023-04-29 11:37:29,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +10: [2023-04-29 11:37:29,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +56: [2023-04-29 11:37:29,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +58: [2023-04-29 11:37:29,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +58: [2023-04-29 11:37:29,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +52: [2023-04-29 11:37:29,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +22: [2023-04-29 11:37:29,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +22: [2023-04-29 11:37:29,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +55: [2023-04-29 11:37:29,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +55: [2023-04-29 11:37:29,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +55: [2023-04-29 11:37:29,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +55: [2023-04-29 11:37:29,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... + 8: [2023-04-29 11:37:29,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +55: [2023-04-29 11:37:29,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +22: [2023-04-29 11:37:29,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +55: [2023-04-29 11:37:29,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +55: [2023-04-29 11:37:29,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt... +14: [2023-04-29 11:37:29,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +34: [2023-04-29 11:37:29,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +46: [2023-04-29 11:37:29,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +14: [2023-04-29 11:37:29,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +58: [2023-04-29 11:37:29,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +35: [2023-04-29 11:37:29,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +10: [2023-04-29 11:37:29,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +46: [2023-04-29 11:37:29,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +58: [2023-04-29 11:37:29,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +10: [2023-04-29 11:37:29,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +10: [2023-04-29 11:37:29,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 0: [2023-04-29 11:37:29,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 3: [2023-04-29 11:37:29,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 3: [2023-04-29 11:37:29,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 3: [2023-04-29 11:37:29,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 6: [2023-04-29 11:37:29,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +10: [2023-04-29 11:37:29,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 3: [2023-04-29 11:37:29,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +10: [2023-04-29 11:37:29,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +50: [2023-04-29 11:37:29,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +46: [2023-04-29 11:37:29,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +14: [2023-04-29 11:37:29,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 6: [2023-04-29 11:37:29,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +45: [2023-04-29 11:37:29,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +46: [2023-04-29 11:37:29,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +10: [2023-04-29 11:37:29,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +59: [2023-04-29 11:37:29,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +57: [2023-04-29 11:37:29,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +10: [2023-04-29 11:37:29,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +52: [2023-04-29 11:37:29,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +52: [2023-04-29 11:37:29,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 6: [2023-04-29 11:37:29,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +17: [2023-04-29 11:37:29,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +22: [2023-04-29 11:37:29,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 6: [2023-04-29 11:37:29,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 0: [2023-04-29 11:37:29,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +46: [2023-04-29 11:37:29,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... + 3: [2023-04-29 11:37:29,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +36: [2023-04-29 11:37:29,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +57: [2023-04-29 11:37:29,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. + 3: [2023-04-29 11:37:29,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +17: [2023-04-29 11:37:29,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 0: [2023-04-29 11:37:29,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 0: [2023-04-29 11:37:29,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +52: [2023-04-29 11:37:29,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 3: [2023-04-29 11:37:29,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +17: [2023-04-29 11:37:29,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +17: [2023-04-29 11:37:29,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +14: [2023-04-29 11:37:29,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 0: [2023-04-29 11:37:29,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 3: [2023-04-29 11:37:29,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +59: [2023-04-29 11:37:29,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +34: [2023-04-29 11:37:29,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +11: [2023-04-29 11:37:29,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +11: [2023-04-29 11:37:29,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +11: [2023-04-29 11:37:29,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +46: [2023-04-29 11:37:29,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +11: [2023-04-29 11:37:29,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +10: [2023-04-29 11:37:29,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +59: [2023-04-29 11:37:29,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +22: [2023-04-29 11:37:29,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +57: [2023-04-29 11:37:29,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +57: [2023-04-29 11:37:29,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +31: [2023-04-29 11:37:29,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +31: [2023-04-29 11:37:29,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +31: [2023-04-29 11:37:29,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +31: [2023-04-29 11:37:29,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +49: [2023-04-29 11:37:29,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +50: [2023-04-29 11:37:29,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +49: [2023-04-29 11:37:29,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +49: [2023-04-29 11:37:29,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +50: [2023-04-29 11:37:29,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 8: [2023-04-29 11:37:29,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 0: [2023-04-29 11:37:29,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +49: [2023-04-29 11:37:29,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +34: [2023-04-29 11:37:29,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. + 0: [2023-04-29 11:37:29,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... + 8: [2023-04-29 11:37:29,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 0: [2023-04-29 11:37:29,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +13: [2023-04-29 11:37:29,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +59: [2023-04-29 11:37:29,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +50: [2023-04-29 11:37:29,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +34: [2023-04-29 11:37:29,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +57: [2023-04-29 11:37:29,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +10: [2023-04-29 11:37:29,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +49: [2023-04-29 11:37:29,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +13: [2023-04-29 11:37:29,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +10: [2023-04-29 11:37:29,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +26: [2023-04-29 11:37:29,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +45: [2023-04-29 11:37:29,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +26: [2023-04-29 11:37:29,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +26: [2023-04-29 11:37:29,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +61: [2023-04-29 11:37:29,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +49: [2023-04-29 11:37:29,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +49: [2023-04-29 11:37:29,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +26: [2023-04-29 11:37:29,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +49: [2023-04-29 11:37:29,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +27: [2023-04-29 11:37:29,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +18: [2023-04-29 11:37:29,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +14: [2023-04-29 11:37:29,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +13: [2023-04-29 11:37:29,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +13: [2023-04-29 11:37:29,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +62: [2023-04-29 11:37:29,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +62: [2023-04-29 11:37:29,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +62: [2023-04-29 11:37:29,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +62: [2023-04-29 11:37:29,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +45: [2023-04-29 11:37:29,052] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +45: [2023-04-29 11:37:29,052] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +22: [2023-04-29 11:37:29,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +34: [2023-04-29 11:37:29,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +63: [2023-04-29 11:37:29,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +63: [2023-04-29 11:37:29,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +43: [2023-04-29 11:37:29,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +10: [2023-04-29 11:37:29,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +61: [2023-04-29 11:37:29,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +39: [2023-04-29 11:37:29,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +39: [2023-04-29 11:37:29,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +27: [2023-04-29 11:37:29,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +50: [2023-04-29 11:37:29,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +14: [2023-04-29 11:37:29,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +62: [2023-04-29 11:37:29,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +10: [2023-04-29 11:37:29,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +28: [2023-04-29 11:37:29,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +28: [2023-04-29 11:37:29,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +22: [2023-04-29 11:37:29,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +57: [2023-04-29 11:37:29,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +62: [2023-04-29 11:37:29,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +39: [2023-04-29 11:37:29,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +62: [2023-04-29 11:37:29,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +57: [2023-04-29 11:37:29,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +62: [2023-04-29 11:37:29,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +23: [2023-04-29 11:37:29,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +23: [2023-04-29 11:37:29,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +27: [2023-04-29 11:37:29,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +23: [2023-04-29 11:37:29,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +23: [2023-04-29 11:37:29,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +43: [2023-04-29 11:37:29,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +61: [2023-04-29 11:37:29,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +57: [2023-04-29 11:37:29,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +53: [2023-04-29 11:37:29,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +57: [2023-04-29 11:37:29,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +57: [2023-04-29 11:37:29,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +57: [2023-04-29 11:37:29,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +24: [2023-04-29 11:37:29,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +24: [2023-04-29 11:37:29,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +43: [2023-04-29 11:37:29,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +43: [2023-04-29 11:37:29,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +39: [2023-04-29 11:37:29,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +39: [2023-04-29 11:37:29,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +43: [2023-04-29 11:37:29,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +43: [2023-04-29 11:37:29,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +43: [2023-04-29 11:37:29,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +43: [2023-04-29 11:37:29,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +27: [2023-04-29 11:37:29,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +53: [2023-04-29 11:37:29,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +24: [2023-04-29 11:37:29,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +28: [2023-04-29 11:37:29,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +24: [2023-04-29 11:37:29,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +39: [2023-04-29 11:37:29,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +61: [2023-04-29 11:37:29,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +18: [2023-04-29 11:37:29,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +18: [2023-04-29 11:37:29,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +11: [2023-04-29 11:37:29,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +11: [2023-04-29 11:37:29,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +28: [2023-04-29 11:37:29,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +53: [2023-04-29 11:37:29,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +14: [2023-04-29 11:37:29,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +53: [2023-04-29 11:37:29,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +24: [2023-04-29 11:37:29,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +11: [2023-04-29 11:37:29,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +22: [2023-04-29 11:37:29,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +57: [2023-04-29 11:37:29,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +24: [2023-04-29 11:37:29,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +11: [2023-04-29 11:37:29,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +18: [2023-04-29 11:37:29,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +31: [2023-04-29 11:37:29,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +57: [2023-04-29 11:37:29,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +57: [2023-04-29 11:37:29,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +57: [2023-04-29 11:37:29,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +23: [2023-04-29 11:37:29,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +24: [2023-04-29 11:37:29,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +14: [2023-04-29 11:37:29,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +14: [2023-04-29 11:37:29,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +31: [2023-04-29 11:37:29,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +24: [2023-04-29 11:37:29,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +22: [2023-04-29 11:37:29,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +31: [2023-04-29 11:37:29,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +31: [2023-04-29 11:37:29,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +18: [2023-04-29 11:37:29,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +53: [2023-04-29 11:37:29,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +53: [2023-04-29 11:37:29,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +40: [2023-04-29 11:37:29,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +39: [2023-04-29 11:37:29,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +12: [2023-04-29 11:37:29,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +12: [2023-04-29 11:37:29,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +53: [2023-04-29 11:37:29,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... + 7: [2023-04-29 11:37:29,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. + 7: [2023-04-29 11:37:29,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +14: [2023-04-29 11:37:29,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +12: [2023-04-29 11:37:29,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +43: [2023-04-29 11:37:29,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +43: [2023-04-29 11:37:29,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +12: [2023-04-29 11:37:29,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +43: [2023-04-29 11:37:29,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +43: [2023-04-29 11:37:29,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +27: [2023-04-29 11:37:29,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +12: [2023-04-29 11:37:29,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +61: [2023-04-29 11:37:29,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 7: [2023-04-29 11:37:29,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. + 7: [2023-04-29 11:37:29,075] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +21: [2023-04-29 11:37:29,075] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +21: [2023-04-29 11:37:29,075] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +21: [2023-04-29 11:37:29,075] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +34: [2023-04-29 11:37:29,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +14: [2023-04-29 11:37:29,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +21: [2023-04-29 11:37:29,076] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +50: [2023-04-29 11:37:29,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +50: [2023-04-29 11:37:29,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +14: [2023-04-29 11:37:29,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +53: [2023-04-29 11:37:29,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +26: [2023-04-29 11:37:29,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +26: [2023-04-29 11:37:29,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +39: [2023-04-29 11:37:29,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +34: [2023-04-29 11:37:29,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +12: [2023-04-29 11:37:29,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +12: [2023-04-29 11:37:29,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +12: [2023-04-29 11:37:29,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +50: [2023-04-29 11:37:29,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +26: [2023-04-29 11:37:29,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +26: [2023-04-29 11:37:29,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +12: [2023-04-29 11:37:29,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +23: [2023-04-29 11:37:29,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +63: [2023-04-29 11:37:29,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +22: [2023-04-29 11:37:29,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +40: [2023-04-29 11:37:29,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +40: [2023-04-29 11:37:29,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +48: [2023-04-29 11:37:29,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +48: [2023-04-29 11:37:29,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +48: [2023-04-29 11:37:29,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +40: [2023-04-29 11:37:29,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +12: [2023-04-29 11:37:29,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +48: [2023-04-29 11:37:29,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +28: [2023-04-29 11:37:29,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +22: [2023-04-29 11:37:29,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +55: [2023-04-29 11:37:29,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +28: [2023-04-29 11:37:29,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +23: [2023-04-29 11:37:29,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +23: [2023-04-29 11:37:29,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 1: [2023-04-29 11:37:29,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. + 1: [2023-04-29 11:37:29,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +24: [2023-04-29 11:37:29,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +24: [2023-04-29 11:37:29,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +63: [2023-04-29 11:37:29,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +61: [2023-04-29 11:37:29,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +24: [2023-04-29 11:37:29,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +27: [2023-04-29 11:37:29,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +24: [2023-04-29 11:37:29,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +22: [2023-04-29 11:37:29,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 1: [2023-04-29 11:37:29,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +63: [2023-04-29 11:37:29,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +48: [2023-04-29 11:37:29,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +27: [2023-04-29 11:37:29,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +57: [2023-04-29 11:37:29,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +12: [2023-04-29 11:37:29,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +12: [2023-04-29 11:37:29,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +22: [2023-04-29 11:37:29,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +12: [2023-04-29 11:37:29,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +48: [2023-04-29 11:37:29,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +29: [2023-04-29 11:37:29,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +29: [2023-04-29 11:37:29,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +29: [2023-04-29 11:37:29,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +48: [2023-04-29 11:37:29,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +29: [2023-04-29 11:37:29,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +23: [2023-04-29 11:37:29,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +48: [2023-04-29 11:37:29,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +20: [2023-04-29 11:37:29,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +20: [2023-04-29 11:37:29,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +63: [2023-04-29 11:37:29,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +43: [2023-04-29 11:37:29,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +27: [2023-04-29 11:37:29,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 1: [2023-04-29 11:37:29,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +28: [2023-04-29 11:37:29,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +55: [2023-04-29 11:37:29,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +23: [2023-04-29 11:37:29,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +20: [2023-04-29 11:37:29,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +63: [2023-04-29 11:37:29,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +20: [2023-04-29 11:37:29,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +61: [2023-04-29 11:37:29,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +63: [2023-04-29 11:37:29,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +55: [2023-04-29 11:37:29,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +55: [2023-04-29 11:37:29,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +26: [2023-04-29 11:37:29,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +26: [2023-04-29 11:37:29,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +26: [2023-04-29 11:37:29,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +26: [2023-04-29 11:37:29,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +12: [2023-04-29 11:37:29,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +12: [2023-04-29 11:37:29,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +12: [2023-04-29 11:37:29,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +61: [2023-04-29 11:37:29,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 6: [2023-04-29 11:37:29,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +63: [2023-04-29 11:37:29,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_00-model_states.pt. +23: [2023-04-29 11:37:29,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +18: [2023-04-29 11:37:29,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +18: [2023-04-29 11:37:29,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +43: [2023-04-29 11:37:29,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 5: [2023-04-29 11:37:29,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. + 5: [2023-04-29 11:37:29,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +40: [2023-04-29 11:37:29,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +48: [2023-04-29 11:37:29,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +48: [2023-04-29 11:37:29,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +23: [2023-04-29 11:37:29,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 3: [2023-04-29 11:37:29,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. + 3: [2023-04-29 11:37:29,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. + 3: [2023-04-29 11:37:29,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +48: [2023-04-29 11:37:29,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +48: [2023-04-29 11:37:29,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. + 3: [2023-04-29 11:37:29,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +28: [2023-04-29 11:37:29,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 5: [2023-04-29 11:37:29,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. + 5: [2023-04-29 11:37:29,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. + 3: [2023-04-29 11:37:29,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +10: [2023-04-29 11:37:29,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +10: [2023-04-29 11:37:29,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +15: [2023-04-29 11:37:29,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +15: [2023-04-29 11:37:29,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +15: [2023-04-29 11:37:29,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +26: [2023-04-29 11:37:29,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +23: [2023-04-29 11:37:29,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +15: [2023-04-29 11:37:29,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +26: [2023-04-29 11:37:29,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +37: [2023-04-29 11:37:29,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +37: [2023-04-29 11:37:29,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. + 7: [2023-04-29 11:37:29,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 6: [2023-04-29 11:37:29,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +37: [2023-04-29 11:37:29,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +37: [2023-04-29 11:37:29,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +37: [2023-04-29 11:37:29,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +37: [2023-04-29 11:37:29,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +37: [2023-04-29 11:37:29,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +37: [2023-04-29 11:37:29,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +26: [2023-04-29 11:37:29,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +26: [2023-04-29 11:37:29,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +21: [2023-04-29 11:37:29,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +10: [2023-04-29 11:37:29,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +63: [2023-04-29 11:37:29,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt... +22: [2023-04-29 11:37:29,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +22: [2023-04-29 11:37:29,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +18: [2023-04-29 11:37:29,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +43: [2023-04-29 11:37:29,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 3: [2023-04-29 11:37:29,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +43: [2023-04-29 11:37:29,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +21: [2023-04-29 11:37:29,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 6: [2023-04-29 11:37:29,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 6: [2023-04-29 11:37:29,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 3: [2023-04-29 11:37:29,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 7: [2023-04-29 11:37:29,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 3: [2023-04-29 11:37:29,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 7: [2023-04-29 11:37:29,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +37: [2023-04-29 11:37:29,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +15: [2023-04-29 11:37:29,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +15: [2023-04-29 11:37:29,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +15: [2023-04-29 11:37:29,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +15: [2023-04-29 11:37:29,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +30: [2023-04-29 11:37:29,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +30: [2023-04-29 11:37:29,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. + 7: [2023-04-29 11:37:29,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 7: [2023-04-29 11:37:29,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 7: [2023-04-29 11:37:29,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 7: [2023-04-29 11:37:29,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +55: [2023-04-29 11:37:29,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +10: [2023-04-29 11:37:29,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 7: [2023-04-29 11:37:29,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +30: [2023-04-29 11:37:29,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +30: [2023-04-29 11:37:29,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +22: [2023-04-29 11:37:29,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +22: [2023-04-29 11:37:29,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +37: [2023-04-29 11:37:29,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 6: [2023-04-29 11:37:29,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... + 6: [2023-04-29 11:37:29,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 6: [2023-04-29 11:37:29,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +37: [2023-04-29 11:37:29,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +23: [2023-04-29 11:37:29,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +37: [2023-04-29 11:37:29,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +21: [2023-04-29 11:37:29,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +22: [2023-04-29 11:37:29,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +21: [2023-04-29 11:37:29,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 7: [2023-04-29 11:37:29,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +19: [2023-04-29 11:37:29,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +19: [2023-04-29 11:37:29,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +49: [2023-04-29 11:37:29,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +19: [2023-04-29 11:37:29,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +19: [2023-04-29 11:37:29,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +40: [2023-04-29 11:37:29,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +15: [2023-04-29 11:37:29,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +15: [2023-04-29 11:37:29,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. + 1: [2023-04-29 11:37:29,114] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +40: [2023-04-29 11:37:29,114] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +40: [2023-04-29 11:37:29,114] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +28: [2023-04-29 11:37:29,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +28: [2023-04-29 11:37:29,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +28: [2023-04-29 11:37:29,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +28: [2023-04-29 11:37:29,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. + 6: [2023-04-29 11:37:29,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... + 7: [2023-04-29 11:37:29,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 7: [2023-04-29 11:37:29,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 7: [2023-04-29 11:37:29,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 1: [2023-04-29 11:37:29,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +23: [2023-04-29 11:37:29,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +23: [2023-04-29 11:37:29,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +20: [2023-04-29 11:37:29,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 1: [2023-04-29 11:37:29,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +20: [2023-04-29 11:37:29,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +29: [2023-04-29 11:37:29,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +24: [2023-04-29 11:37:29,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +24: [2023-04-29 11:37:29,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +22: [2023-04-29 11:37:29,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +55: [2023-04-29 11:37:29,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +15: [2023-04-29 11:37:29,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +15: [2023-04-29 11:37:29,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. + 1: [2023-04-29 11:37:29,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +29: [2023-04-29 11:37:29,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +49: [2023-04-29 11:37:29,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +49: [2023-04-29 11:37:29,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +20: [2023-04-29 11:37:29,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +49: [2023-04-29 11:37:29,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +29: [2023-04-29 11:37:29,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +24: [2023-04-29 11:37:29,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +24: [2023-04-29 11:37:29,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +62: [2023-04-29 11:37:29,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +62: [2023-04-29 11:37:29,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +55: [2023-04-29 11:37:29,123] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +20: [2023-04-29 11:37:29,123] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +29: [2023-04-29 11:37:29,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +37: [2023-04-29 11:37:29,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +54: [2023-04-29 11:37:29,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +54: [2023-04-29 11:37:29,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +54: [2023-04-29 11:37:29,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +54: [2023-04-29 11:37:29,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +55: [2023-04-29 11:37:29,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 3: [2023-04-29 11:37:29,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 3: [2023-04-29 11:37:29,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +10: [2023-04-29 11:37:29,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +48: [2023-04-29 11:37:29,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +10: [2023-04-29 11:37:29,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +48: [2023-04-29 11:37:29,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 3: [2023-04-29 11:37:29,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 3: [2023-04-29 11:37:29,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 3: [2023-04-29 11:37:29,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +10: [2023-04-29 11:37:29,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 5: [2023-04-29 11:37:29,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 5: [2023-04-29 11:37:29,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 5: [2023-04-29 11:37:29,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 5: [2023-04-29 11:37:29,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +31: [2023-04-29 11:37:29,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +62: [2023-04-29 11:37:29,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +62: [2023-04-29 11:37:29,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 3: [2023-04-29 11:37:29,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +48: [2023-04-29 11:37:29,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 3: [2023-04-29 11:37:29,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +48: [2023-04-29 11:37:29,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +30: [2023-04-29 11:37:29,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +30: [2023-04-29 11:37:29,133] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +11: [2023-04-29 11:37:29,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +11: [2023-04-29 11:37:29,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +30: [2023-04-29 11:37:29,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +10: [2023-04-29 11:37:29,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +16: [2023-04-29 11:37:29,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. + 3: [2023-04-29 11:37:29,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 2: [2023-04-29 11:37:29,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. + 2: [2023-04-29 11:37:29,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +30: [2023-04-29 11:37:29,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +16: [2023-04-29 11:37:29,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +16: [2023-04-29 11:37:29,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +16: [2023-04-29 11:37:29,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +44: [2023-04-29 11:37:29,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +44: [2023-04-29 11:37:29,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +24: [2023-04-29 11:37:29,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +24: [2023-04-29 11:37:29,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 9: [2023-04-29 11:37:29,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. + 9: [2023-04-29 11:37:29,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +31: [2023-04-29 11:37:29,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... + 2: [2023-04-29 11:37:29,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. + 2: [2023-04-29 11:37:29,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +11: [2023-04-29 11:37:29,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +11: [2023-04-29 11:37:29,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +11: [2023-04-29 11:37:29,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... + 9: [2023-04-29 11:37:29,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. + 9: [2023-04-29 11:37:29,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +33: [2023-04-29 11:37:29,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +33: [2023-04-29 11:37:29,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +11: [2023-04-29 11:37:29,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +49: [2023-04-29 11:37:29,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +54: [2023-04-29 11:37:29,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +54: [2023-04-29 11:37:29,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +44: [2023-04-29 11:37:29,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +31: [2023-04-29 11:37:29,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +31: [2023-04-29 11:37:29,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +31: [2023-04-29 11:37:29,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +54: [2023-04-29 11:37:29,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +33: [2023-04-29 11:37:29,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +44: [2023-04-29 11:37:29,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +54: [2023-04-29 11:37:29,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +33: [2023-04-29 11:37:29,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +15: [2023-04-29 11:37:29,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +28: [2023-04-29 11:37:29,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +37: [2023-04-29 11:37:29,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +28: [2023-04-29 11:37:29,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +37: [2023-04-29 11:37:29,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +37: [2023-04-29 11:37:29,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +12: [2023-04-29 11:37:29,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +12: [2023-04-29 11:37:29,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +28: [2023-04-29 11:37:29,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +11: [2023-04-29 11:37:29,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +28: [2023-04-29 11:37:29,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +19: [2023-04-29 11:37:29,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +11: [2023-04-29 11:37:29,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +12: [2023-04-29 11:37:29,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +15: [2023-04-29 11:37:29,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +26: [2023-04-29 11:37:29,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +12: [2023-04-29 11:37:29,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +24: [2023-04-29 11:37:29,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +19: [2023-04-29 11:37:29,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +54: [2023-04-29 11:37:29,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +54: [2023-04-29 11:37:29,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +62: [2023-04-29 11:37:29,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +62: [2023-04-29 11:37:29,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +31: [2023-04-29 11:37:29,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +31: [2023-04-29 11:37:29,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +31: [2023-04-29 11:37:29,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +54: [2023-04-29 11:37:29,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +15: [2023-04-29 11:37:29,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +54: [2023-04-29 11:37:29,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +33: [2023-04-29 11:37:29,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +33: [2023-04-29 11:37:29,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +19: [2023-04-29 11:37:29,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +19: [2023-04-29 11:37:29,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +49: [2023-04-29 11:37:29,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +26: [2023-04-29 11:37:29,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +15: [2023-04-29 11:37:29,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +26: [2023-04-29 11:37:29,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +33: [2023-04-29 11:37:29,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +54: [2023-04-29 11:37:29,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +58: [2023-04-29 11:37:29,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +58: [2023-04-29 11:37:29,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +58: [2023-04-29 11:37:29,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +58: [2023-04-29 11:37:29,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +49: [2023-04-29 11:37:29,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +48: [2023-04-29 11:37:29,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +33: [2023-04-29 11:37:29,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +26: [2023-04-29 11:37:29,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +33: [2023-04-29 11:37:29,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +54: [2023-04-29 11:37:29,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +54: [2023-04-29 11:37:29,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +54: [2023-04-29 11:37:29,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +26: [2023-04-29 11:37:29,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +49: [2023-04-29 11:37:29,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +33: [2023-04-29 11:37:29,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +33: [2023-04-29 11:37:29,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 2: [2023-04-29 11:37:29,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +62: [2023-04-29 11:37:29,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +23: [2023-04-29 11:37:29,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +24: [2023-04-29 11:37:29,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +16: [2023-04-29 11:37:29,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +26: [2023-04-29 11:37:29,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +21: [2023-04-29 11:37:29,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 2: [2023-04-29 11:37:29,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 2: [2023-04-29 11:37:29,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +62: [2023-04-29 11:37:29,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +24: [2023-04-29 11:37:29,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +16: [2023-04-29 11:37:29,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +44: [2023-04-29 11:37:29,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +44: [2023-04-29 11:37:29,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 9: [2023-04-29 11:37:29,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 9: [2023-04-29 11:37:29,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 9: [2023-04-29 11:37:29,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +23: [2023-04-29 11:37:29,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 7: [2023-04-29 11:37:29,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 9: [2023-04-29 11:37:29,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +24: [2023-04-29 11:37:29,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +26: [2023-04-29 11:37:29,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... + 2: [2023-04-29 11:37:29,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +33: [2023-04-29 11:37:29,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +21: [2023-04-29 11:37:29,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +16: [2023-04-29 11:37:29,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +26: [2023-04-29 11:37:29,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +26: [2023-04-29 11:37:29,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 7: [2023-04-29 11:37:29,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +23: [2023-04-29 11:37:29,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +21: [2023-04-29 11:37:29,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +48: [2023-04-29 11:37:29,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +48: [2023-04-29 11:37:29,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. + 9: [2023-04-29 11:37:29,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 9: [2023-04-29 11:37:29,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 7: [2023-04-29 11:37:29,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +26: [2023-04-29 11:37:29,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +44: [2023-04-29 11:37:29,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +16: [2023-04-29 11:37:29,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +23: [2023-04-29 11:37:29,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +37: [2023-04-29 11:37:29,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +44: [2023-04-29 11:37:29,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 9: [2023-04-29 11:37:29,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 9: [2023-04-29 11:37:29,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +21: [2023-04-29 11:37:29,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +33: [2023-04-29 11:37:29,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 9: [2023-04-29 11:37:29,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 7: [2023-04-29 11:37:29,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +23: [2023-04-29 11:37:29,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +12: [2023-04-29 11:37:29,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 9: [2023-04-29 11:37:29,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 9: [2023-04-29 11:37:29,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 9: [2023-04-29 11:37:29,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +12: [2023-04-29 11:37:29,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +23: [2023-04-29 11:37:29,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +24: [2023-04-29 11:37:29,175] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +12: [2023-04-29 11:37:29,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +33: [2023-04-29 11:37:29,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +33: [2023-04-29 11:37:29,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +13: [2023-04-29 11:37:29,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +13: [2023-04-29 11:37:29,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +13: [2023-04-29 11:37:29,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +33: [2023-04-29 11:37:29,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +13: [2023-04-29 11:37:29,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +13: [2023-04-29 11:37:29,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +13: [2023-04-29 11:37:29,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +13: [2023-04-29 11:37:29,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +46: [2023-04-29 11:37:29,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +46: [2023-04-29 11:37:29,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +46: [2023-04-29 11:37:29,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +13: [2023-04-29 11:37:29,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +48: [2023-04-29 11:37:29,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +46: [2023-04-29 11:37:29,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +29: [2023-04-29 11:37:29,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +12: [2023-04-29 11:37:29,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +23: [2023-04-29 11:37:29,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... + 7: [2023-04-29 11:37:29,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +19: [2023-04-29 11:37:29,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +19: [2023-04-29 11:37:29,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +19: [2023-04-29 11:37:29,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +19: [2023-04-29 11:37:29,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +26: [2023-04-29 11:37:29,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +48: [2023-04-29 11:37:29,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +26: [2023-04-29 11:37:29,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +13: [2023-04-29 11:37:29,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +23: [2023-04-29 11:37:29,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... + 7: [2023-04-29 11:37:29,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +13: [2023-04-29 11:37:29,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +13: [2023-04-29 11:37:29,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +46: [2023-04-29 11:37:29,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +29: [2023-04-29 11:37:29,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +46: [2023-04-29 11:37:29,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +46: [2023-04-29 11:37:29,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +46: [2023-04-29 11:37:29,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 7: [2023-04-29 11:37:29,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 7: [2023-04-29 11:37:29,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +15: [2023-04-29 11:37:29,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +15: [2023-04-29 11:37:29,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +15: [2023-04-29 11:37:29,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +29: [2023-04-29 11:37:29,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +13: [2023-04-29 11:37:29,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +19: [2023-04-29 11:37:29,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +13: [2023-04-29 11:37:29,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +20: [2023-04-29 11:37:29,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +20: [2023-04-29 11:37:29,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +58: [2023-04-29 11:37:29,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +13: [2023-04-29 11:37:29,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +13: [2023-04-29 11:37:29,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +13: [2023-04-29 11:37:29,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +58: [2023-04-29 11:37:29,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +58: [2023-04-29 11:37:29,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +19: [2023-04-29 11:37:29,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +58: [2023-04-29 11:37:29,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +19: [2023-04-29 11:37:29,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +21: [2023-04-29 11:37:29,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +29: [2023-04-29 11:37:29,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +19: [2023-04-29 11:37:29,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 7: [2023-04-29 11:37:29,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +21: [2023-04-29 11:37:29,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +29: [2023-04-29 11:37:29,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +20: [2023-04-29 11:37:29,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 3: [2023-04-29 11:37:29,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 3: [2023-04-29 11:37:29,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +29: [2023-04-29 11:37:29,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +37: [2023-04-29 11:37:29,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +26: [2023-04-29 11:37:29,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +20: [2023-04-29 11:37:29,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +24: [2023-04-29 11:37:29,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +20: [2023-04-29 11:37:29,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +20: [2023-04-29 11:37:29,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +24: [2023-04-29 11:37:29,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 7: [2023-04-29 11:37:29,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 7: [2023-04-29 11:37:29,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 7: [2023-04-29 11:37:29,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +26: [2023-04-29 11:37:29,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +29: [2023-04-29 11:37:29,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +21: [2023-04-29 11:37:29,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +30: [2023-04-29 11:37:29,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +37: [2023-04-29 11:37:29,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 3: [2023-04-29 11:37:29,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +29: [2023-04-29 11:37:29,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +37: [2023-04-29 11:37:29,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... + 3: [2023-04-29 11:37:29,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... + 3: [2023-04-29 11:37:29,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +20: [2023-04-29 11:37:29,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +48: [2023-04-29 11:37:29,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +15: [2023-04-29 11:37:29,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +30: [2023-04-29 11:37:29,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +21: [2023-04-29 11:37:29,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... + 3: [2023-04-29 11:37:29,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +24: [2023-04-29 11:37:29,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +48: [2023-04-29 11:37:29,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +20: [2023-04-29 11:37:29,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... + 3: [2023-04-29 11:37:29,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +30: [2023-04-29 11:37:29,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +30: [2023-04-29 11:37:29,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... + 3: [2023-04-29 11:37:29,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +30: [2023-04-29 11:37:29,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +30: [2023-04-29 11:37:29,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +24: [2023-04-29 11:37:29,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +24: [2023-04-29 11:37:29,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +28: [2023-04-29 11:37:29,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +24: [2023-04-29 11:37:29,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +48: [2023-04-29 11:37:29,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +30: [2023-04-29 11:37:29,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +30: [2023-04-29 11:37:29,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +26: [2023-04-29 11:37:29,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +26: [2023-04-29 11:37:29,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 7: [2023-04-29 11:37:29,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +24: [2023-04-29 11:37:29,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +28: [2023-04-29 11:37:29,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +24: [2023-04-29 11:37:29,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +24: [2023-04-29 11:37:29,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +19: [2023-04-29 11:37:29,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +37: [2023-04-29 11:37:29,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +37: [2023-04-29 11:37:29,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +37: [2023-04-29 11:37:29,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +54: [2023-04-29 11:37:29,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +28: [2023-04-29 11:37:29,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +28: [2023-04-29 11:37:29,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +28: [2023-04-29 11:37:29,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +48: [2023-04-29 11:37:29,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +48: [2023-04-29 11:37:29,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +48: [2023-04-29 11:37:29,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +15: [2023-04-29 11:37:29,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +48: [2023-04-29 11:37:29,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +15: [2023-04-29 11:37:29,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +15: [2023-04-29 11:37:29,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +44: [2023-04-29 11:37:29,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +44: [2023-04-29 11:37:29,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +19: [2023-04-29 11:37:29,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +54: [2023-04-29 11:37:29,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +54: [2023-04-29 11:37:29,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +15: [2023-04-29 11:37:29,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +44: [2023-04-29 11:37:29,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +44: [2023-04-29 11:37:29,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +28: [2023-04-29 11:37:29,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +28: [2023-04-29 11:37:29,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +48: [2023-04-29 11:37:29,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +48: [2023-04-29 11:37:29,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +48: [2023-04-29 11:37:29,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +48: [2023-04-29 11:37:29,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +28: [2023-04-29 11:37:29,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... + 7: [2023-04-29 11:37:29,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 7: [2023-04-29 11:37:29,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +44: [2023-04-29 11:37:29,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +44: [2023-04-29 11:37:29,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +19: [2023-04-29 11:37:29,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +19: [2023-04-29 11:37:29,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 7: [2023-04-29 11:37:29,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +33: [2023-04-29 11:37:29,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +33: [2023-04-29 11:37:29,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +33: [2023-04-29 11:37:29,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +33: [2023-04-29 11:37:29,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +54: [2023-04-29 11:37:29,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +44: [2023-04-29 11:37:29,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +44: [2023-04-29 11:37:29,229] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +15: [2023-04-29 11:37:29,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +54: [2023-04-29 11:37:29,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +54: [2023-04-29 11:37:29,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +54: [2023-04-29 11:37:29,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +15: [2023-04-29 11:37:29,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +33: [2023-04-29 11:37:29,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +44: [2023-04-29 11:37:29,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +44: [2023-04-29 11:37:29,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +19: [2023-04-29 11:37:29,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +19: [2023-04-29 11:37:29,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +19: [2023-04-29 11:37:29,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +15: [2023-04-29 11:37:29,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +54: [2023-04-29 11:37:29,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +44: [2023-04-29 11:37:29,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +44: [2023-04-29 11:37:29,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +44: [2023-04-29 11:37:29,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +54: [2023-04-29 11:37:29,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +53: [2023-04-29 11:37:29,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +53: [2023-04-29 11:37:29,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +54: [2023-04-29 11:37:29,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +53: [2023-04-29 11:37:29,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +19: [2023-04-29 11:37:29,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +53: [2023-04-29 11:37:29,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +15: [2023-04-29 11:37:29,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +15: [2023-04-29 11:37:29,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +15: [2023-04-29 11:37:29,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +54: [2023-04-29 11:37:29,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 9: [2023-04-29 11:37:29,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +19: [2023-04-29 11:37:29,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 5: [2023-04-29 11:37:29,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 5: [2023-04-29 11:37:29,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 5: [2023-04-29 11:37:29,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 5: [2023-04-29 11:37:29,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 5: [2023-04-29 11:37:29,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 5: [2023-04-29 11:37:29,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 5: [2023-04-29 11:37:29,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 5: [2023-04-29 11:37:29,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 9: [2023-04-29 11:37:29,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 9: [2023-04-29 11:37:29,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 9: [2023-04-29 11:37:29,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +13: [2023-04-29 11:37:29,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +13: [2023-04-29 11:37:29,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +44: [2023-04-29 11:37:29,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +53: [2023-04-29 11:37:29,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +44: [2023-04-29 11:37:29,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +53: [2023-04-29 11:37:29,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +53: [2023-04-29 11:37:29,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +54: [2023-04-29 11:37:29,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +15: [2023-04-29 11:37:29,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +15: [2023-04-29 11:37:29,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +33: [2023-04-29 11:37:29,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +54: [2023-04-29 11:37:29,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +46: [2023-04-29 11:37:29,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +37: [2023-04-29 11:37:29,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +53: [2023-04-29 11:37:29,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +37: [2023-04-29 11:37:29,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 9: [2023-04-29 11:37:29,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 9: [2023-04-29 11:37:29,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 9: [2023-04-29 11:37:29,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 9: [2023-04-29 11:37:29,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +32: [2023-04-29 11:37:29,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +32: [2023-04-29 11:37:29,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +32: [2023-04-29 11:37:29,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +54: [2023-04-29 11:37:29,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... + 5: [2023-04-29 11:37:29,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +32: [2023-04-29 11:37:29,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 5: [2023-04-29 11:37:29,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... + 5: [2023-04-29 11:37:29,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +37: [2023-04-29 11:37:29,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 5: [2023-04-29 11:37:29,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +25: [2023-04-29 11:37:29,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +25: [2023-04-29 11:37:29,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. + 9: [2023-04-29 11:37:29,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... + 9: [2023-04-29 11:37:29,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +37: [2023-04-29 11:37:29,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +37: [2023-04-29 11:37:29,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 9: [2023-04-29 11:37:29,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +33: [2023-04-29 11:37:29,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +33: [2023-04-29 11:37:29,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 5: [2023-04-29 11:37:29,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +33: [2023-04-29 11:37:29,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +25: [2023-04-29 11:37:29,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +25: [2023-04-29 11:37:29,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_08-model_01-model_states.pt. +33: [2023-04-29 11:37:29,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +13: [2023-04-29 11:37:29,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +44: [2023-04-29 11:37:29,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +37: [2023-04-29 11:37:29,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 5: [2023-04-29 11:37:29,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 5: [2023-04-29 11:37:29,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +13: [2023-04-29 11:37:29,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 5: [2023-04-29 11:37:29,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +58: [2023-04-29 11:37:29,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +32: [2023-04-29 11:37:29,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +33: [2023-04-29 11:37:29,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +33: [2023-04-29 11:37:29,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +37: [2023-04-29 11:37:29,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +32: [2023-04-29 11:37:29,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +46: [2023-04-29 11:37:29,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +32: [2023-04-29 11:37:29,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +37: [2023-04-29 11:37:29,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... + 9: [2023-04-29 11:37:29,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +19: [2023-04-29 11:37:29,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +54: [2023-04-29 11:37:29,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +58: [2023-04-29 11:37:29,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +54: [2023-04-29 11:37:29,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +32: [2023-04-29 11:37:29,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +46: [2023-04-29 11:37:29,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +46: [2023-04-29 11:37:29,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +33: [2023-04-29 11:37:29,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +33: [2023-04-29 11:37:29,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +33: [2023-04-29 11:37:29,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +19: [2023-04-29 11:37:29,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +52: [2023-04-29 11:37:29,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +52: [2023-04-29 11:37:29,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +37: [2023-04-29 11:37:29,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +58: [2023-04-29 11:37:29,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +58: [2023-04-29 11:37:29,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +58: [2023-04-29 11:37:29,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +58: [2023-04-29 11:37:29,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +19: [2023-04-29 11:37:29,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +52: [2023-04-29 11:37:29,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +52: [2023-04-29 11:37:29,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +32: [2023-04-29 11:37:29,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +32: [2023-04-29 11:37:29,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +51: [2023-04-29 11:37:29,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +51: [2023-04-29 11:37:29,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +51: [2023-04-29 11:37:29,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +51: [2023-04-29 11:37:29,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +19: [2023-04-29 11:37:29,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +52: [2023-04-29 11:37:29,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +52: [2023-04-29 11:37:29,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +58: [2023-04-29 11:37:29,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +58: [2023-04-29 11:37:29,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +52: [2023-04-29 11:37:29,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +32: [2023-04-29 11:37:29,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +32: [2023-04-29 11:37:29,272] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +52: [2023-04-29 11:37:29,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +13: [2023-04-29 11:37:29,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +13: [2023-04-29 11:37:29,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +33: [2023-04-29 11:37:29,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 9: [2023-04-29 11:37:29,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +40: [2023-04-29 11:37:29,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +40: [2023-04-29 11:37:29,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +40: [2023-04-29 11:37:29,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +40: [2023-04-29 11:37:29,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +46: [2023-04-29 11:37:29,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +25: [2023-04-29 11:37:29,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +51: [2023-04-29 11:37:29,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +51: [2023-04-29 11:37:29,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +51: [2023-04-29 11:37:29,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +51: [2023-04-29 11:37:29,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +25: [2023-04-29 11:37:29,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +25: [2023-04-29 11:37:29,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +25: [2023-04-29 11:37:29,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +13: [2023-04-29 11:37:29,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +13: [2023-04-29 11:37:29,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 9: [2023-04-29 11:37:29,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +42: [2023-04-29 11:37:29,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +42: [2023-04-29 11:37:29,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +42: [2023-04-29 11:37:29,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +44: [2023-04-29 11:37:29,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +42: [2023-04-29 11:37:29,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +51: [2023-04-29 11:37:29,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +51: [2023-04-29 11:37:29,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +51: [2023-04-29 11:37:29,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. + 9: [2023-04-29 11:37:29,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +51: [2023-04-29 11:37:29,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. + 9: [2023-04-29 11:37:29,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +41: [2023-04-29 11:37:29,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +41: [2023-04-29 11:37:29,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +50: [2023-04-29 11:37:29,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +50: [2023-04-29 11:37:29,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +41: [2023-04-29 11:37:29,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +50: [2023-04-29 11:37:29,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +41: [2023-04-29 11:37:29,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +58: [2023-04-29 11:37:29,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +58: [2023-04-29 11:37:29,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +58: [2023-04-29 11:37:29,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +58: [2023-04-29 11:37:29,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +50: [2023-04-29 11:37:29,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +19: [2023-04-29 11:37:29,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +46: [2023-04-29 11:37:29,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +46: [2023-04-29 11:37:29,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +41: [2023-04-29 11:37:29,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +58: [2023-04-29 11:37:29,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +58: [2023-04-29 11:37:29,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +58: [2023-04-29 11:37:29,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +58: [2023-04-29 11:37:29,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +46: [2023-04-29 11:37:29,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +19: [2023-04-29 11:37:29,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +41: [2023-04-29 11:37:29,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +41: [2023-04-29 11:37:29,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +44: [2023-04-29 11:37:29,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +44: [2023-04-29 11:37:29,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +44: [2023-04-29 11:37:29,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +41: [2023-04-29 11:37:29,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +59: [2023-04-29 11:37:29,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +59: [2023-04-29 11:37:29,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +59: [2023-04-29 11:37:29,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +32: [2023-04-29 11:37:29,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +59: [2023-04-29 11:37:29,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +52: [2023-04-29 11:37:29,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +52: [2023-04-29 11:37:29,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +52: [2023-04-29 11:37:29,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +52: [2023-04-29 11:37:29,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +19: [2023-04-29 11:37:29,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +59: [2023-04-29 11:37:29,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +59: [2023-04-29 11:37:29,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +59: [2023-04-29 11:37:29,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +59: [2023-04-29 11:37:29,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +40: [2023-04-29 11:37:29,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +40: [2023-04-29 11:37:29,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +40: [2023-04-29 11:37:29,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +32: [2023-04-29 11:37:29,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +40: [2023-04-29 11:37:29,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +44: [2023-04-29 11:37:29,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +32: [2023-04-29 11:37:29,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +32: [2023-04-29 11:37:29,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +51: [2023-04-29 11:37:29,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +51: [2023-04-29 11:37:29,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +50: [2023-04-29 11:37:29,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +50: [2023-04-29 11:37:29,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 5: [2023-04-29 11:37:29,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +42: [2023-04-29 11:37:29,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +53: [2023-04-29 11:37:29,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +42: [2023-04-29 11:37:29,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +49: [2023-04-29 11:37:29,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +42: [2023-04-29 11:37:29,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +49: [2023-04-29 11:37:29,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +42: [2023-04-29 11:37:29,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +49: [2023-04-29 11:37:29,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +49: [2023-04-29 11:37:29,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +51: [2023-04-29 11:37:29,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +51: [2023-04-29 11:37:29,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +30: [2023-04-29 11:37:29,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +30: [2023-04-29 11:37:29,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +30: [2023-04-29 11:37:29,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +30: [2023-04-29 11:37:29,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +50: [2023-04-29 11:37:29,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +53: [2023-04-29 11:37:29,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +53: [2023-04-29 11:37:29,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +53: [2023-04-29 11:37:29,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +44: [2023-04-29 11:37:29,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +44: [2023-04-29 11:37:29,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +50: [2023-04-29 11:37:29,326] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +30: [2023-04-29 11:37:29,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +50: [2023-04-29 11:37:29,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +50: [2023-04-29 11:37:29,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +30: [2023-04-29 11:37:29,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +50: [2023-04-29 11:37:29,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +50: [2023-04-29 11:37:29,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +30: [2023-04-29 11:37:29,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +30: [2023-04-29 11:37:29,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 5: [2023-04-29 11:37:29,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +44: [2023-04-29 11:37:29,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +62: [2023-04-29 11:37:29,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +62: [2023-04-29 11:37:29,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +62: [2023-04-29 11:37:29,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +62: [2023-04-29 11:37:29,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +50: [2023-04-29 11:37:29,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 1: [2023-04-29 11:37:29,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 1: [2023-04-29 11:37:29,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 1: [2023-04-29 11:37:29,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 1: [2023-04-29 11:37:29,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 1: [2023-04-29 11:37:29,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 1: [2023-04-29 11:37:29,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 1: [2023-04-29 11:37:29,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 1: [2023-04-29 11:37:29,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +32: [2023-04-29 11:37:29,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 5: [2023-04-29 11:37:29,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 5: [2023-04-29 11:37:29,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +52: [2023-04-29 11:37:29,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +50: [2023-04-29 11:37:29,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +52: [2023-04-29 11:37:29,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +50: [2023-04-29 11:37:29,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 1: [2023-04-29 11:37:29,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 1: [2023-04-29 11:37:29,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 1: [2023-04-29 11:37:29,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +38: [2023-04-29 11:37:29,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +38: [2023-04-29 11:37:29,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 1: [2023-04-29 11:37:29,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +52: [2023-04-29 11:37:29,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +50: [2023-04-29 11:37:29,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 1: [2023-04-29 11:37:29,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +32: [2023-04-29 11:37:29,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 1: [2023-04-29 11:37:29,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 1: [2023-04-29 11:37:29,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... + 1: [2023-04-29 11:37:29,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +38: [2023-04-29 11:37:29,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +35: [2023-04-29 11:37:29,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +35: [2023-04-29 11:37:29,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +35: [2023-04-29 11:37:29,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +38: [2023-04-29 11:37:29,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +35: [2023-04-29 11:37:29,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +53: [2023-04-29 11:37:29,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +52: [2023-04-29 11:37:29,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +39: [2023-04-29 11:37:29,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +39: [2023-04-29 11:37:29,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +32: [2023-04-29 11:37:29,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +52: [2023-04-29 11:37:29,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +38: [2023-04-29 11:37:29,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +38: [2023-04-29 11:37:29,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 5: [2023-04-29 11:37:29,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +38: [2023-04-29 11:37:29,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +38: [2023-04-29 11:37:29,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +39: [2023-04-29 11:37:29,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +38: [2023-04-29 11:37:29,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +39: [2023-04-29 11:37:29,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +35: [2023-04-29 11:37:29,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +49: [2023-04-29 11:37:29,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +60: [2023-04-29 11:37:29,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +60: [2023-04-29 11:37:29,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +49: [2023-04-29 11:37:29,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +38: [2023-04-29 11:37:29,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +52: [2023-04-29 11:37:29,349] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +49: [2023-04-29 11:37:29,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +39: [2023-04-29 11:37:29,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +39: [2023-04-29 11:37:29,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +35: [2023-04-29 11:37:29,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +35: [2023-04-29 11:37:29,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +39: [2023-04-29 11:37:29,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +60: [2023-04-29 11:37:29,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +60: [2023-04-29 11:37:29,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +35: [2023-04-29 11:37:29,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +49: [2023-04-29 11:37:29,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +60: [2023-04-29 11:37:29,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +39: [2023-04-29 11:37:29,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +42: [2023-04-29 11:37:29,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +42: [2023-04-29 11:37:29,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +42: [2023-04-29 11:37:29,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +38: [2023-04-29 11:37:29,354] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +38: [2023-04-29 11:37:29,354] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +41: [2023-04-29 11:37:29,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +60: [2023-04-29 11:37:29,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +42: [2023-04-29 11:37:29,354] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +32: [2023-04-29 11:37:29,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +52: [2023-04-29 11:37:29,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +59: [2023-04-29 11:37:29,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +40: [2023-04-29 11:37:29,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +40: [2023-04-29 11:37:29,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +40: [2023-04-29 11:37:29,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +53: [2023-04-29 11:37:29,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +40: [2023-04-29 11:37:29,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +53: [2023-04-29 11:37:29,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +62: [2023-04-29 11:37:29,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +62: [2023-04-29 11:37:29,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +63: [2023-04-29 11:37:29,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +63: [2023-04-29 11:37:29,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +63: [2023-04-29 11:37:29,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +63: [2023-04-29 11:37:29,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +60: [2023-04-29 11:37:29,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +60: [2023-04-29 11:37:29,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +42: [2023-04-29 11:37:29,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +42: [2023-04-29 11:37:29,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +42: [2023-04-29 11:37:29,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +53: [2023-04-29 11:37:29,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +40: [2023-04-29 11:37:29,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +58: [2023-04-29 11:37:29,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +58: [2023-04-29 11:37:29,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +42: [2023-04-29 11:37:29,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +62: [2023-04-29 11:37:29,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +63: [2023-04-29 11:37:29,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +52: [2023-04-29 11:37:29,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +56: [2023-04-29 11:37:29,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +56: [2023-04-29 11:37:29,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +56: [2023-04-29 11:37:29,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +56: [2023-04-29 11:37:29,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 5: [2023-04-29 11:37:29,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +63: [2023-04-29 11:37:29,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +36: [2023-04-29 11:37:29,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +36: [2023-04-29 11:37:29,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +36: [2023-04-29 11:37:29,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +63: [2023-04-29 11:37:29,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +36: [2023-04-29 11:37:29,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +62: [2023-04-29 11:37:29,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +63: [2023-04-29 11:37:29,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +40: [2023-04-29 11:37:29,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +40: [2023-04-29 11:37:29,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +40: [2023-04-29 11:37:29,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +52: [2023-04-29 11:37:29,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +58: [2023-04-29 11:37:29,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +58: [2023-04-29 11:37:29,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +59: [2023-04-29 11:37:29,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +59: [2023-04-29 11:37:29,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +56: [2023-04-29 11:37:29,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +56: [2023-04-29 11:37:29,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +56: [2023-04-29 11:37:29,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 5: [2023-04-29 11:37:29,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +46: [2023-04-29 11:37:29,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +46: [2023-04-29 11:37:29,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +56: [2023-04-29 11:37:29,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +32: [2023-04-29 11:37:29,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 5: [2023-04-29 11:37:29,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +62: [2023-04-29 11:37:29,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +62: [2023-04-29 11:37:29,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +36: [2023-04-29 11:37:29,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +36: [2023-04-29 11:37:29,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +32: [2023-04-29 11:37:29,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +41: [2023-04-29 11:37:29,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +41: [2023-04-29 11:37:29,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +41: [2023-04-29 11:37:29,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +36: [2023-04-29 11:37:29,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +62: [2023-04-29 11:37:29,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +36: [2023-04-29 11:37:29,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +40: [2023-04-29 11:37:29,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +62: [2023-04-29 11:37:29,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +51: [2023-04-29 11:37:29,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +46: [2023-04-29 11:37:29,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +46: [2023-04-29 11:37:29,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +50: [2023-04-29 11:37:29,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +40: [2023-04-29 11:37:29,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +38: [2023-04-29 11:37:29,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +32: [2023-04-29 11:37:29,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +38: [2023-04-29 11:37:29,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +40: [2023-04-29 11:37:29,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +62: [2023-04-29 11:37:29,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +62: [2023-04-29 11:37:29,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +52: [2023-04-29 11:37:29,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +25: [2023-04-29 11:37:29,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +25: [2023-04-29 11:37:29,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +25: [2023-04-29 11:37:29,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +25: [2023-04-29 11:37:29,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +25: [2023-04-29 11:37:29,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +59: [2023-04-29 11:37:29,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +25: [2023-04-29 11:37:29,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +25: [2023-04-29 11:37:29,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +32: [2023-04-29 11:37:29,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +41: [2023-04-29 11:37:29,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +25: [2023-04-29 11:37:29,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +51: [2023-04-29 11:37:29,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +50: [2023-04-29 11:37:29,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +51: [2023-04-29 11:37:29,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +51: [2023-04-29 11:37:29,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +51: [2023-04-29 11:37:29,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +40: [2023-04-29 11:37:29,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +61: [2023-04-29 11:37:29,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +61: [2023-04-29 11:37:29,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +59: [2023-04-29 11:37:29,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +50: [2023-04-29 11:37:29,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +51: [2023-04-29 11:37:29,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +25: [2023-04-29 11:37:29,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +25: [2023-04-29 11:37:29,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +52: [2023-04-29 11:37:29,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +51: [2023-04-29 11:37:29,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +25: [2023-04-29 11:37:29,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +25: [2023-04-29 11:37:29,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +32: [2023-04-29 11:37:29,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +25: [2023-04-29 11:37:29,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +61: [2023-04-29 11:37:29,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +42: [2023-04-29 11:37:29,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +32: [2023-04-29 11:37:29,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +61: [2023-04-29 11:37:29,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +25: [2023-04-29 11:37:29,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +25: [2023-04-29 11:37:29,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +62: [2023-04-29 11:37:29,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +62: [2023-04-29 11:37:29,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +51: [2023-04-29 11:37:29,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +25: [2023-04-29 11:37:29,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +50: [2023-04-29 11:37:29,389] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +38: [2023-04-29 11:37:29,389] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +32: [2023-04-29 11:37:29,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +42: [2023-04-29 11:37:29,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +50: [2023-04-29 11:37:29,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +58: [2023-04-29 11:37:29,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +58: [2023-04-29 11:37:29,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +40: [2023-04-29 11:37:29,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +38: [2023-04-29 11:37:29,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +30: [2023-04-29 11:37:29,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +32: [2023-04-29 11:37:29,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +42: [2023-04-29 11:37:29,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +46: [2023-04-29 11:37:29,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +35: [2023-04-29 11:37:29,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +35: [2023-04-29 11:37:29,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +47: [2023-04-29 11:37:29,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +47: [2023-04-29 11:37:29,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +47: [2023-04-29 11:37:29,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +35: [2023-04-29 11:37:29,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +47: [2023-04-29 11:37:29,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +35: [2023-04-29 11:37:29,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +21: [2023-04-29 11:37:29,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +21: [2023-04-29 11:37:29,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +21: [2023-04-29 11:37:29,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +45: [2023-04-29 11:37:29,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +21: [2023-04-29 11:37:29,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +45: [2023-04-29 11:37:29,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +45: [2023-04-29 11:37:29,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +46: [2023-04-29 11:37:29,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +52: [2023-04-29 11:37:29,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +45: [2023-04-29 11:37:29,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +42: [2023-04-29 11:37:29,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +58: [2023-04-29 11:37:29,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +40: [2023-04-29 11:37:29,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 1: [2023-04-29 11:37:29,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +58: [2023-04-29 11:37:29,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +59: [2023-04-29 11:37:29,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +59: [2023-04-29 11:37:29,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +42: [2023-04-29 11:37:29,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +32: [2023-04-29 11:37:29,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +32: [2023-04-29 11:37:29,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +30: [2023-04-29 11:37:29,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +30: [2023-04-29 11:37:29,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +40: [2023-04-29 11:37:29,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +30: [2023-04-29 11:37:29,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +45: [2023-04-29 11:37:29,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +21: [2023-04-29 11:37:29,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +45: [2023-04-29 11:37:29,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +46: [2023-04-29 11:37:29,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +45: [2023-04-29 11:37:29,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +42: [2023-04-29 11:37:29,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +45: [2023-04-29 11:37:29,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +21: [2023-04-29 11:37:29,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 1: [2023-04-29 11:37:29,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +21: [2023-04-29 11:37:29,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +21: [2023-04-29 11:37:29,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +41: [2023-04-29 11:37:29,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +46: [2023-04-29 11:37:29,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +42: [2023-04-29 11:37:29,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +40: [2023-04-29 11:37:29,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +42: [2023-04-29 11:37:29,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... + 1: [2023-04-29 11:37:29,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +41: [2023-04-29 11:37:29,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +41: [2023-04-29 11:37:29,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +32: [2023-04-29 11:37:29,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +32: [2023-04-29 11:37:29,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... + 1: [2023-04-29 11:37:29,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +49: [2023-04-29 11:37:29,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +52: [2023-04-29 11:37:29,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +50: [2023-04-29 11:37:29,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +59: [2023-04-29 11:37:29,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +51: [2023-04-29 11:37:29,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +61: [2023-04-29 11:37:29,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +61: [2023-04-29 11:37:29,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +61: [2023-04-29 11:37:29,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +39: [2023-04-29 11:37:29,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +52: [2023-04-29 11:37:29,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +49: [2023-04-29 11:37:29,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... + 2: [2023-04-29 11:37:29,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +50: [2023-04-29 11:37:29,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 2: [2023-04-29 11:37:29,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 2: [2023-04-29 11:37:29,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 2: [2023-04-29 11:37:29,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 2: [2023-04-29 11:37:29,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 2: [2023-04-29 11:37:29,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 2: [2023-04-29 11:37:29,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 2: [2023-04-29 11:37:29,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +39: [2023-04-29 11:37:29,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +61: [2023-04-29 11:37:29,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +39: [2023-04-29 11:37:29,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +60: [2023-04-29 11:37:29,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +39: [2023-04-29 11:37:29,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +30: [2023-04-29 11:37:29,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +51: [2023-04-29 11:37:29,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +35: [2023-04-29 11:37:29,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +38: [2023-04-29 11:37:29,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +50: [2023-04-29 11:37:29,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +49: [2023-04-29 11:37:29,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 2: [2023-04-29 11:37:29,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +52: [2023-04-29 11:37:29,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +49: [2023-04-29 11:37:29,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +49: [2023-04-29 11:37:29,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 2: [2023-04-29 11:37:29,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... + 2: [2023-04-29 11:37:29,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 2: [2023-04-29 11:37:29,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +51: [2023-04-29 11:37:29,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +51: [2023-04-29 11:37:29,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 2: [2023-04-29 11:37:29,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +47: [2023-04-29 11:37:29,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 2: [2023-04-29 11:37:29,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 1: [2023-04-29 11:37:29,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +47: [2023-04-29 11:37:29,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 2: [2023-04-29 11:37:29,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... + 2: [2023-04-29 11:37:29,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +63: [2023-04-29 11:37:29,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +52: [2023-04-29 11:37:29,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +49: [2023-04-29 11:37:29,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +50: [2023-04-29 11:37:29,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +50: [2023-04-29 11:37:29,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +63: [2023-04-29 11:37:29,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +40: [2023-04-29 11:37:29,425] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +35: [2023-04-29 11:37:29,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +51: [2023-04-29 11:37:29,425] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +35: [2023-04-29 11:37:29,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +35: [2023-04-29 11:37:29,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +51: [2023-04-29 11:37:29,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +52: [2023-04-29 11:37:29,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +56: [2023-04-29 11:37:29,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +56: [2023-04-29 11:37:29,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 0: [2023-04-29 11:37:29,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 0: [2023-04-29 11:37:29,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 0: [2023-04-29 11:37:29,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +47: [2023-04-29 11:37:29,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +47: [2023-04-29 11:37:29,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +30: [2023-04-29 11:37:29,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +30: [2023-04-29 11:37:29,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +50: [2023-04-29 11:37:29,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. + 0: [2023-04-29 11:37:29,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +35: [2023-04-29 11:37:29,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 1: [2023-04-29 11:37:29,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +50: [2023-04-29 11:37:29,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +62: [2023-04-29 11:37:29,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +62: [2023-04-29 11:37:29,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +42: [2023-04-29 11:37:29,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +42: [2023-04-29 11:37:29,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +49: [2023-04-29 11:37:29,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +42: [2023-04-29 11:37:29,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +52: [2023-04-29 11:37:29,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +63: [2023-04-29 11:37:29,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +49: [2023-04-29 11:37:29,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +16: [2023-04-29 11:37:29,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +16: [2023-04-29 11:37:29,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +52: [2023-04-29 11:37:29,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +30: [2023-04-29 11:37:29,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +16: [2023-04-29 11:37:29,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +16: [2023-04-29 11:37:29,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +16: [2023-04-29 11:37:29,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +16: [2023-04-29 11:37:29,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +60: [2023-04-29 11:37:29,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +16: [2023-04-29 11:37:29,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 0: [2023-04-29 11:37:29,432] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +16: [2023-04-29 11:37:29,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +36: [2023-04-29 11:37:29,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +36: [2023-04-29 11:37:29,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +51: [2023-04-29 11:37:29,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +38: [2023-04-29 11:37:29,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +38: [2023-04-29 11:37:29,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +60: [2023-04-29 11:37:29,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +56: [2023-04-29 11:37:29,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 0: [2023-04-29 11:37:29,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +63: [2023-04-29 11:37:29,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 0: [2023-04-29 11:37:29,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +51: [2023-04-29 11:37:29,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +60: [2023-04-29 11:37:29,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 0: [2023-04-29 11:37:29,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +38: [2023-04-29 11:37:29,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +27: [2023-04-29 11:37:29,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +27: [2023-04-29 11:37:29,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +27: [2023-04-29 11:37:29,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +27: [2023-04-29 11:37:29,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +50: [2023-04-29 11:37:29,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +42: [2023-04-29 11:37:29,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 1: [2023-04-29 11:37:29,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 1: [2023-04-29 11:37:29,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +52: [2023-04-29 11:37:29,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +16: [2023-04-29 11:37:29,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +16: [2023-04-29 11:37:29,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +39: [2023-04-29 11:37:29,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +35: [2023-04-29 11:37:29,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +50: [2023-04-29 11:37:29,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +41: [2023-04-29 11:37:29,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +41: [2023-04-29 11:37:29,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +36: [2023-04-29 11:37:29,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +36: [2023-04-29 11:37:29,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +41: [2023-04-29 11:37:29,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +38: [2023-04-29 11:37:29,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +41: [2023-04-29 11:37:29,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +39: [2023-04-29 11:37:29,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +16: [2023-04-29 11:37:29,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +35: [2023-04-29 11:37:29,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +16: [2023-04-29 11:37:29,442] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +16: [2023-04-29 11:37:29,442] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +60: [2023-04-29 11:37:29,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +35: [2023-04-29 11:37:29,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +16: [2023-04-29 11:37:29,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +25: [2023-04-29 11:37:29,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +39: [2023-04-29 11:37:29,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +16: [2023-04-29 11:37:29,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt... +16: [2023-04-29 11:37:29,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt... +20: [2023-04-29 11:37:29,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +20: [2023-04-29 11:37:29,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +20: [2023-04-29 11:37:29,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +39: [2023-04-29 11:37:29,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +20: [2023-04-29 11:37:29,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +40: [2023-04-29 11:37:29,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +40: [2023-04-29 11:37:29,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +40: [2023-04-29 11:37:29,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +47: [2023-04-29 11:37:29,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +47: [2023-04-29 11:37:29,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +47: [2023-04-29 11:37:29,447] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +47: [2023-04-29 11:37:29,447] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +35: [2023-04-29 11:37:29,447] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +63: [2023-04-29 11:37:29,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 0: [2023-04-29 11:37:29,448] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 0: [2023-04-29 11:37:29,448] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 0: [2023-04-29 11:37:29,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 4: [2023-04-29 11:37:29,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 4: [2023-04-29 11:37:29,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 4: [2023-04-29 11:37:29,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 4: [2023-04-29 11:37:29,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 8: [2023-04-29 11:37:29,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 8: [2023-04-29 11:37:29,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +40: [2023-04-29 11:37:29,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 0: [2023-04-29 11:37:29,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 8: [2023-04-29 11:37:29,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 8: [2023-04-29 11:37:29,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +20: [2023-04-29 11:37:29,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +56: [2023-04-29 11:37:29,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +60: [2023-04-29 11:37:29,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +60: [2023-04-29 11:37:29,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +29: [2023-04-29 11:37:29,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +29: [2023-04-29 11:37:29,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +60: [2023-04-29 11:37:29,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +20: [2023-04-29 11:37:29,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +29: [2023-04-29 11:37:29,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +20: [2023-04-29 11:37:29,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +63: [2023-04-29 11:37:29,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +29: [2023-04-29 11:37:29,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +56: [2023-04-29 11:37:29,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +56: [2023-04-29 11:37:29,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +56: [2023-04-29 11:37:29,453] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +20: [2023-04-29 11:37:29,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +47: [2023-04-29 11:37:29,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +47: [2023-04-29 11:37:29,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +47: [2023-04-29 11:37:29,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +56: [2023-04-29 11:37:29,453] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. + 4: [2023-04-29 11:37:29,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +25: [2023-04-29 11:37:29,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +47: [2023-04-29 11:37:29,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 4: [2023-04-29 11:37:29,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +18: [2023-04-29 11:37:29,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +18: [2023-04-29 11:37:29,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +25: [2023-04-29 11:37:29,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +62: [2023-04-29 11:37:29,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +18: [2023-04-29 11:37:29,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +62: [2023-04-29 11:37:29,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 4: [2023-04-29 11:37:29,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +18: [2023-04-29 11:37:29,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 4: [2023-04-29 11:37:29,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +60: [2023-04-29 11:37:29,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +42: [2023-04-29 11:37:29,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +56: [2023-04-29 11:37:29,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +56: [2023-04-29 11:37:29,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +29: [2023-04-29 11:37:29,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +25: [2023-04-29 11:37:29,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +29: [2023-04-29 11:37:29,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +45: [2023-04-29 11:37:29,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +45: [2023-04-29 11:37:29,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +45: [2023-04-29 11:37:29,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +29: [2023-04-29 11:37:29,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +45: [2023-04-29 11:37:29,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +29: [2023-04-29 11:37:29,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +42: [2023-04-29 11:37:29,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +42: [2023-04-29 11:37:29,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +62: [2023-04-29 11:37:29,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +56: [2023-04-29 11:37:29,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +34: [2023-04-29 11:37:29,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +34: [2023-04-29 11:37:29,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +53: [2023-04-29 11:37:29,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +53: [2023-04-29 11:37:29,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +53: [2023-04-29 11:37:29,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +46: [2023-04-29 11:37:29,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +46: [2023-04-29 11:37:29,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +60: [2023-04-29 11:37:29,462] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +60: [2023-04-29 11:37:29,462] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +53: [2023-04-29 11:37:29,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +36: [2023-04-29 11:37:29,462] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +38: [2023-04-29 11:37:29,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +38: [2023-04-29 11:37:29,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +27: [2023-04-29 11:37:29,463] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +63: [2023-04-29 11:37:29,463] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +50: [2023-04-29 11:37:29,463] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +45: [2023-04-29 11:37:29,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +63: [2023-04-29 11:37:29,463] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +38: [2023-04-29 11:37:29,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +60: [2023-04-29 11:37:29,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +38: [2023-04-29 11:37:29,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +21: [2023-04-29 11:37:29,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +36: [2023-04-29 11:37:29,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +27: [2023-04-29 11:37:29,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +38: [2023-04-29 11:37:29,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +27: [2023-04-29 11:37:29,466] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +27: [2023-04-29 11:37:29,466] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +45: [2023-04-29 11:37:29,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +50: [2023-04-29 11:37:29,466] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +34: [2023-04-29 11:37:29,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +34: [2023-04-29 11:37:29,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +42: [2023-04-29 11:37:29,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +46: [2023-04-29 11:37:29,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +46: [2023-04-29 11:37:29,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +36: [2023-04-29 11:37:29,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +25: [2023-04-29 11:37:29,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +34: [2023-04-29 11:37:29,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +34: [2023-04-29 11:37:29,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +62: [2023-04-29 11:37:29,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +36: [2023-04-29 11:37:29,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +62: [2023-04-29 11:37:29,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +62: [2023-04-29 11:37:29,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +62: [2023-04-29 11:37:29,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +34: [2023-04-29 11:37:29,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +46: [2023-04-29 11:37:29,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +34: [2023-04-29 11:37:29,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +36: [2023-04-29 11:37:29,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +38: [2023-04-29 11:37:29,470] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +38: [2023-04-29 11:37:29,470] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +46: [2023-04-29 11:37:29,473] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +36: [2023-04-29 11:37:29,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +36: [2023-04-29 11:37:29,473] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +34: [2023-04-29 11:37:29,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +62: [2023-04-29 11:37:29,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +34: [2023-04-29 11:37:29,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +41: [2023-04-29 11:37:29,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +41: [2023-04-29 11:37:29,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +21: [2023-04-29 11:37:29,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +21: [2023-04-29 11:37:29,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +21: [2023-04-29 11:37:29,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +35: [2023-04-29 11:37:29,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +45: [2023-04-29 11:37:29,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +45: [2023-04-29 11:37:29,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +36: [2023-04-29 11:37:29,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +46: [2023-04-29 11:37:29,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +41: [2023-04-29 11:37:29,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +34: [2023-04-29 11:37:29,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 0: [2023-04-29 11:37:29,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +40: [2023-04-29 11:37:29,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +35: [2023-04-29 11:37:29,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +40: [2023-04-29 11:37:29,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 8: [2023-04-29 11:37:29,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +35: [2023-04-29 11:37:29,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +38: [2023-04-29 11:37:29,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +38: [2023-04-29 11:37:29,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +40: [2023-04-29 11:37:29,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +56: [2023-04-29 11:37:29,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +56: [2023-04-29 11:37:29,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +60: [2023-04-29 11:37:29,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 0: [2023-04-29 11:37:29,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 8: [2023-04-29 11:37:29,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +34: [2023-04-29 11:37:29,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +56: [2023-04-29 11:37:29,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +62: [2023-04-29 11:37:29,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +62: [2023-04-29 11:37:29,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +62: [2023-04-29 11:37:29,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +46: [2023-04-29 11:37:29,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... + 0: [2023-04-29 11:37:29,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +43: [2023-04-29 11:37:29,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +43: [2023-04-29 11:37:29,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 0: [2023-04-29 11:37:29,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +41: [2023-04-29 11:37:29,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +61: [2023-04-29 11:37:29,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +61: [2023-04-29 11:37:29,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +61: [2023-04-29 11:37:29,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +61: [2023-04-29 11:37:29,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +55: [2023-04-29 11:37:29,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +55: [2023-04-29 11:37:29,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +55: [2023-04-29 11:37:29,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +25: [2023-04-29 11:37:29,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +55: [2023-04-29 11:37:29,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +60: [2023-04-29 11:37:29,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +25: [2023-04-29 11:37:29,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +56: [2023-04-29 11:37:29,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 8: [2023-04-29 11:37:29,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +56: [2023-04-29 11:37:29,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +43: [2023-04-29 11:37:29,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +43: [2023-04-29 11:37:29,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +57: [2023-04-29 11:37:29,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +57: [2023-04-29 11:37:29,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +57: [2023-04-29 11:37:29,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 2: [2023-04-29 11:37:29,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +60: [2023-04-29 11:37:29,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +18: [2023-04-29 11:37:29,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +57: [2023-04-29 11:37:29,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +61: [2023-04-29 11:37:29,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +61: [2023-04-29 11:37:29,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +61: [2023-04-29 11:37:29,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +60: [2023-04-29 11:37:29,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +45: [2023-04-29 11:37:29,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +25: [2023-04-29 11:37:29,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +38: [2023-04-29 11:37:29,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +43: [2023-04-29 11:37:29,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +62: [2023-04-29 11:37:29,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +18: [2023-04-29 11:37:29,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +18: [2023-04-29 11:37:29,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +61: [2023-04-29 11:37:29,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +61: [2023-04-29 11:37:29,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +61: [2023-04-29 11:37:29,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +38: [2023-04-29 11:37:29,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +43: [2023-04-29 11:37:29,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +43: [2023-04-29 11:37:29,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +61: [2023-04-29 11:37:29,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 8: [2023-04-29 11:37:29,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +45: [2023-04-29 11:37:29,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +34: [2023-04-29 11:37:29,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +57: [2023-04-29 11:37:29,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +57: [2023-04-29 11:37:29,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +18: [2023-04-29 11:37:29,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +45: [2023-04-29 11:37:29,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +57: [2023-04-29 11:37:29,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +57: [2023-04-29 11:37:29,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +61: [2023-04-29 11:37:29,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +43: [2023-04-29 11:37:29,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 2: [2023-04-29 11:37:29,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 2: [2023-04-29 11:37:29,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 2: [2023-04-29 11:37:29,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +45: [2023-04-29 11:37:29,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +21: [2023-04-29 11:37:29,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +53: [2023-04-29 11:37:29,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +34: [2023-04-29 11:37:29,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +53: [2023-04-29 11:37:29,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +45: [2023-04-29 11:37:29,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +53: [2023-04-29 11:37:29,493] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +47: [2023-04-29 11:37:29,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +53: [2023-04-29 11:37:29,493] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +61: [2023-04-29 11:37:29,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +61: [2023-04-29 11:37:29,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +61: [2023-04-29 11:37:29,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +36: [2023-04-29 11:37:29,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +45: [2023-04-29 11:37:29,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +47: [2023-04-29 11:37:29,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +34: [2023-04-29 11:37:29,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +36: [2023-04-29 11:37:29,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +34: [2023-04-29 11:37:29,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +61: [2023-04-29 11:37:29,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +47: [2023-04-29 11:37:29,502] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +36: [2023-04-29 11:37:29,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +55: [2023-04-29 11:37:29,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +55: [2023-04-29 11:37:29,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +47: [2023-04-29 11:37:29,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +35: [2023-04-29 11:37:29,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +35: [2023-04-29 11:37:29,505] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +55: [2023-04-29 11:37:29,505] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +62: [2023-04-29 11:37:29,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +21: [2023-04-29 11:37:29,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +21: [2023-04-29 11:37:29,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +55: [2023-04-29 11:37:29,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +36: [2023-04-29 11:37:29,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +45: [2023-04-29 11:37:29,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +21: [2023-04-29 11:37:29,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +47: [2023-04-29 11:37:29,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +55: [2023-04-29 11:37:29,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 0: [2023-04-29 11:37:29,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +45: [2023-04-29 11:37:29,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +48: [2023-04-29 11:37:29,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +48: [2023-04-29 11:37:29,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +48: [2023-04-29 11:37:29,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +48: [2023-04-29 11:37:29,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +55: [2023-04-29 11:37:29,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +55: [2023-04-29 11:37:29,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +14: [2023-04-29 11:37:29,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +14: [2023-04-29 11:37:29,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +14: [2023-04-29 11:37:29,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +14: [2023-04-29 11:37:29,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +47: [2023-04-29 11:37:29,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +35: [2023-04-29 11:37:29,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +57: [2023-04-29 11:37:29,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +57: [2023-04-29 11:37:29,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +29: [2023-04-29 11:37:29,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +35: [2023-04-29 11:37:29,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +16: [2023-04-29 11:37:29,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +16: [2023-04-29 11:37:29,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +16: [2023-04-29 11:37:29,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. + 2: [2023-04-29 11:37:29,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +55: [2023-04-29 11:37:29,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +57: [2023-04-29 11:37:29,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +57: [2023-04-29 11:37:29,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +55: [2023-04-29 11:37:29,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +29: [2023-04-29 11:37:29,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +55: [2023-04-29 11:37:29,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +11: [2023-04-29 11:37:29,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +11: [2023-04-29 11:37:29,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +55: [2023-04-29 11:37:29,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +62: [2023-04-29 11:37:29,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 4: [2023-04-29 11:37:29,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 4: [2023-04-29 11:37:29,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 0: [2023-04-29 11:37:29,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 0: [2023-04-29 11:37:29,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +20: [2023-04-29 11:37:29,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 4: [2023-04-29 11:37:29,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +37: [2023-04-29 11:37:29,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +37: [2023-04-29 11:37:29,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 4: [2023-04-29 11:37:29,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +47: [2023-04-29 11:37:29,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +37: [2023-04-29 11:37:29,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +37: [2023-04-29 11:37:29,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 2: [2023-04-29 11:37:29,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +11: [2023-04-29 11:37:29,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +55: [2023-04-29 11:37:29,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +11: [2023-04-29 11:37:29,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +35: [2023-04-29 11:37:29,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 4: [2023-04-29 11:37:29,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 2: [2023-04-29 11:37:29,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +11: [2023-04-29 11:37:29,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 2: [2023-04-29 11:37:29,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 0: [2023-04-29 11:37:29,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +16: [2023-04-29 11:37:29,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_00-model_states.pt. +11: [2023-04-29 11:37:29,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +39: [2023-04-29 11:37:29,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +39: [2023-04-29 11:37:29,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +20: [2023-04-29 11:37:29,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +47: [2023-04-29 11:37:29,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +37: [2023-04-29 11:37:29,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +35: [2023-04-29 11:37:29,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +11: [2023-04-29 11:37:29,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +11: [2023-04-29 11:37:29,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +47: [2023-04-29 11:37:29,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +37: [2023-04-29 11:37:29,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +12: [2023-04-29 11:37:29,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +12: [2023-04-29 11:37:29,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +37: [2023-04-29 11:37:29,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +12: [2023-04-29 11:37:29,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +12: [2023-04-29 11:37:29,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +20: [2023-04-29 11:37:29,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +20: [2023-04-29 11:37:29,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +47: [2023-04-29 11:37:29,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +39: [2023-04-29 11:37:29,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +39: [2023-04-29 11:37:29,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +37: [2023-04-29 11:37:29,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +35: [2023-04-29 11:37:29,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +29: [2023-04-29 11:37:29,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +29: [2023-04-29 11:37:29,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +54: [2023-04-29 11:37:29,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +54: [2023-04-29 11:37:29,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +33: [2023-04-29 11:37:29,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +33: [2023-04-29 11:37:29,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +35: [2023-04-29 11:37:29,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +33: [2023-04-29 11:37:29,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +33: [2023-04-29 11:37:29,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +54: [2023-04-29 11:37:29,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +49: [2023-04-29 11:37:29,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +49: [2023-04-29 11:37:29,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +49: [2023-04-29 11:37:29,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +54: [2023-04-29 11:37:29,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +49: [2023-04-29 11:37:29,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +14: [2023-04-29 11:37:29,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +47: [2023-04-29 11:37:29,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 4: [2023-04-29 11:37:29,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 4: [2023-04-29 11:37:29,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 4: [2023-04-29 11:37:29,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +41: [2023-04-29 11:37:29,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 6: [2023-04-29 11:37:29,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 6: [2023-04-29 11:37:29,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 6: [2023-04-29 11:37:29,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +48: [2023-04-29 11:37:29,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +47: [2023-04-29 11:37:29,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +49: [2023-04-29 11:37:29,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +20: [2023-04-29 11:37:29,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +48: [2023-04-29 11:37:29,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 6: [2023-04-29 11:37:29,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +29: [2023-04-29 11:37:29,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +44: [2023-04-29 11:37:29,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +44: [2023-04-29 11:37:29,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +44: [2023-04-29 11:37:29,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +43: [2023-04-29 11:37:29,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +44: [2023-04-29 11:37:29,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +49: [2023-04-29 11:37:29,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +14: [2023-04-29 11:37:29,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +49: [2023-04-29 11:37:29,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +14: [2023-04-29 11:37:29,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +60: [2023-04-29 11:37:29,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +60: [2023-04-29 11:37:29,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +49: [2023-04-29 11:37:29,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +29: [2023-04-29 11:37:29,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 6: [2023-04-29 11:37:29,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +14: [2023-04-29 11:37:29,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 8: [2023-04-29 11:37:29,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 8: [2023-04-29 11:37:29,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 6: [2023-04-29 11:37:29,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +16: [2023-04-29 11:37:29,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 0: [2023-04-29 11:37:29,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 6: [2023-04-29 11:37:29,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +61: [2023-04-29 11:37:29,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 4: [2023-04-29 11:37:29,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +48: [2023-04-29 11:37:29,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +48: [2023-04-29 11:37:29,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 4: [2023-04-29 11:37:29,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +34: [2023-04-29 11:37:29,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +34: [2023-04-29 11:37:29,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +17: [2023-04-29 11:37:29,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +17: [2023-04-29 11:37:29,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +17: [2023-04-29 11:37:29,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +57: [2023-04-29 11:37:29,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 8: [2023-04-29 11:37:29,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +17: [2023-04-29 11:37:29,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +41: [2023-04-29 11:37:29,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 8: [2023-04-29 11:37:29,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 6: [2023-04-29 11:37:29,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +16: [2023-04-29 11:37:29,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +16: [2023-04-29 11:37:29,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 0: [2023-04-29 11:37:29,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 0: [2023-04-29 11:37:29,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +60: [2023-04-29 11:37:29,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +60: [2023-04-29 11:37:29,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +18: [2023-04-29 11:37:29,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +18: [2023-04-29 11:37:29,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +56: [2023-04-29 11:37:29,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +56: [2023-04-29 11:37:29,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 4: [2023-04-29 11:37:29,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 8: [2023-04-29 11:37:29,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 8: [2023-04-29 11:37:29,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +12: [2023-04-29 11:37:29,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +41: [2023-04-29 11:37:29,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +57: [2023-04-29 11:37:29,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 4: [2023-04-29 11:37:29,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +18: [2023-04-29 11:37:29,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +18: [2023-04-29 11:37:29,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +57: [2023-04-29 11:37:29,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +57: [2023-04-29 11:37:29,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +20: [2023-04-29 11:37:29,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +41: [2023-04-29 11:37:29,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +47: [2023-04-29 11:37:29,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +18: [2023-04-29 11:37:29,551] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 8: [2023-04-29 11:37:29,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 8: [2023-04-29 11:37:29,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +47: [2023-04-29 11:37:29,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 4: [2023-04-29 11:37:29,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +34: [2023-04-29 11:37:29,551] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +12: [2023-04-29 11:37:29,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +56: [2023-04-29 11:37:29,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +56: [2023-04-29 11:37:29,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +12: [2023-04-29 11:37:29,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +20: [2023-04-29 11:37:29,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +60: [2023-04-29 11:37:29,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +41: [2023-04-29 11:37:29,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +39: [2023-04-29 11:37:29,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 8: [2023-04-29 11:37:29,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +18: [2023-04-29 11:37:29,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +39: [2023-04-29 11:37:29,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +56: [2023-04-29 11:37:29,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +56: [2023-04-29 11:37:29,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +61: [2023-04-29 11:37:29,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 8: [2023-04-29 11:37:29,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +39: [2023-04-29 11:37:29,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +61: [2023-04-29 11:37:29,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +12: [2023-04-29 11:37:29,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +16: [2023-04-29 11:37:29,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +18: [2023-04-29 11:37:29,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +18: [2023-04-29 11:37:29,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +20: [2023-04-29 11:37:29,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +18: [2023-04-29 11:37:29,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +43: [2023-04-29 11:37:29,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +43: [2023-04-29 11:37:29,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +57: [2023-04-29 11:37:29,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 0: [2023-04-29 11:37:29,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +34: [2023-04-29 11:37:29,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +45: [2023-04-29 11:37:29,558] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +18: [2023-04-29 11:37:29,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +29: [2023-04-29 11:37:29,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +29: [2023-04-29 11:37:29,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +60: [2023-04-29 11:37:29,558] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +60: [2023-04-29 11:37:29,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +39: [2023-04-29 11:37:29,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +18: [2023-04-29 11:37:29,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +54: [2023-04-29 11:37:29,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +18: [2023-04-29 11:37:29,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +43: [2023-04-29 11:37:29,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +56: [2023-04-29 11:37:29,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +56: [2023-04-29 11:37:29,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +54: [2023-04-29 11:37:29,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +41: [2023-04-29 11:37:29,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +41: [2023-04-29 11:37:29,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +54: [2023-04-29 11:37:29,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +53: [2023-04-29 11:37:29,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 8: [2023-04-29 11:37:29,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +54: [2023-04-29 11:37:29,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 0: [2023-04-29 11:37:29,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +18: [2023-04-29 11:37:29,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +33: [2023-04-29 11:37:29,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +33: [2023-04-29 11:37:29,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +45: [2023-04-29 11:37:29,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +33: [2023-04-29 11:37:29,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +36: [2023-04-29 11:37:29,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +53: [2023-04-29 11:37:29,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +53: [2023-04-29 11:37:29,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +53: [2023-04-29 11:37:29,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +27: [2023-04-29 11:37:29,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +27: [2023-04-29 11:37:29,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +27: [2023-04-29 11:37:29,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +27: [2023-04-29 11:37:29,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +27: [2023-04-29 11:37:29,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +27: [2023-04-29 11:37:29,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +27: [2023-04-29 11:37:29,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +27: [2023-04-29 11:37:29,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +57: [2023-04-29 11:37:29,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +36: [2023-04-29 11:37:29,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +61: [2023-04-29 11:37:29,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 0: [2023-04-29 11:37:29,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +45: [2023-04-29 11:37:29,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +58: [2023-04-29 11:37:29,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +58: [2023-04-29 11:37:29,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +58: [2023-04-29 11:37:29,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +18: [2023-04-29 11:37:29,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +58: [2023-04-29 11:37:29,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +33: [2023-04-29 11:37:29,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +53: [2023-04-29 11:37:29,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +53: [2023-04-29 11:37:29,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +34: [2023-04-29 11:37:29,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +60: [2023-04-29 11:37:29,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +48: [2023-04-29 11:37:29,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +48: [2023-04-29 11:37:29,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 0: [2023-04-29 11:37:29,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 0: [2023-04-29 11:37:29,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +53: [2023-04-29 11:37:29,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +53: [2023-04-29 11:37:29,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +47: [2023-04-29 11:37:29,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +36: [2023-04-29 11:37:29,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +48: [2023-04-29 11:37:29,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +43: [2023-04-29 11:37:29,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +47: [2023-04-29 11:37:29,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +53: [2023-04-29 11:37:29,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +45: [2023-04-29 11:37:29,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +48: [2023-04-29 11:37:29,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +34: [2023-04-29 11:37:29,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +41: [2023-04-29 11:37:29,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... + 0: [2023-04-29 11:37:29,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +27: [2023-04-29 11:37:29,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +44: [2023-04-29 11:37:29,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +36: [2023-04-29 11:37:29,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... + 8: [2023-04-29 11:37:29,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +57: [2023-04-29 11:37:29,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +44: [2023-04-29 11:37:29,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +18: [2023-04-29 11:37:29,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +17: [2023-04-29 11:37:29,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 8: [2023-04-29 11:37:29,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +27: [2023-04-29 11:37:29,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +44: [2023-04-29 11:37:29,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +44: [2023-04-29 11:37:29,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 4: [2023-04-29 11:37:29,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +61: [2023-04-29 11:37:29,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +53: [2023-04-29 11:37:29,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +53: [2023-04-29 11:37:29,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +27: [2023-04-29 11:37:29,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +27: [2023-04-29 11:37:29,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +27: [2023-04-29 11:37:29,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +53: [2023-04-29 11:37:29,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +27: [2023-04-29 11:37:29,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +27: [2023-04-29 11:37:29,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... + 8: [2023-04-29 11:37:29,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +27: [2023-04-29 11:37:29,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... + 0: [2023-04-29 11:37:29,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +53: [2023-04-29 11:37:29,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +34: [2023-04-29 11:37:29,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +34: [2023-04-29 11:37:29,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +34: [2023-04-29 11:37:29,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +45: [2023-04-29 11:37:29,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +45: [2023-04-29 11:37:29,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +34: [2023-04-29 11:37:29,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +48: [2023-04-29 11:37:29,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +48: [2023-04-29 11:37:29,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +48: [2023-04-29 11:37:29,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +53: [2023-04-29 11:37:29,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +53: [2023-04-29 11:37:29,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 0: [2023-04-29 11:37:29,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... + 0: [2023-04-29 11:37:29,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +53: [2023-04-29 11:37:29,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +17: [2023-04-29 11:37:29,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +17: [2023-04-29 11:37:29,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +11: [2023-04-29 11:37:29,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +34: [2023-04-29 11:37:29,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +55: [2023-04-29 11:37:29,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +48: [2023-04-29 11:37:29,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +36: [2023-04-29 11:37:29,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. + 4: [2023-04-29 11:37:29,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 4: [2023-04-29 11:37:29,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +18: [2023-04-29 11:37:29,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... + 8: [2023-04-29 11:37:29,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +36: [2023-04-29 11:37:29,577] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +17: [2023-04-29 11:37:29,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +45: [2023-04-29 11:37:29,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +45: [2023-04-29 11:37:29,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... + 8: [2023-04-29 11:37:29,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +34: [2023-04-29 11:37:29,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +55: [2023-04-29 11:37:29,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +61: [2023-04-29 11:37:29,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +36: [2023-04-29 11:37:29,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +57: [2023-04-29 11:37:29,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +57: [2023-04-29 11:37:29,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +61: [2023-04-29 11:37:29,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +55: [2023-04-29 11:37:29,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +55: [2023-04-29 11:37:29,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +37: [2023-04-29 11:37:29,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +11: [2023-04-29 11:37:29,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +36: [2023-04-29 11:37:29,584] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +34: [2023-04-29 11:37:29,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +11: [2023-04-29 11:37:29,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +57: [2023-04-29 11:37:29,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +55: [2023-04-29 11:37:29,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +55: [2023-04-29 11:37:29,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +55: [2023-04-29 11:37:29,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +43: [2023-04-29 11:37:29,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +61: [2023-04-29 11:37:29,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +11: [2023-04-29 11:37:29,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +55: [2023-04-29 11:37:29,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +55: [2023-04-29 11:37:29,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +43: [2023-04-29 11:37:29,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +43: [2023-04-29 11:37:29,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +58: [2023-04-29 11:37:29,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +58: [2023-04-29 11:37:29,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +58: [2023-04-29 11:37:29,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +58: [2023-04-29 11:37:29,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +37: [2023-04-29 11:37:29,594] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +37: [2023-04-29 11:37:29,594] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +37: [2023-04-29 11:37:29,594] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +34: [2023-04-29 11:37:29,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +34: [2023-04-29 11:37:29,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +57: [2023-04-29 11:37:29,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +55: [2023-04-29 11:37:29,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +46: [2023-04-29 11:37:29,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +46: [2023-04-29 11:37:29,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +55: [2023-04-29 11:37:29,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +59: [2023-04-29 11:37:29,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +59: [2023-04-29 11:37:29,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +63: [2023-04-29 11:37:29,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +63: [2023-04-29 11:37:29,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +63: [2023-04-29 11:37:29,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +63: [2023-04-29 11:37:29,600] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +46: [2023-04-29 11:37:29,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +46: [2023-04-29 11:37:29,600] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +55: [2023-04-29 11:37:29,601] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +11: [2023-04-29 11:37:29,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +46: [2023-04-29 11:37:29,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +46: [2023-04-29 11:37:29,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +34: [2023-04-29 11:37:29,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +49: [2023-04-29 11:37:29,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +46: [2023-04-29 11:37:29,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +23: [2023-04-29 11:37:29,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +23: [2023-04-29 11:37:29,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +59: [2023-04-29 11:37:29,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +59: [2023-04-29 11:37:29,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +54: [2023-04-29 11:37:29,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +54: [2023-04-29 11:37:29,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +46: [2023-04-29 11:37:29,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +59: [2023-04-29 11:37:29,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +59: [2023-04-29 11:37:29,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +54: [2023-04-29 11:37:29,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +48: [2023-04-29 11:37:29,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +54: [2023-04-29 11:37:29,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +23: [2023-04-29 11:37:29,608] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +49: [2023-04-29 11:37:29,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +23: [2023-04-29 11:37:29,608] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +55: [2023-04-29 11:37:29,608] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +37: [2023-04-29 11:37:29,609] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +22: [2023-04-29 11:37:29,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +22: [2023-04-29 11:37:29,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +22: [2023-04-29 11:37:29,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +22: [2023-04-29 11:37:29,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 6: [2023-04-29 11:37:29,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 6: [2023-04-29 11:37:29,610] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 6: [2023-04-29 11:37:29,610] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 6: [2023-04-29 11:37:29,610] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 6: [2023-04-29 11:37:29,610] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +23: [2023-04-29 11:37:29,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +23: [2023-04-29 11:37:29,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 4: [2023-04-29 11:37:29,610] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +59: [2023-04-29 11:37:29,611] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +59: [2023-04-29 11:37:29,611] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +11: [2023-04-29 11:37:29,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +54: [2023-04-29 11:37:29,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +54: [2023-04-29 11:37:29,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +54: [2023-04-29 11:37:29,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +11: [2023-04-29 11:37:29,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 8: [2023-04-29 11:37:29,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +55: [2023-04-29 11:37:29,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +18: [2023-04-29 11:37:29,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 6: [2023-04-29 11:37:29,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 6: [2023-04-29 11:37:29,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +23: [2023-04-29 11:37:29,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +59: [2023-04-29 11:37:29,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +23: [2023-04-29 11:37:29,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +13: [2023-04-29 11:37:29,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +13: [2023-04-29 11:37:29,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +54: [2023-04-29 11:37:29,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +13: [2023-04-29 11:37:29,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +48: [2023-04-29 11:37:29,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... + 4: [2023-04-29 11:37:29,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +32: [2023-04-29 11:37:29,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +32: [2023-04-29 11:37:29,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +13: [2023-04-29 11:37:29,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +57: [2023-04-29 11:37:29,614] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +48: [2023-04-29 11:37:29,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. + 6: [2023-04-29 11:37:29,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +11: [2023-04-29 11:37:29,614] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +59: [2023-04-29 11:37:29,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 4: [2023-04-29 11:37:29,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +33: [2023-04-29 11:37:29,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. + 8: [2023-04-29 11:37:29,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +32: [2023-04-29 11:37:29,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +49: [2023-04-29 11:37:29,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +49: [2023-04-29 11:37:29,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +32: [2023-04-29 11:37:29,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. + 4: [2023-04-29 11:37:29,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +54: [2023-04-29 11:37:29,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +59: [2023-04-29 11:37:29,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +55: [2023-04-29 11:37:29,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +32: [2023-04-29 11:37:29,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +59: [2023-04-29 11:37:29,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +55: [2023-04-29 11:37:29,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +32: [2023-04-29 11:37:29,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +48: [2023-04-29 11:37:29,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +57: [2023-04-29 11:37:29,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +31: [2023-04-29 11:37:29,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +31: [2023-04-29 11:37:29,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +31: [2023-04-29 11:37:29,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 3: [2023-04-29 11:37:29,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 3: [2023-04-29 11:37:29,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +31: [2023-04-29 11:37:29,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +17: [2023-04-29 11:37:29,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +17: [2023-04-29 11:37:29,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +17: [2023-04-29 11:37:29,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 3: [2023-04-29 11:37:29,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +17: [2023-04-29 11:37:29,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 3: [2023-04-29 11:37:29,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +48: [2023-04-29 11:37:29,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +44: [2023-04-29 11:37:29,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +20: [2023-04-29 11:37:29,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +22: [2023-04-29 11:37:29,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +22: [2023-04-29 11:37:29,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +22: [2023-04-29 11:37:29,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +20: [2023-04-29 11:37:29,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +20: [2023-04-29 11:37:29,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +39: [2023-04-29 11:37:29,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +54: [2023-04-29 11:37:29,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +20: [2023-04-29 11:37:29,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +22: [2023-04-29 11:37:29,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +37: [2023-04-29 11:37:29,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 8: [2023-04-29 11:37:29,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +32: [2023-04-29 11:37:29,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 8: [2023-04-29 11:37:29,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +37: [2023-04-29 11:37:29,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 3: [2023-04-29 11:37:29,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +37: [2023-04-29 11:37:29,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 4: [2023-04-29 11:37:29,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +63: [2023-04-29 11:37:29,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +17: [2023-04-29 11:37:29,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 3: [2023-04-29 11:37:29,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +31: [2023-04-29 11:37:29,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +31: [2023-04-29 11:37:29,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +59: [2023-04-29 11:37:29,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +57: [2023-04-29 11:37:29,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +44: [2023-04-29 11:37:29,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +17: [2023-04-29 11:37:29,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +27: [2023-04-29 11:37:29,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +32: [2023-04-29 11:37:29,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +63: [2023-04-29 11:37:29,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +17: [2023-04-29 11:37:29,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +48: [2023-04-29 11:37:29,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. + 3: [2023-04-29 11:37:29,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +33: [2023-04-29 11:37:29,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +57: [2023-04-29 11:37:29,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +17: [2023-04-29 11:37:29,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +31: [2023-04-29 11:37:29,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +59: [2023-04-29 11:37:29,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +18: [2023-04-29 11:37:29,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 4: [2023-04-29 11:37:29,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +49: [2023-04-29 11:37:29,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +48: [2023-04-29 11:37:29,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +31: [2023-04-29 11:37:29,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 3: [2023-04-29 11:37:29,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +18: [2023-04-29 11:37:29,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +39: [2023-04-29 11:37:29,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +39: [2023-04-29 11:37:29,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +22: [2023-04-29 11:37:29,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +54: [2023-04-29 11:37:29,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +22: [2023-04-29 11:37:29,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +33: [2023-04-29 11:37:29,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +63: [2023-04-29 11:37:29,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +22: [2023-04-29 11:37:29,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +22: [2023-04-29 11:37:29,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +53: [2023-04-29 11:37:29,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +17: [2023-04-29 11:37:29,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +39: [2023-04-29 11:37:29,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +57: [2023-04-29 11:37:29,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... + 4: [2023-04-29 11:37:29,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +27: [2023-04-29 11:37:29,633] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +48: [2023-04-29 11:37:29,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +18: [2023-04-29 11:37:29,634] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +33: [2023-04-29 11:37:29,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +39: [2023-04-29 11:37:29,634] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +22: [2023-04-29 11:37:29,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +18: [2023-04-29 11:37:29,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 4: [2023-04-29 11:37:29,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +48: [2023-04-29 11:37:29,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +44: [2023-04-29 11:37:29,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +54: [2023-04-29 11:37:29,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +44: [2023-04-29 11:37:29,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +44: [2023-04-29 11:37:29,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +57: [2023-04-29 11:37:29,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +57: [2023-04-29 11:37:29,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +27: [2023-04-29 11:37:29,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +27: [2023-04-29 11:37:29,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +17: [2023-04-29 11:37:29,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +22: [2023-04-29 11:37:29,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +49: [2023-04-29 11:37:29,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +54: [2023-04-29 11:37:29,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +63: [2023-04-29 11:37:29,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +22: [2023-04-29 11:37:29,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +22: [2023-04-29 11:37:29,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +39: [2023-04-29 11:37:29,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +14: [2023-04-29 11:37:29,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +14: [2023-04-29 11:37:29,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +14: [2023-04-29 11:37:29,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +14: [2023-04-29 11:37:29,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +14: [2023-04-29 11:37:29,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +14: [2023-04-29 11:37:29,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +59: [2023-04-29 11:37:29,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +14: [2023-04-29 11:37:29,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +14: [2023-04-29 11:37:29,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +59: [2023-04-29 11:37:29,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... + 8: [2023-04-29 11:37:29,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +44: [2023-04-29 11:37:29,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +44: [2023-04-29 11:37:29,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +44: [2023-04-29 11:37:29,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +44: [2023-04-29 11:37:29,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +39: [2023-04-29 11:37:29,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +37: [2023-04-29 11:37:29,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +37: [2023-04-29 11:37:29,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +37: [2023-04-29 11:37:29,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +37: [2023-04-29 11:37:29,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +33: [2023-04-29 11:37:29,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +44: [2023-04-29 11:37:29,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +44: [2023-04-29 11:37:29,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +13: [2023-04-29 11:37:29,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +39: [2023-04-29 11:37:29,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +44: [2023-04-29 11:37:29,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +33: [2023-04-29 11:37:29,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. + 6: [2023-04-29 11:37:29,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +57: [2023-04-29 11:37:29,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +57: [2023-04-29 11:37:29,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... + 6: [2023-04-29 11:37:29,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +14: [2023-04-29 11:37:29,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... + 6: [2023-04-29 11:37:29,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +53: [2023-04-29 11:37:29,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +53: [2023-04-29 11:37:29,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +53: [2023-04-29 11:37:29,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. + 6: [2023-04-29 11:37:29,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 8: [2023-04-29 11:37:29,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +13: [2023-04-29 11:37:29,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +48: [2023-04-29 11:37:29,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +14: [2023-04-29 11:37:29,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +54: [2023-04-29 11:37:29,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +54: [2023-04-29 11:37:29,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +13: [2023-04-29 11:37:29,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +13: [2023-04-29 11:37:29,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +52: [2023-04-29 11:37:29,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +52: [2023-04-29 11:37:29,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +52: [2023-04-29 11:37:29,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 6: [2023-04-29 11:37:29,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +52: [2023-04-29 11:37:29,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 6: [2023-04-29 11:37:29,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +44: [2023-04-29 11:37:29,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +44: [2023-04-29 11:37:29,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 6: [2023-04-29 11:37:29,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +14: [2023-04-29 11:37:29,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +44: [2023-04-29 11:37:29,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +14: [2023-04-29 11:37:29,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +14: [2023-04-29 11:37:29,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +14: [2023-04-29 11:37:29,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +14: [2023-04-29 11:37:29,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +44: [2023-04-29 11:37:29,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +17: [2023-04-29 11:37:29,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +43: [2023-04-29 11:37:29,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +43: [2023-04-29 11:37:29,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +14: [2023-04-29 11:37:29,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +43: [2023-04-29 11:37:29,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +43: [2023-04-29 11:37:29,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_33-model_01-model_states.pt. +48: [2023-04-29 11:37:29,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +52: [2023-04-29 11:37:29,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 6: [2023-04-29 11:37:29,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +33: [2023-04-29 11:37:29,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +33: [2023-04-29 11:37:29,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +52: [2023-04-29 11:37:29,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +52: [2023-04-29 11:37:29,650] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +52: [2023-04-29 11:37:29,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +54: [2023-04-29 11:37:29,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +17: [2023-04-29 11:37:29,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +49: [2023-04-29 11:37:29,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +17: [2023-04-29 11:37:29,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +49: [2023-04-29 11:37:29,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +27: [2023-04-29 11:37:29,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +48: [2023-04-29 11:37:29,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +23: [2023-04-29 11:37:29,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +23: [2023-04-29 11:37:29,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +23: [2023-04-29 11:37:29,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +23: [2023-04-29 11:37:29,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +58: [2023-04-29 11:37:29,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +20: [2023-04-29 11:37:29,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +17: [2023-04-29 11:37:29,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 8: [2023-04-29 11:37:29,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +20: [2023-04-29 11:37:29,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 8: [2023-04-29 11:37:29,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +53: [2023-04-29 11:37:29,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +33: [2023-04-29 11:37:29,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +33: [2023-04-29 11:37:29,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +33: [2023-04-29 11:37:29,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +58: [2023-04-29 11:37:29,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +48: [2023-04-29 11:37:29,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +33: [2023-04-29 11:37:29,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +17: [2023-04-29 11:37:29,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +27: [2023-04-29 11:37:29,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +20: [2023-04-29 11:37:29,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +20: [2023-04-29 11:37:29,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +18: [2023-04-29 11:37:29,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +18: [2023-04-29 11:37:29,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +17: [2023-04-29 11:37:29,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +27: [2023-04-29 11:37:29,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +33: [2023-04-29 11:37:29,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +26: [2023-04-29 11:37:29,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +26: [2023-04-29 11:37:29,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +26: [2023-04-29 11:37:29,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +18: [2023-04-29 11:37:29,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +33: [2023-04-29 11:37:29,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +26: [2023-04-29 11:37:29,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +33: [2023-04-29 11:37:29,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +58: [2023-04-29 11:37:29,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +37: [2023-04-29 11:37:29,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +33: [2023-04-29 11:37:29,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +46: [2023-04-29 11:37:29,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +27: [2023-04-29 11:37:29,667] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +54: [2023-04-29 11:37:29,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +58: [2023-04-29 11:37:29,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +58: [2023-04-29 11:37:29,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +11: [2023-04-29 11:37:29,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +11: [2023-04-29 11:37:29,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +11: [2023-04-29 11:37:29,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +28: [2023-04-29 11:37:29,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +28: [2023-04-29 11:37:29,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +11: [2023-04-29 11:37:29,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +28: [2023-04-29 11:37:29,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +28: [2023-04-29 11:37:29,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +41: [2023-04-29 11:37:29,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +41: [2023-04-29 11:37:29,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +46: [2023-04-29 11:37:29,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +58: [2023-04-29 11:37:29,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +37: [2023-04-29 11:37:29,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +19: [2023-04-29 11:37:29,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +19: [2023-04-29 11:37:29,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +37: [2023-04-29 11:37:29,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +19: [2023-04-29 11:37:29,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +48: [2023-04-29 11:37:29,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +19: [2023-04-29 11:37:29,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +51: [2023-04-29 11:37:29,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +51: [2023-04-29 11:37:29,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +51: [2023-04-29 11:37:29,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +37: [2023-04-29 11:37:29,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +51: [2023-04-29 11:37:29,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +41: [2023-04-29 11:37:29,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +41: [2023-04-29 11:37:29,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +58: [2023-04-29 11:37:29,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +58: [2023-04-29 11:37:29,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +28: [2023-04-29 11:37:29,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +48: [2023-04-29 11:37:29,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +28: [2023-04-29 11:37:29,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +53: [2023-04-29 11:37:29,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +28: [2023-04-29 11:37:29,677] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +53: [2023-04-29 11:37:29,677] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +41: [2023-04-29 11:37:29,678] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +28: [2023-04-29 11:37:29,678] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +41: [2023-04-29 11:37:29,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +43: [2023-04-29 11:37:29,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +43: [2023-04-29 11:37:29,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +54: [2023-04-29 11:37:29,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +58: [2023-04-29 11:37:29,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +58: [2023-04-29 11:37:29,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +58: [2023-04-29 11:37:29,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +58: [2023-04-29 11:37:29,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +12: [2023-04-29 11:37:29,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +12: [2023-04-29 11:37:29,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +41: [2023-04-29 11:37:29,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +53: [2023-04-29 11:37:29,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +12: [2023-04-29 11:37:29,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +12: [2023-04-29 11:37:29,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +12: [2023-04-29 11:37:29,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +12: [2023-04-29 11:37:29,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +12: [2023-04-29 11:37:29,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +12: [2023-04-29 11:37:29,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +51: [2023-04-29 11:37:29,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +43: [2023-04-29 11:37:29,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +59: [2023-04-29 11:37:29,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +41: [2023-04-29 11:37:29,683] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +10: [2023-04-29 11:37:29,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +10: [2023-04-29 11:37:29,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +10: [2023-04-29 11:37:29,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +46: [2023-04-29 11:37:29,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +51: [2023-04-29 11:37:29,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +51: [2023-04-29 11:37:29,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +10: [2023-04-29 11:37:29,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +43: [2023-04-29 11:37:29,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt... +51: [2023-04-29 11:37:29,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +58: [2023-04-29 11:37:29,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +32: [2023-04-29 11:37:29,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +32: [2023-04-29 11:37:29,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +23: [2023-04-29 11:37:29,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +23: [2023-04-29 11:37:29,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +12: [2023-04-29 11:37:29,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +58: [2023-04-29 11:37:29,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +58: [2023-04-29 11:37:29,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +50: [2023-04-29 11:37:29,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +50: [2023-04-29 11:37:29,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 3: [2023-04-29 11:37:29,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +31: [2023-04-29 11:37:29,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +58: [2023-04-29 11:37:29,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +48: [2023-04-29 11:37:29,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +12: [2023-04-29 11:37:29,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +23: [2023-04-29 11:37:29,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +12: [2023-04-29 11:37:29,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +50: [2023-04-29 11:37:29,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +50: [2023-04-29 11:37:29,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +46: [2023-04-29 11:37:29,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 3: [2023-04-29 11:37:29,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +23: [2023-04-29 11:37:29,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +23: [2023-04-29 11:37:29,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +12: [2023-04-29 11:37:29,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +12: [2023-04-29 11:37:29,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +12: [2023-04-29 11:37:29,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +54: [2023-04-29 11:37:29,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +26: [2023-04-29 11:37:29,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +17: [2023-04-29 11:37:29,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +12: [2023-04-29 11:37:29,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +12: [2023-04-29 11:37:29,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +26: [2023-04-29 11:37:29,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +23: [2023-04-29 11:37:29,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +23: [2023-04-29 11:37:29,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +50: [2023-04-29 11:37:29,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +50: [2023-04-29 11:37:29,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +54: [2023-04-29 11:37:29,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +59: [2023-04-29 11:37:29,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +59: [2023-04-29 11:37:29,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +54: [2023-04-29 11:37:29,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +32: [2023-04-29 11:37:29,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +50: [2023-04-29 11:37:29,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +31: [2023-04-29 11:37:29,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +22: [2023-04-29 11:37:29,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +17: [2023-04-29 11:37:29,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +32: [2023-04-29 11:37:29,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +26: [2023-04-29 11:37:29,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +26: [2023-04-29 11:37:29,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 3: [2023-04-29 11:37:29,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 3: [2023-04-29 11:37:29,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +59: [2023-04-29 11:37:29,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +59: [2023-04-29 11:37:29,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +46: [2023-04-29 11:37:29,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +63: [2023-04-29 11:37:29,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +23: [2023-04-29 11:37:29,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +50: [2023-04-29 11:37:29,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +21: [2023-04-29 11:37:29,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +21: [2023-04-29 11:37:29,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +21: [2023-04-29 11:37:29,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +46: [2023-04-29 11:37:29,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +21: [2023-04-29 11:37:29,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +11: [2023-04-29 11:37:29,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +19: [2023-04-29 11:37:29,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +11: [2023-04-29 11:37:29,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +52: [2023-04-29 11:37:29,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +22: [2023-04-29 11:37:29,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +11: [2023-04-29 11:37:29,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +11: [2023-04-29 11:37:29,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +63: [2023-04-29 11:37:29,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +26: [2023-04-29 11:37:29,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +26: [2023-04-29 11:37:29,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +26: [2023-04-29 11:37:29,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +26: [2023-04-29 11:37:29,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +50: [2023-04-29 11:37:29,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +50: [2023-04-29 11:37:29,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +59: [2023-04-29 11:37:29,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +59: [2023-04-29 11:37:29,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +22: [2023-04-29 11:37:29,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +63: [2023-04-29 11:37:29,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +50: [2023-04-29 11:37:29,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +59: [2023-04-29 11:37:29,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +50: [2023-04-29 11:37:29,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +19: [2023-04-29 11:37:29,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +19: [2023-04-29 11:37:29,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +14: [2023-04-29 11:37:29,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +63: [2023-04-29 11:37:29,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +17: [2023-04-29 11:37:29,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +26: [2023-04-29 11:37:29,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +63: [2023-04-29 11:37:29,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +19: [2023-04-29 11:37:29,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +44: [2023-04-29 11:37:29,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +44: [2023-04-29 11:37:29,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +54: [2023-04-29 11:37:29,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +26: [2023-04-29 11:37:29,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +22: [2023-04-29 11:37:29,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +31: [2023-04-29 11:37:29,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +31: [2023-04-29 11:37:29,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +22: [2023-04-29 11:37:29,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +22: [2023-04-29 11:37:29,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +22: [2023-04-29 11:37:29,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +40: [2023-04-29 11:37:29,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +26: [2023-04-29 11:37:29,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +40: [2023-04-29 11:37:29,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +40: [2023-04-29 11:37:29,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +14: [2023-04-29 11:37:29,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +40: [2023-04-29 11:37:29,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +26: [2023-04-29 11:37:29,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +17: [2023-04-29 11:37:29,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 3: [2023-04-29 11:37:29,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +23: [2023-04-29 11:37:29,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +44: [2023-04-29 11:37:29,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +63: [2023-04-29 11:37:29,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +22: [2023-04-29 11:37:29,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 6: [2023-04-29 11:37:29,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +59: [2023-04-29 11:37:29,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +10: [2023-04-29 11:37:29,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +44: [2023-04-29 11:37:29,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +10: [2023-04-29 11:37:29,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +22: [2023-04-29 11:37:29,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +10: [2023-04-29 11:37:29,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 6: [2023-04-29 11:37:29,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 6: [2023-04-29 11:37:29,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +40: [2023-04-29 11:37:29,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +20: [2023-04-29 11:37:29,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +31: [2023-04-29 11:37:29,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +63: [2023-04-29 11:37:29,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +10: [2023-04-29 11:37:29,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +59: [2023-04-29 11:37:29,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +40: [2023-04-29 11:37:29,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 3: [2023-04-29 11:37:29,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +40: [2023-04-29 11:37:29,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +40: [2023-04-29 11:37:29,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +52: [2023-04-29 11:37:29,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +52: [2023-04-29 11:37:29,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +46: [2023-04-29 11:37:29,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 6: [2023-04-29 11:37:29,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +52: [2023-04-29 11:37:29,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +22: [2023-04-29 11:37:29,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +14: [2023-04-29 11:37:29,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +14: [2023-04-29 11:37:29,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +20: [2023-04-29 11:37:29,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +32: [2023-04-29 11:37:29,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +32: [2023-04-29 11:37:29,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 6: [2023-04-29 11:37:29,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +17: [2023-04-29 11:37:29,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +20: [2023-04-29 11:37:29,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +46: [2023-04-29 11:37:29,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +63: [2023-04-29 11:37:29,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... + 6: [2023-04-29 11:37:29,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +52: [2023-04-29 11:37:29,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 6: [2023-04-29 11:37:29,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +59: [2023-04-29 11:37:29,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +31: [2023-04-29 11:37:29,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +54: [2023-04-29 11:37:29,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +54: [2023-04-29 11:37:29,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +21: [2023-04-29 11:37:29,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +33: [2023-04-29 11:37:29,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 3: [2023-04-29 11:37:29,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 6: [2023-04-29 11:37:29,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +20: [2023-04-29 11:37:29,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +59: [2023-04-29 11:37:29,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +23: [2023-04-29 11:37:29,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +59: [2023-04-29 11:37:29,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +59: [2023-04-29 11:37:29,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +17: [2023-04-29 11:37:29,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +32: [2023-04-29 11:37:29,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +21: [2023-04-29 11:37:29,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +24: [2023-04-29 11:37:29,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +24: [2023-04-29 11:37:29,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +23: [2023-04-29 11:37:29,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +23: [2023-04-29 11:37:29,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 3: [2023-04-29 11:37:29,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +22: [2023-04-29 11:37:29,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +32: [2023-04-29 11:37:29,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +59: [2023-04-29 11:37:29,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +21: [2023-04-29 11:37:29,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +24: [2023-04-29 11:37:29,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +20: [2023-04-29 11:37:29,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +22: [2023-04-29 11:37:29,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +24: [2023-04-29 11:37:29,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +14: [2023-04-29 11:37:29,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +37: [2023-04-29 11:37:29,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +37: [2023-04-29 11:37:29,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +59: [2023-04-29 11:37:29,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +24: [2023-04-29 11:37:29,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 9: [2023-04-29 11:37:29,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 9: [2023-04-29 11:37:29,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +24: [2023-04-29 11:37:29,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +50: [2023-04-29 11:37:29,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +50: [2023-04-29 11:37:29,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 9: [2023-04-29 11:37:29,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +20: [2023-04-29 11:37:29,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 9: [2023-04-29 11:37:29,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +33: [2023-04-29 11:37:29,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +44: [2023-04-29 11:37:29,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +17: [2023-04-29 11:37:29,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +21: [2023-04-29 11:37:29,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +24: [2023-04-29 11:37:29,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +31: [2023-04-29 11:37:29,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +24: [2023-04-29 11:37:29,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +44: [2023-04-29 11:37:29,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +31: [2023-04-29 11:37:29,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +22: [2023-04-29 11:37:29,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +22: [2023-04-29 11:37:29,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +22: [2023-04-29 11:37:29,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +37: [2023-04-29 11:37:29,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +33: [2023-04-29 11:37:29,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +37: [2023-04-29 11:37:29,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +33: [2023-04-29 11:37:29,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +20: [2023-04-29 11:37:29,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +62: [2023-04-29 11:37:29,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +62: [2023-04-29 11:37:29,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +62: [2023-04-29 11:37:29,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +62: [2023-04-29 11:37:29,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +22: [2023-04-29 11:37:29,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +50: [2023-04-29 11:37:29,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +17: [2023-04-29 11:37:29,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +37: [2023-04-29 11:37:29,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +14: [2023-04-29 11:37:29,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +20: [2023-04-29 11:37:29,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +44: [2023-04-29 11:37:29,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +44: [2023-04-29 11:37:29,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +50: [2023-04-29 11:37:29,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +52: [2023-04-29 11:37:29,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +52: [2023-04-29 11:37:29,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +62: [2023-04-29 11:37:29,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +62: [2023-04-29 11:37:29,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +62: [2023-04-29 11:37:29,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +62: [2023-04-29 11:37:29,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +43: [2023-04-29 11:37:29,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +51: [2023-04-29 11:37:29,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +28: [2023-04-29 11:37:29,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +28: [2023-04-29 11:37:29,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +37: [2023-04-29 11:37:29,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +24: [2023-04-29 11:37:29,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +52: [2023-04-29 11:37:29,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +24: [2023-04-29 11:37:29,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +24: [2023-04-29 11:37:29,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +37: [2023-04-29 11:37:29,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +24: [2023-04-29 11:37:29,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +30: [2023-04-29 11:37:29,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +30: [2023-04-29 11:37:29,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +30: [2023-04-29 11:37:29,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +30: [2023-04-29 11:37:29,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +41: [2023-04-29 11:37:29,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +41: [2023-04-29 11:37:29,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +41: [2023-04-29 11:37:29,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +28: [2023-04-29 11:37:29,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +43: [2023-04-29 11:37:29,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +12: [2023-04-29 11:37:29,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +14: [2023-04-29 11:37:29,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +43: [2023-04-29 11:37:29,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +37: [2023-04-29 11:37:29,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +14: [2023-04-29 11:37:29,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +43: [2023-04-29 11:37:29,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +12: [2023-04-29 11:37:29,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +43: [2023-04-29 11:37:29,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +28: [2023-04-29 11:37:29,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +28: [2023-04-29 11:37:29,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +28: [2023-04-29 11:37:29,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +12: [2023-04-29 11:37:29,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +58: [2023-04-29 11:37:29,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +58: [2023-04-29 11:37:29,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +41: [2023-04-29 11:37:29,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +31: [2023-04-29 11:37:29,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +31: [2023-04-29 11:37:29,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +31: [2023-04-29 11:37:29,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 7: [2023-04-29 11:37:29,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 7: [2023-04-29 11:37:29,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +31: [2023-04-29 11:37:29,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 7: [2023-04-29 11:37:29,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 7: [2023-04-29 11:37:29,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +43: [2023-04-29 11:37:29,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_00-model_states.pt. +28: [2023-04-29 11:37:29,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +43: [2023-04-29 11:37:29,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +12: [2023-04-29 11:37:29,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +33: [2023-04-29 11:37:29,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +11: [2023-04-29 11:37:29,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +58: [2023-04-29 11:37:29,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +58: [2023-04-29 11:37:29,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +28: [2023-04-29 11:37:29,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +51: [2023-04-29 11:37:29,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +51: [2023-04-29 11:37:29,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +43: [2023-04-29 11:37:29,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt... +26: [2023-04-29 11:37:29,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +26: [2023-04-29 11:37:29,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +23: [2023-04-29 11:37:29,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +50: [2023-04-29 11:37:29,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +23: [2023-04-29 11:37:29,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 9: [2023-04-29 11:37:29,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 9: [2023-04-29 11:37:29,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 9: [2023-04-29 11:37:29,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +11: [2023-04-29 11:37:29,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... + 9: [2023-04-29 11:37:29,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +39: [2023-04-29 11:37:29,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +39: [2023-04-29 11:37:29,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +39: [2023-04-29 11:37:29,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +25: [2023-04-29 11:37:29,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +25: [2023-04-29 11:37:29,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +39: [2023-04-29 11:37:29,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +11: [2023-04-29 11:37:29,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +10: [2023-04-29 11:37:29,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +10: [2023-04-29 11:37:29,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +10: [2023-04-29 11:37:29,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +26: [2023-04-29 11:37:29,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +33: [2023-04-29 11:37:29,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +10: [2023-04-29 11:37:29,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +26: [2023-04-29 11:37:29,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +26: [2023-04-29 11:37:29,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +25: [2023-04-29 11:37:29,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +33: [2023-04-29 11:37:29,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +33: [2023-04-29 11:37:29,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +25: [2023-04-29 11:37:29,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +51: [2023-04-29 11:37:29,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +23: [2023-04-29 11:37:29,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +23: [2023-04-29 11:37:29,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +23: [2023-04-29 11:37:29,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +39: [2023-04-29 11:37:29,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +30: [2023-04-29 11:37:29,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +39: [2023-04-29 11:37:29,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +39: [2023-04-29 11:37:29,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +11: [2023-04-29 11:37:29,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +11: [2023-04-29 11:37:29,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +11: [2023-04-29 11:37:29,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +40: [2023-04-29 11:37:29,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +39: [2023-04-29 11:37:29,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +10: [2023-04-29 11:37:29,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +30: [2023-04-29 11:37:29,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +23: [2023-04-29 11:37:29,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +24: [2023-04-29 11:37:29,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +26: [2023-04-29 11:37:29,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +26: [2023-04-29 11:37:29,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +10: [2023-04-29 11:37:29,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +10: [2023-04-29 11:37:29,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +10: [2023-04-29 11:37:29,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +30: [2023-04-29 11:37:29,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +30: [2023-04-29 11:37:29,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +28: [2023-04-29 11:37:29,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +28: [2023-04-29 11:37:29,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +26: [2023-04-29 11:37:29,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +26: [2023-04-29 11:37:29,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +41: [2023-04-29 11:37:29,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +24: [2023-04-29 11:37:29,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +23: [2023-04-29 11:37:29,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +24: [2023-04-29 11:37:29,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +11: [2023-04-29 11:37:29,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +11: [2023-04-29 11:37:29,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +41: [2023-04-29 11:37:29,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +41: [2023-04-29 11:37:29,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +51: [2023-04-29 11:37:29,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +23: [2023-04-29 11:37:29,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +28: [2023-04-29 11:37:29,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +24: [2023-04-29 11:37:29,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +10: [2023-04-29 11:37:29,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +12: [2023-04-29 11:37:29,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 2: [2023-04-29 11:37:29,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 2: [2023-04-29 11:37:29,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +26: [2023-04-29 11:37:29,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +40: [2023-04-29 11:37:29,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +40: [2023-04-29 11:37:29,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +40: [2023-04-29 11:37:29,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +42: [2023-04-29 11:37:29,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +42: [2023-04-29 11:37:29,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +42: [2023-04-29 11:37:29,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +42: [2023-04-29 11:37:29,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +58: [2023-04-29 11:37:29,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +58: [2023-04-29 11:37:29,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +12: [2023-04-29 11:37:29,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +10: [2023-04-29 11:37:29,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +12: [2023-04-29 11:37:29,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +31: [2023-04-29 11:37:29,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +12: [2023-04-29 11:37:29,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +31: [2023-04-29 11:37:29,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +21: [2023-04-29 11:37:29,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +50: [2023-04-29 11:37:29,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +28: [2023-04-29 11:37:29,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 2: [2023-04-29 11:37:29,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 2: [2023-04-29 11:37:29,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +28: [2023-04-29 11:37:29,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +10: [2023-04-29 11:37:29,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +31: [2023-04-29 11:37:29,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +10: [2023-04-29 11:37:29,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +31: [2023-04-29 11:37:29,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +50: [2023-04-29 11:37:29,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +58: [2023-04-29 11:37:29,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 2: [2023-04-29 11:37:29,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 7: [2023-04-29 11:37:29,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +15: [2023-04-29 11:37:29,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +15: [2023-04-29 11:37:29,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +42: [2023-04-29 11:37:29,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 7: [2023-04-29 11:37:29,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 7: [2023-04-29 11:37:29,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +15: [2023-04-29 11:37:29,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +15: [2023-04-29 11:37:29,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +42: [2023-04-29 11:37:29,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 2: [2023-04-29 11:37:29,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +10: [2023-04-29 11:37:29,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +26: [2023-04-29 11:37:29,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +42: [2023-04-29 11:37:29,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +28: [2023-04-29 11:37:29,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +42: [2023-04-29 11:37:29,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +28: [2023-04-29 11:37:29,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +26: [2023-04-29 11:37:29,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 5: [2023-04-29 11:37:29,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 5: [2023-04-29 11:37:29,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +28: [2023-04-29 11:37:29,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +41: [2023-04-29 11:37:29,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +21: [2023-04-29 11:37:29,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +58: [2023-04-29 11:37:29,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +50: [2023-04-29 11:37:29,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 2: [2023-04-29 11:37:29,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 5: [2023-04-29 11:37:29,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 2: [2023-04-29 11:37:29,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 5: [2023-04-29 11:37:29,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +10: [2023-04-29 11:37:29,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +21: [2023-04-29 11:37:29,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +15: [2023-04-29 11:37:29,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 7: [2023-04-29 11:37:29,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +15: [2023-04-29 11:37:29,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +10: [2023-04-29 11:37:29,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +15: [2023-04-29 11:37:29,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +15: [2023-04-29 11:37:29,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +25: [2023-04-29 11:37:29,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +50: [2023-04-29 11:37:29,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +25: [2023-04-29 11:37:29,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +15: [2023-04-29 11:37:29,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +15: [2023-04-29 11:37:29,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +25: [2023-04-29 11:37:29,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +50: [2023-04-29 11:37:29,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +21: [2023-04-29 11:37:29,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +51: [2023-04-29 11:37:29,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 5: [2023-04-29 11:37:29,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +25: [2023-04-29 11:37:29,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 5: [2023-04-29 11:37:29,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +26: [2023-04-29 11:37:29,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +40: [2023-04-29 11:37:29,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +50: [2023-04-29 11:37:29,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +15: [2023-04-29 11:37:29,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +10: [2023-04-29 11:37:29,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +21: [2023-04-29 11:37:29,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +50: [2023-04-29 11:37:29,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. + 5: [2023-04-29 11:37:29,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +51: [2023-04-29 11:37:29,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +15: [2023-04-29 11:37:29,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +24: [2023-04-29 11:37:29,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +24: [2023-04-29 11:37:29,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +26: [2023-04-29 11:37:29,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 5: [2023-04-29 11:37:29,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +51: [2023-04-29 11:37:29,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +46: [2023-04-29 11:37:29,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +46: [2023-04-29 11:37:29,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +46: [2023-04-29 11:37:29,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +46: [2023-04-29 11:37:29,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +21: [2023-04-29 11:37:29,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +50: [2023-04-29 11:37:29,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +62: [2023-04-29 11:37:29,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +62: [2023-04-29 11:37:29,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +21: [2023-04-29 11:37:29,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +24: [2023-04-29 11:37:29,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +40: [2023-04-29 11:37:29,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 9: [2023-04-29 11:37:29,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 9: [2023-04-29 11:37:29,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +62: [2023-04-29 11:37:29,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +24: [2023-04-29 11:37:29,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +13: [2023-04-29 11:37:29,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 1: [2023-04-29 11:37:29,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 1: [2023-04-29 11:37:29,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 1: [2023-04-29 11:37:29,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 9: [2023-04-29 11:37:29,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +13: [2023-04-29 11:37:29,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +13: [2023-04-29 11:37:29,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 1: [2023-04-29 11:37:29,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +40: [2023-04-29 11:37:29,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +13: [2023-04-29 11:37:29,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +13: [2023-04-29 11:37:29,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 9: [2023-04-29 11:37:29,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +13: [2023-04-29 11:37:29,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +13: [2023-04-29 11:37:29,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +13: [2023-04-29 11:37:29,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +40: [2023-04-29 11:37:29,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +15: [2023-04-29 11:37:29,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +62: [2023-04-29 11:37:29,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +21: [2023-04-29 11:37:29,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +26: [2023-04-29 11:37:29,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +26: [2023-04-29 11:37:29,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +19: [2023-04-29 11:37:29,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +19: [2023-04-29 11:37:29,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +13: [2023-04-29 11:37:29,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +19: [2023-04-29 11:37:29,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +13: [2023-04-29 11:37:29,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 9: [2023-04-29 11:37:29,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 9: [2023-04-29 11:37:29,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +19: [2023-04-29 11:37:29,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +19: [2023-04-29 11:37:29,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +13: [2023-04-29 11:37:29,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +15: [2023-04-29 11:37:29,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +19: [2023-04-29 11:37:29,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +19: [2023-04-29 11:37:29,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +19: [2023-04-29 11:37:29,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +13: [2023-04-29 11:37:29,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 9: [2023-04-29 11:37:29,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +15: [2023-04-29 11:37:29,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +13: [2023-04-29 11:37:29,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +50: [2023-04-29 11:37:29,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 9: [2023-04-29 11:37:29,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +13: [2023-04-29 11:37:29,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +13: [2023-04-29 11:37:29,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 9: [2023-04-29 11:37:29,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +13: [2023-04-29 11:37:29,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +19: [2023-04-29 11:37:29,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +19: [2023-04-29 11:37:29,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +15: [2023-04-29 11:37:29,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +19: [2023-04-29 11:37:29,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 3: [2023-04-29 11:37:29,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 3: [2023-04-29 11:37:29,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 3: [2023-04-29 11:37:29,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +30: [2023-04-29 11:37:29,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +24: [2023-04-29 11:37:29,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 3: [2023-04-29 11:37:29,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +19: [2023-04-29 11:37:29,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +19: [2023-04-29 11:37:29,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... + 9: [2023-04-29 11:37:29,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +24: [2023-04-29 11:37:29,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +10: [2023-04-29 11:37:29,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +19: [2023-04-29 11:37:29,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +50: [2023-04-29 11:37:29,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +19: [2023-04-29 11:37:29,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +19: [2023-04-29 11:37:29,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +39: [2023-04-29 11:37:29,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +46: [2023-04-29 11:37:29,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +30: [2023-04-29 11:37:29,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +46: [2023-04-29 11:37:29,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +50: [2023-04-29 11:37:29,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 7: [2023-04-29 11:37:29,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 7: [2023-04-29 11:37:29,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +16: [2023-04-29 11:37:29,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +16: [2023-04-29 11:37:29,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +30: [2023-04-29 11:37:29,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +50: [2023-04-29 11:37:29,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +16: [2023-04-29 11:37:29,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +16: [2023-04-29 11:37:29,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 5: [2023-04-29 11:37:29,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 5: [2023-04-29 11:37:29,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 5: [2023-04-29 11:37:29,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 7: [2023-04-29 11:37:29,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 7: [2023-04-29 11:37:29,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +46: [2023-04-29 11:37:29,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +24: [2023-04-29 11:37:29,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 5: [2023-04-29 11:37:29,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +50: [2023-04-29 11:37:29,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +62: [2023-04-29 11:37:29,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +62: [2023-04-29 11:37:29,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +39: [2023-04-29 11:37:29,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. + 9: [2023-04-29 11:37:29,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 9: [2023-04-29 11:37:29,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 9: [2023-04-29 11:37:29,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +16: [2023-04-29 11:37:29,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +49: [2023-04-29 11:37:29,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +49: [2023-04-29 11:37:29,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +49: [2023-04-29 11:37:29,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +16: [2023-04-29 11:37:29,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +46: [2023-04-29 11:37:29,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +49: [2023-04-29 11:37:29,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +30: [2023-04-29 11:37:29,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +39: [2023-04-29 11:37:29,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +39: [2023-04-29 11:37:29,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. + 1: [2023-04-29 11:37:29,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 1: [2023-04-29 11:37:29,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 7: [2023-04-29 11:37:29,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 7: [2023-04-29 11:37:29,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 7: [2023-04-29 11:37:29,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +24: [2023-04-29 11:37:29,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +16: [2023-04-29 11:37:29,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +16: [2023-04-29 11:37:29,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +50: [2023-04-29 11:37:29,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... + 1: [2023-04-29 11:37:29,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 1: [2023-04-29 11:37:29,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +50: [2023-04-29 11:37:29,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +10: [2023-04-29 11:37:29,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +10: [2023-04-29 11:37:29,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +30: [2023-04-29 11:37:29,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +30: [2023-04-29 11:37:29,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 9: [2023-04-29 11:37:29,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... + 9: [2023-04-29 11:37:29,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... + 9: [2023-04-29 11:37:29,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +62: [2023-04-29 11:37:29,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +62: [2023-04-29 11:37:29,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 7: [2023-04-29 11:37:29,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +10: [2023-04-29 11:37:29,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +24: [2023-04-29 11:37:29,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +16: [2023-04-29 11:37:29,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +16: [2023-04-29 11:37:29,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +31: [2023-04-29 11:37:29,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 1: [2023-04-29 11:37:29,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 1: [2023-04-29 11:37:29,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 1: [2023-04-29 11:37:29,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 1: [2023-04-29 11:37:29,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +28: [2023-04-29 11:37:29,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +30: [2023-04-29 11:37:29,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +30: [2023-04-29 11:37:29,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +16: [2023-04-29 11:37:29,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +24: [2023-04-29 11:37:29,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +29: [2023-04-29 11:37:29,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +29: [2023-04-29 11:37:29,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 7: [2023-04-29 11:37:29,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +29: [2023-04-29 11:37:29,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +25: [2023-04-29 11:37:29,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +25: [2023-04-29 11:37:29,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +29: [2023-04-29 11:37:29,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +25: [2023-04-29 11:37:29,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +25: [2023-04-29 11:37:29,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 3: [2023-04-29 11:37:29,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +39: [2023-04-29 11:37:29,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +16: [2023-04-29 11:37:29,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 1: [2023-04-29 11:37:29,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 3: [2023-04-29 11:37:29,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 3: [2023-04-29 11:37:29,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +31: [2023-04-29 11:37:29,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +28: [2023-04-29 11:37:29,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +28: [2023-04-29 11:37:29,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... + 3: [2023-04-29 11:37:29,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +31: [2023-04-29 11:37:29,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +31: [2023-04-29 11:37:29,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +31: [2023-04-29 11:37:29,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 1: [2023-04-29 11:37:29,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 1: [2023-04-29 11:37:29,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 1: [2023-04-29 11:37:29,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +25: [2023-04-29 11:37:29,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 7: [2023-04-29 11:37:29,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +42: [2023-04-29 11:37:29,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +42: [2023-04-29 11:37:29,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +42: [2023-04-29 11:37:29,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +25: [2023-04-29 11:37:29,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 2: [2023-04-29 11:37:29,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +25: [2023-04-29 11:37:29,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +25: [2023-04-29 11:37:29,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +28: [2023-04-29 11:37:29,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +42: [2023-04-29 11:37:29,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +24: [2023-04-29 11:37:29,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +24: [2023-04-29 11:37:29,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +25: [2023-04-29 11:37:29,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 2: [2023-04-29 11:37:29,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 7: [2023-04-29 11:37:29,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +35: [2023-04-29 11:37:29,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +35: [2023-04-29 11:37:29,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +31: [2023-04-29 11:37:29,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +28: [2023-04-29 11:37:29,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +28: [2023-04-29 11:37:29,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +16: [2023-04-29 11:37:29,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +10: [2023-04-29 11:37:29,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +31: [2023-04-29 11:37:29,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +31: [2023-04-29 11:37:29,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +24: [2023-04-29 11:37:29,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +49: [2023-04-29 11:37:29,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +35: [2023-04-29 11:37:29,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +35: [2023-04-29 11:37:29,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. + 2: [2023-04-29 11:37:29,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 2: [2023-04-29 11:37:29,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +25: [2023-04-29 11:37:29,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... + 7: [2023-04-29 11:37:29,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 5: [2023-04-29 11:37:29,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +16: [2023-04-29 11:37:29,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +49: [2023-04-29 11:37:29,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 7: [2023-04-29 11:37:29,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +24: [2023-04-29 11:37:29,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +28: [2023-04-29 11:37:29,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +35: [2023-04-29 11:37:29,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +35: [2023-04-29 11:37:29,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +28: [2023-04-29 11:37:29,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... + 5: [2023-04-29 11:37:29,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +24: [2023-04-29 11:37:29,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... + 7: [2023-04-29 11:37:29,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +24: [2023-04-29 11:37:29,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +49: [2023-04-29 11:37:29,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +49: [2023-04-29 11:37:29,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +35: [2023-04-29 11:37:29,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +25: [2023-04-29 11:37:29,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +39: [2023-04-29 11:37:29,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +39: [2023-04-29 11:37:29,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +39: [2023-04-29 11:37:29,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +25: [2023-04-29 11:37:29,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 5: [2023-04-29 11:37:29,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 5: [2023-04-29 11:37:29,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +35: [2023-04-29 11:37:29,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 7: [2023-04-29 11:37:29,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... + 7: [2023-04-29 11:37:29,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +25: [2023-04-29 11:37:29,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +25: [2023-04-29 11:37:29,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +25: [2023-04-29 11:37:29,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +60: [2023-04-29 11:37:29,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +60: [2023-04-29 11:37:29,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +13: [2023-04-29 11:37:29,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +10: [2023-04-29 11:37:29,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +10: [2023-04-29 11:37:29,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +29: [2023-04-29 11:37:29,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +10: [2023-04-29 11:37:29,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +60: [2023-04-29 11:37:29,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +25: [2023-04-29 11:37:29,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +15: [2023-04-29 11:37:29,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +16: [2023-04-29 11:37:29,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +32: [2023-04-29 11:37:29,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +32: [2023-04-29 11:37:29,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. + 5: [2023-04-29 11:37:29,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +29: [2023-04-29 11:37:29,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +32: [2023-04-29 11:37:29,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +32: [2023-04-29 11:37:29,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +60: [2023-04-29 11:37:29,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +60: [2023-04-29 11:37:29,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +60: [2023-04-29 11:37:29,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +60: [2023-04-29 11:37:29,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +16: [2023-04-29 11:37:29,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +15: [2023-04-29 11:37:29,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +15: [2023-04-29 11:37:29,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +29: [2023-04-29 11:37:29,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +29: [2023-04-29 11:37:29,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +13: [2023-04-29 11:37:29,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +13: [2023-04-29 11:37:29,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 5: [2023-04-29 11:37:29,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 5: [2023-04-29 11:37:29,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 5: [2023-04-29 11:37:29,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 9: [2023-04-29 11:37:29,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 9: [2023-04-29 11:37:29,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +51: [2023-04-29 11:37:29,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +51: [2023-04-29 11:37:29,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +51: [2023-04-29 11:37:29,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +60: [2023-04-29 11:37:29,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 2: [2023-04-29 11:37:29,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +51: [2023-04-29 11:37:29,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +42: [2023-04-29 11:37:29,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +46: [2023-04-29 11:37:29,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +42: [2023-04-29 11:37:29,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +19: [2023-04-29 11:37:29,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +19: [2023-04-29 11:37:29,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +19: [2023-04-29 11:37:29,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +15: [2023-04-29 11:37:29,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +15: [2023-04-29 11:37:29,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +42: [2023-04-29 11:37:29,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 9: [2023-04-29 11:37:29,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +42: [2023-04-29 11:37:29,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +38: [2023-04-29 11:37:29,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +38: [2023-04-29 11:37:29,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +38: [2023-04-29 11:37:29,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +38: [2023-04-29 11:37:29,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. + 2: [2023-04-29 11:37:29,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 9: [2023-04-29 11:37:29,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +19: [2023-04-29 11:37:29,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +46: [2023-04-29 11:37:29,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +13: [2023-04-29 11:37:29,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +53: [2023-04-29 11:37:29,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +53: [2023-04-29 11:37:29,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +53: [2023-04-29 11:37:29,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +53: [2023-04-29 11:37:29,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +46: [2023-04-29 11:37:29,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 2: [2023-04-29 11:37:29,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 2: [2023-04-29 11:37:29,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +38: [2023-04-29 11:37:29,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +38: [2023-04-29 11:37:29,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +15: [2023-04-29 11:37:29,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +38: [2023-04-29 11:37:29,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +38: [2023-04-29 11:37:29,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +53: [2023-04-29 11:37:29,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +46: [2023-04-29 11:37:29,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +53: [2023-04-29 11:37:29,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +53: [2023-04-29 11:37:29,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +53: [2023-04-29 11:37:29,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +15: [2023-04-29 11:37:29,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +13: [2023-04-29 11:37:29,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +32: [2023-04-29 11:37:29,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 1: [2023-04-29 11:37:29,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +32: [2023-04-29 11:37:29,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +46: [2023-04-29 11:37:29,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 7: [2023-04-29 11:37:29,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +13: [2023-04-29 11:37:29,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +32: [2023-04-29 11:37:29,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +32: [2023-04-29 11:37:29,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +25: [2023-04-29 11:37:29,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +46: [2023-04-29 11:37:29,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +13: [2023-04-29 11:37:29,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +15: [2023-04-29 11:37:29,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +15: [2023-04-29 11:37:29,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... + 1: [2023-04-29 11:37:29,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 1: [2023-04-29 11:37:29,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 1: [2023-04-29 11:37:29,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +46: [2023-04-29 11:37:29,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +15: [2023-04-29 11:37:29,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +15: [2023-04-29 11:37:29,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +19: [2023-04-29 11:37:29,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 7: [2023-04-29 11:37:29,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +19: [2023-04-29 11:37:29,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +49: [2023-04-29 11:37:29,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. + 7: [2023-04-29 11:37:29,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 9: [2023-04-29 11:37:29,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +33: [2023-04-29 11:37:29,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +33: [2023-04-29 11:37:29,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. + 9: [2023-04-29 11:37:29,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 1: [2023-04-29 11:37:29,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 1: [2023-04-29 11:37:29,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +15: [2023-04-29 11:37:29,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +33: [2023-04-29 11:37:29,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +51: [2023-04-29 11:37:29,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +33: [2023-04-29 11:37:29,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +19: [2023-04-29 11:37:29,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +46: [2023-04-29 11:37:29,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... + 5: [2023-04-29 11:37:29,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 7: [2023-04-29 11:37:29,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +49: [2023-04-29 11:37:29,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +15: [2023-04-29 11:37:29,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 3: [2023-04-29 11:37:29,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +51: [2023-04-29 11:37:29,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +15: [2023-04-29 11:37:29,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 1: [2023-04-29 11:37:29,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 1: [2023-04-29 11:37:29,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... + 1: [2023-04-29 11:37:29,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... + 3: [2023-04-29 11:37:29,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +15: [2023-04-29 11:37:29,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... + 9: [2023-04-29 11:37:29,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 5: [2023-04-29 11:37:29,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +19: [2023-04-29 11:37:29,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 3: [2023-04-29 11:37:29,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 5: [2023-04-29 11:37:29,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +25: [2023-04-29 11:37:29,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 1: [2023-04-29 11:37:29,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +15: [2023-04-29 11:37:29,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +51: [2023-04-29 11:37:29,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +51: [2023-04-29 11:37:29,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 5: [2023-04-29 11:37:29,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +13: [2023-04-29 11:37:29,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 9: [2023-04-29 11:37:29,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 3: [2023-04-29 11:37:29,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... + 3: [2023-04-29 11:37:29,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 3: [2023-04-29 11:37:29,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... + 3: [2023-04-29 11:37:29,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +35: [2023-04-29 11:37:29,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +49: [2023-04-29 11:37:29,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. + 3: [2023-04-29 11:37:29,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +42: [2023-04-29 11:37:29,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +42: [2023-04-29 11:37:29,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +42: [2023-04-29 11:37:29,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. + 1: [2023-04-29 11:37:29,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +16: [2023-04-29 11:37:29,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +63: [2023-04-29 11:37:29,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +63: [2023-04-29 11:37:29,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +60: [2023-04-29 11:37:29,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +60: [2023-04-29 11:37:29,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +60: [2023-04-29 11:37:29,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +42: [2023-04-29 11:37:29,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +48: [2023-04-29 11:37:29,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +48: [2023-04-29 11:37:29,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +60: [2023-04-29 11:37:29,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +25: [2023-04-29 11:37:29,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 1: [2023-04-29 11:37:29,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +48: [2023-04-29 11:37:29,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +25: [2023-04-29 11:37:29,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +63: [2023-04-29 11:37:29,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +48: [2023-04-29 11:37:29,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +16: [2023-04-29 11:37:29,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +63: [2023-04-29 11:37:29,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. + 5: [2023-04-29 11:37:29,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +35: [2023-04-29 11:37:29,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +49: [2023-04-29 11:37:29,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +25: [2023-04-29 11:37:29,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +47: [2023-04-29 11:37:29,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +47: [2023-04-29 11:37:29,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +47: [2023-04-29 11:37:29,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +47: [2023-04-29 11:37:29,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. + 7: [2023-04-29 11:37:29,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +16: [2023-04-29 11:37:29,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... + 2: [2023-04-29 11:37:29,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 2: [2023-04-29 11:37:29,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +60: [2023-04-29 11:37:29,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +49: [2023-04-29 11:37:29,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +16: [2023-04-29 11:37:29,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +63: [2023-04-29 11:37:29,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +63: [2023-04-29 11:37:29,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +44: [2023-04-29 11:37:29,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +44: [2023-04-29 11:37:29,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +63: [2023-04-29 11:37:29,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 2: [2023-04-29 11:37:29,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. + 2: [2023-04-29 11:37:29,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_09-model_01-model_states.pt. +29: [2023-04-29 11:37:29,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +49: [2023-04-29 11:37:29,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. + 5: [2023-04-29 11:37:29,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +47: [2023-04-29 11:37:29,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +63: [2023-04-29 11:37:29,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +47: [2023-04-29 11:37:29,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +33: [2023-04-29 11:37:29,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +44: [2023-04-29 11:37:29,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +44: [2023-04-29 11:37:29,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +47: [2023-04-29 11:37:29,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +59: [2023-04-29 11:37:29,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +59: [2023-04-29 11:37:29,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +59: [2023-04-29 11:37:29,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +59: [2023-04-29 11:37:29,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +47: [2023-04-29 11:37:29,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +32: [2023-04-29 11:37:29,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +32: [2023-04-29 11:37:29,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 1: [2023-04-29 11:37:29,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +49: [2023-04-29 11:37:29,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +33: [2023-04-29 11:37:29,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +29: [2023-04-29 11:37:29,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... + 5: [2023-04-29 11:37:29,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +60: [2023-04-29 11:37:29,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +33: [2023-04-29 11:37:29,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +33: [2023-04-29 11:37:29,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +49: [2023-04-29 11:37:29,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... + 1: [2023-04-29 11:37:29,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +29: [2023-04-29 11:37:29,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +35: [2023-04-29 11:37:29,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +32: [2023-04-29 11:37:29,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +32: [2023-04-29 11:37:29,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 7: [2023-04-29 11:37:29,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +59: [2023-04-29 11:37:29,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +29: [2023-04-29 11:37:29,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 7: [2023-04-29 11:37:29,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +59: [2023-04-29 11:37:29,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 5: [2023-04-29 11:37:29,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +32: [2023-04-29 11:37:29,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +59: [2023-04-29 11:37:29,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +32: [2023-04-29 11:37:29,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 7: [2023-04-29 11:37:29,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +59: [2023-04-29 11:37:29,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +54: [2023-04-29 11:37:29,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +54: [2023-04-29 11:37:29,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +54: [2023-04-29 11:37:29,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +16: [2023-04-29 11:37:29,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +16: [2023-04-29 11:37:29,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +16: [2023-04-29 11:37:29,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +29: [2023-04-29 11:37:29,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +25: [2023-04-29 11:37:29,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +16: [2023-04-29 11:37:29,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +35: [2023-04-29 11:37:29,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +35: [2023-04-29 11:37:29,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. + 5: [2023-04-29 11:37:29,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +29: [2023-04-29 11:37:29,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... + 5: [2023-04-29 11:37:29,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +54: [2023-04-29 11:37:29,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +35: [2023-04-29 11:37:29,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +35: [2023-04-29 11:37:29,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +32: [2023-04-29 11:37:29,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +29: [2023-04-29 11:37:29,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +42: [2023-04-29 11:37:29,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +32: [2023-04-29 11:37:29,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 5: [2023-04-29 11:37:29,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +38: [2023-04-29 11:37:29,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +38: [2023-04-29 11:37:29,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +38: [2023-04-29 11:37:29,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +38: [2023-04-29 11:37:29,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. + 5: [2023-04-29 11:37:29,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +60: [2023-04-29 11:37:29,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +60: [2023-04-29 11:37:29,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +35: [2023-04-29 11:37:29,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +58: [2023-04-29 11:37:29,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +58: [2023-04-29 11:37:29,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +58: [2023-04-29 11:37:29,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +58: [2023-04-29 11:37:29,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +35: [2023-04-29 11:37:29,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +29: [2023-04-29 11:37:29,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +35: [2023-04-29 11:37:29,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +48: [2023-04-29 11:37:29,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +25: [2023-04-29 11:37:29,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +36: [2023-04-29 11:37:29,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +36: [2023-04-29 11:37:29,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +36: [2023-04-29 11:37:29,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. + 4: [2023-04-29 11:37:29,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 4: [2023-04-29 11:37:29,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 4: [2023-04-29 11:37:29,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +36: [2023-04-29 11:37:29,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. + 4: [2023-04-29 11:37:29,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +60: [2023-04-29 11:37:29,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 2: [2023-04-29 11:37:29,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +48: [2023-04-29 11:37:29,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +42: [2023-04-29 11:37:29,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +48: [2023-04-29 11:37:29,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +42: [2023-04-29 11:37:29,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +48: [2023-04-29 11:37:29,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 1: [2023-04-29 11:37:29,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 2: [2023-04-29 11:37:29,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 4: [2023-04-29 11:37:29,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +60: [2023-04-29 11:37:29,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +25: [2023-04-29 11:37:29,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +38: [2023-04-29 11:37:29,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +44: [2023-04-29 11:37:29,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +44: [2023-04-29 11:37:29,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 1: [2023-04-29 11:37:29,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +42: [2023-04-29 11:37:29,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 2: [2023-04-29 11:37:29,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... +60: [2023-04-29 11:37:29,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +36: [2023-04-29 11:37:29,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +36: [2023-04-29 11:37:29,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +36: [2023-04-29 11:37:29,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 2: [2023-04-29 11:37:29,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt... + 4: [2023-04-29 11:37:29,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 4: [2023-04-29 11:37:29,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +32: [2023-04-29 11:37:29,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +36: [2023-04-29 11:37:29,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 4: [2023-04-29 11:37:29,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +44: [2023-04-29 11:37:29,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +60: [2023-04-29 11:37:29,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +53: [2023-04-29 11:37:29,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +60: [2023-04-29 11:37:29,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +16: [2023-04-29 11:37:29,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +38: [2023-04-29 11:37:29,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +38: [2023-04-29 11:37:29,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +32: [2023-04-29 11:37:29,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +44: [2023-04-29 11:37:29,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +38: [2023-04-29 11:37:29,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +53: [2023-04-29 11:37:29,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +53: [2023-04-29 11:37:29,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +53: [2023-04-29 11:37:29,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +32: [2023-04-29 11:37:29,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +41: [2023-04-29 11:37:29,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +41: [2023-04-29 11:37:29,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +30: [2023-04-29 11:37:29,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +30: [2023-04-29 11:37:29,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +32: [2023-04-29 11:37:29,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +54: [2023-04-29 11:37:29,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +41: [2023-04-29 11:37:29,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +41: [2023-04-29 11:37:29,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +16: [2023-04-29 11:37:29,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +30: [2023-04-29 11:37:29,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +30: [2023-04-29 11:37:29,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +60: [2023-04-29 11:37:29,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +54: [2023-04-29 11:37:29,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +35: [2023-04-29 11:37:29,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +35: [2023-04-29 11:37:29,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +30: [2023-04-29 11:37:29,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +30: [2023-04-29 11:37:29,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +54: [2023-04-29 11:37:29,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +41: [2023-04-29 11:37:29,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +51: [2023-04-29 11:37:29,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +30: [2023-04-29 11:37:29,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +41: [2023-04-29 11:37:29,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +30: [2023-04-29 11:37:29,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +41: [2023-04-29 11:37:29,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +54: [2023-04-29 11:37:29,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +35: [2023-04-29 11:37:29,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +41: [2023-04-29 11:37:29,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +58: [2023-04-29 11:37:29,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +35: [2023-04-29 11:37:29,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +51: [2023-04-29 11:37:29,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +35: [2023-04-29 11:37:29,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +16: [2023-04-29 11:37:29,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +16: [2023-04-29 11:37:29,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +51: [2023-04-29 11:37:29,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +60: [2023-04-29 11:37:29,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +58: [2023-04-29 11:37:29,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +58: [2023-04-29 11:37:29,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +58: [2023-04-29 11:37:29,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +38: [2023-04-29 11:37:29,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +32: [2023-04-29 11:37:29,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +60: [2023-04-29 11:37:29,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +16: [2023-04-29 11:37:29,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +16: [2023-04-29 11:37:29,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +51: [2023-04-29 11:37:29,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +32: [2023-04-29 11:37:29,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +53: [2023-04-29 11:37:29,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +51: [2023-04-29 11:37:29,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +38: [2023-04-29 11:37:29,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +51: [2023-04-29 11:37:29,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +51: [2023-04-29 11:37:29,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +51: [2023-04-29 11:37:29,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +16: [2023-04-29 11:37:29,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +38: [2023-04-29 11:37:29,999] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +35: [2023-04-29 11:37:29,999] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +51: [2023-04-29 11:37:30,000] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +51: [2023-04-29 11:37:30,000] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +38: [2023-04-29 11:37:30,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +32: [2023-04-29 11:37:30,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +53: [2023-04-29 11:37:30,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +53: [2023-04-29 11:37:30,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +53: [2023-04-29 11:37:30,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +59: [2023-04-29 11:37:30,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +47: [2023-04-29 11:37:30,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +47: [2023-04-29 11:37:30,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +47: [2023-04-29 11:37:30,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +47: [2023-04-29 11:37:30,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +38: [2023-04-29 11:37:30,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +32: [2023-04-29 11:37:30,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +63: [2023-04-29 11:37:30,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +16: [2023-04-29 11:37:30,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +47: [2023-04-29 11:37:30,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +20: [2023-04-29 11:37:30,006] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +20: [2023-04-29 11:37:30,006] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +20: [2023-04-29 11:37:30,006] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +53: [2023-04-29 11:37:30,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +20: [2023-04-29 11:37:30,006] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +53: [2023-04-29 11:37:30,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +53: [2023-04-29 11:37:30,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +53: [2023-04-29 11:37:30,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +63: [2023-04-29 11:37:30,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +63: [2023-04-29 11:37:30,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +33: [2023-04-29 11:37:30,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +51: [2023-04-29 11:37:30,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +51: [2023-04-29 11:37:30,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +63: [2023-04-29 11:37:30,009] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +51: [2023-04-29 11:37:30,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +51: [2023-04-29 11:37:30,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +38: [2023-04-29 11:37:30,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +38: [2023-04-29 11:37:30,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +20: [2023-04-29 11:37:30,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +20: [2023-04-29 11:37:30,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +20: [2023-04-29 11:37:30,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +20: [2023-04-29 11:37:30,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +51: [2023-04-29 11:37:30,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +47: [2023-04-29 11:37:30,013] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +47: [2023-04-29 11:37:30,013] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +33: [2023-04-29 11:37:30,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +59: [2023-04-29 11:37:30,013] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +42: [2023-04-29 11:37:30,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +38: [2023-04-29 11:37:30,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +49: [2023-04-29 11:37:30,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +49: [2023-04-29 11:37:30,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +49: [2023-04-29 11:37:30,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +51: [2023-04-29 11:37:30,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +49: [2023-04-29 11:37:30,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +59: [2023-04-29 11:37:30,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 4: [2023-04-29 11:37:30,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +33: [2023-04-29 11:37:30,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +33: [2023-04-29 11:37:30,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +33: [2023-04-29 11:37:30,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +42: [2023-04-29 11:37:30,019] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +49: [2023-04-29 11:37:30,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +59: [2023-04-29 11:37:30,020] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +49: [2023-04-29 11:37:30,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +32: [2023-04-29 11:37:30,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +49: [2023-04-29 11:37:30,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +49: [2023-04-29 11:37:30,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +32: [2023-04-29 11:37:30,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +36: [2023-04-29 11:37:30,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +37: [2023-04-29 11:37:30,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +37: [2023-04-29 11:37:30,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +37: [2023-04-29 11:37:30,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +37: [2023-04-29 11:37:30,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +33: [2023-04-29 11:37:30,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +37: [2023-04-29 11:37:30,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +37: [2023-04-29 11:37:30,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +37: [2023-04-29 11:37:30,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +48: [2023-04-29 11:37:30,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 2: [2023-04-29 11:37:30,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +37: [2023-04-29 11:37:30,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +50: [2023-04-29 11:37:30,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +33: [2023-04-29 11:37:30,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +50: [2023-04-29 11:37:30,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +33: [2023-04-29 11:37:30,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +63: [2023-04-29 11:37:30,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +47: [2023-04-29 11:37:30,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +32: [2023-04-29 11:37:30,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +53: [2023-04-29 11:37:30,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 2: [2023-04-29 11:37:30,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +53: [2023-04-29 11:37:30,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +57: [2023-04-29 11:37:30,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +57: [2023-04-29 11:37:30,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +57: [2023-04-29 11:37:30,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +53: [2023-04-29 11:37:30,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +57: [2023-04-29 11:37:30,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +37: [2023-04-29 11:37:30,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +48: [2023-04-29 11:37:30,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +50: [2023-04-29 11:37:30,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +50: [2023-04-29 11:37:30,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +47: [2023-04-29 11:37:30,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +59: [2023-04-29 11:37:30,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 2: [2023-04-29 11:37:30,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. + 2: [2023-04-29 11:37:30,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +53: [2023-04-29 11:37:30,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +47: [2023-04-29 11:37:30,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +37: [2023-04-29 11:37:30,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +57: [2023-04-29 11:37:30,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +48: [2023-04-29 11:37:30,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 2: [2023-04-29 11:37:30,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_00-model_states.pt. +37: [2023-04-29 11:37:30,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +37: [2023-04-29 11:37:30,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +57: [2023-04-29 11:37:30,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +36: [2023-04-29 11:37:30,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +36: [2023-04-29 11:37:30,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +63: [2023-04-29 11:37:30,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +63: [2023-04-29 11:37:30,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +57: [2023-04-29 11:37:30,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +57: [2023-04-29 11:37:30,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +44: [2023-04-29 11:37:30,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +44: [2023-04-29 11:37:30,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +47: [2023-04-29 11:37:30,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +48: [2023-04-29 11:37:30,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +48: [2023-04-29 11:37:30,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 2: [2023-04-29 11:37:30,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... + 2: [2023-04-29 11:37:30,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +63: [2023-04-29 11:37:30,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +42: [2023-04-29 11:37:30,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +42: [2023-04-29 11:37:30,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +32: [2023-04-29 11:37:30,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +47: [2023-04-29 11:37:30,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +47: [2023-04-29 11:37:30,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +60: [2023-04-29 11:37:30,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. + 2: [2023-04-29 11:37:30,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt... +44: [2023-04-29 11:37:30,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +44: [2023-04-29 11:37:30,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +36: [2023-04-29 11:37:30,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +48: [2023-04-29 11:37:30,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +47: [2023-04-29 11:37:30,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 4: [2023-04-29 11:37:30,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 4: [2023-04-29 11:37:30,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 4: [2023-04-29 11:37:30,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +44: [2023-04-29 11:37:30,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +44: [2023-04-29 11:37:30,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... + 4: [2023-04-29 11:37:30,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +35: [2023-04-29 11:37:30,044] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +48: [2023-04-29 11:37:30,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +42: [2023-04-29 11:37:30,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +54: [2023-04-29 11:37:30,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +47: [2023-04-29 11:37:30,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +48: [2023-04-29 11:37:30,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +59: [2023-04-29 11:37:30,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +60: [2023-04-29 11:37:30,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +60: [2023-04-29 11:37:30,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +42: [2023-04-29 11:37:30,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +60: [2023-04-29 11:37:30,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +42: [2023-04-29 11:37:30,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +44: [2023-04-29 11:37:30,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +44: [2023-04-29 11:37:30,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +30: [2023-04-29 11:37:30,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +59: [2023-04-29 11:37:30,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +37: [2023-04-29 11:37:30,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +60: [2023-04-29 11:37:30,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +35: [2023-04-29 11:37:30,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +30: [2023-04-29 11:37:30,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +30: [2023-04-29 11:37:30,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +21: [2023-04-29 11:37:30,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +21: [2023-04-29 11:37:30,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +21: [2023-04-29 11:37:30,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +21: [2023-04-29 11:37:30,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +54: [2023-04-29 11:37:30,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +32: [2023-04-29 11:37:30,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +59: [2023-04-29 11:37:30,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +34: [2023-04-29 11:37:30,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +34: [2023-04-29 11:37:30,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +32: [2023-04-29 11:37:30,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +34: [2023-04-29 11:37:30,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +30: [2023-04-29 11:37:30,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +36: [2023-04-29 11:37:30,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +34: [2023-04-29 11:37:30,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +58: [2023-04-29 11:37:30,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +60: [2023-04-29 11:37:30,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +60: [2023-04-29 11:37:30,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +54: [2023-04-29 11:37:30,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +41: [2023-04-29 11:37:30,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +35: [2023-04-29 11:37:30,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +21: [2023-04-29 11:37:30,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +41: [2023-04-29 11:37:30,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +60: [2023-04-29 11:37:30,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +42: [2023-04-29 11:37:30,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +50: [2023-04-29 11:37:30,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +50: [2023-04-29 11:37:30,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +21: [2023-04-29 11:37:30,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +21: [2023-04-29 11:37:30,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +21: [2023-04-29 11:37:30,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +58: [2023-04-29 11:37:30,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +58: [2023-04-29 11:37:30,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +32: [2023-04-29 11:37:30,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +58: [2023-04-29 11:37:30,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +54: [2023-04-29 11:37:30,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +55: [2023-04-29 11:37:30,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +55: [2023-04-29 11:37:30,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +55: [2023-04-29 11:37:30,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +39: [2023-04-29 11:37:30,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +39: [2023-04-29 11:37:30,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +55: [2023-04-29 11:37:30,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +35: [2023-04-29 11:37:30,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +58: [2023-04-29 11:37:30,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +39: [2023-04-29 11:37:30,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +54: [2023-04-29 11:37:30,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +39: [2023-04-29 11:37:30,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +43: [2023-04-29 11:37:30,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +58: [2023-04-29 11:37:30,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +43: [2023-04-29 11:37:30,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +43: [2023-04-29 11:37:30,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +43: [2023-04-29 11:37:30,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +55: [2023-04-29 11:37:30,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +38: [2023-04-29 11:37:30,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +41: [2023-04-29 11:37:30,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +36: [2023-04-29 11:37:30,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +37: [2023-04-29 11:37:30,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +37: [2023-04-29 11:37:30,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +41: [2023-04-29 11:37:30,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +58: [2023-04-29 11:37:30,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +50: [2023-04-29 11:37:30,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +55: [2023-04-29 11:37:30,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 0: [2023-04-29 11:37:30,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. + 0: [2023-04-29 11:37:30,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +55: [2023-04-29 11:37:30,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 0: [2023-04-29 11:37:30,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +39: [2023-04-29 11:37:30,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +39: [2023-04-29 11:37:30,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +39: [2023-04-29 11:37:30,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +37: [2023-04-29 11:37:30,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +55: [2023-04-29 11:37:30,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 0: [2023-04-29 11:37:30,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +39: [2023-04-29 11:37:30,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +58: [2023-04-29 11:37:30,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +35: [2023-04-29 11:37:30,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +35: [2023-04-29 11:37:30,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +43: [2023-04-29 11:37:30,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +36: [2023-04-29 11:37:30,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +54: [2023-04-29 11:37:30,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +38: [2023-04-29 11:37:30,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +43: [2023-04-29 11:37:30,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +43: [2023-04-29 11:37:30,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +50: [2023-04-29 11:37:30,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +43: [2023-04-29 11:37:30,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +32: [2023-04-29 11:37:30,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +54: [2023-04-29 11:37:30,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +20: [2023-04-29 11:37:30,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +38: [2023-04-29 11:37:30,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +47: [2023-04-29 11:37:30,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +56: [2023-04-29 11:37:30,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +56: [2023-04-29 11:37:30,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +56: [2023-04-29 11:37:30,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +56: [2023-04-29 11:37:30,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +35: [2023-04-29 11:37:30,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +35: [2023-04-29 11:37:30,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +38: [2023-04-29 11:37:30,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +62: [2023-04-29 11:37:30,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +62: [2023-04-29 11:37:30,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +62: [2023-04-29 11:37:30,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +62: [2023-04-29 11:37:30,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. + 4: [2023-04-29 11:37:30,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 4: [2023-04-29 11:37:30,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +54: [2023-04-29 11:37:30,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +36: [2023-04-29 11:37:30,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +34: [2023-04-29 11:37:30,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 4: [2023-04-29 11:37:30,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +30: [2023-04-29 11:37:30,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +30: [2023-04-29 11:37:30,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +38: [2023-04-29 11:37:30,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +20: [2023-04-29 11:37:30,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +34: [2023-04-29 11:37:30,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +34: [2023-04-29 11:37:30,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +41: [2023-04-29 11:37:30,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +30: [2023-04-29 11:37:30,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +30: [2023-04-29 11:37:30,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +38: [2023-04-29 11:37:30,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +20: [2023-04-29 11:37:30,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +41: [2023-04-29 11:37:30,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +34: [2023-04-29 11:37:30,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +51: [2023-04-29 11:37:30,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +38: [2023-04-29 11:37:30,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +20: [2023-04-29 11:37:30,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +38: [2023-04-29 11:37:30,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +53: [2023-04-29 11:37:30,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +20: [2023-04-29 11:37:30,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 0: [2023-04-29 11:37:30,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 0: [2023-04-29 11:37:30,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 0: [2023-04-29 11:37:30,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 0: [2023-04-29 11:37:30,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +51: [2023-04-29 11:37:30,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +53: [2023-04-29 11:37:30,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +57: [2023-04-29 11:37:30,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +41: [2023-04-29 11:37:30,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +49: [2023-04-29 11:37:30,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +41: [2023-04-29 11:37:30,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +56: [2023-04-29 11:37:30,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +56: [2023-04-29 11:37:30,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +56: [2023-04-29 11:37:30,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +51: [2023-04-29 11:37:30,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +37: [2023-04-29 11:37:30,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +53: [2023-04-29 11:37:30,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +56: [2023-04-29 11:37:30,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +51: [2023-04-29 11:37:30,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +57: [2023-04-29 11:37:30,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +47: [2023-04-29 11:37:30,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +49: [2023-04-29 11:37:30,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +45: [2023-04-29 11:37:30,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +45: [2023-04-29 11:37:30,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +45: [2023-04-29 11:37:30,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +45: [2023-04-29 11:37:30,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +53: [2023-04-29 11:37:30,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +57: [2023-04-29 11:37:30,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +57: [2023-04-29 11:37:30,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +48: [2023-04-29 11:37:30,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +48: [2023-04-29 11:37:30,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +49: [2023-04-29 11:37:30,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +47: [2023-04-29 11:37:30,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +53: [2023-04-29 11:37:30,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +20: [2023-04-29 11:37:30,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +53: [2023-04-29 11:37:30,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +45: [2023-04-29 11:37:30,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +37: [2023-04-29 11:37:30,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +42: [2023-04-29 11:37:30,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +42: [2023-04-29 11:37:30,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +48: [2023-04-29 11:37:30,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +45: [2023-04-29 11:37:30,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +48: [2023-04-29 11:37:30,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +47: [2023-04-29 11:37:30,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +45: [2023-04-29 11:37:30,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +42: [2023-04-29 11:37:30,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +42: [2023-04-29 11:37:30,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +45: [2023-04-29 11:37:30,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +53: [2023-04-29 11:37:30,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +47: [2023-04-29 11:37:30,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +56: [2023-04-29 11:37:30,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +56: [2023-04-29 11:37:30,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +56: [2023-04-29 11:37:30,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +56: [2023-04-29 11:37:30,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +48: [2023-04-29 11:37:30,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +47: [2023-04-29 11:37:30,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +48: [2023-04-29 11:37:30,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +37: [2023-04-29 11:37:30,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +20: [2023-04-29 11:37:30,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +48: [2023-04-29 11:37:30,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +53: [2023-04-29 11:37:30,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +48: [2023-04-29 11:37:30,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +55: [2023-04-29 11:37:30,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +49: [2023-04-29 11:37:30,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +34: [2023-04-29 11:37:30,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +34: [2023-04-29 11:37:30,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +42: [2023-04-29 11:37:30,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +47: [2023-04-29 11:37:30,114] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +42: [2023-04-29 11:37:30,114] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +42: [2023-04-29 11:37:30,114] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +62: [2023-04-29 11:37:30,114] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +42: [2023-04-29 11:37:30,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +62: [2023-04-29 11:37:30,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +62: [2023-04-29 11:37:30,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +62: [2023-04-29 11:37:30,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +56: [2023-04-29 11:37:30,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +56: [2023-04-29 11:37:30,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +56: [2023-04-29 11:37:30,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +56: [2023-04-29 11:37:30,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +34: [2023-04-29 11:37:30,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +34: [2023-04-29 11:37:30,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +21: [2023-04-29 11:37:30,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +51: [2023-04-29 11:37:30,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +34: [2023-04-29 11:37:30,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +34: [2023-04-29 11:37:30,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +20: [2023-04-29 11:37:30,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +37: [2023-04-29 11:37:30,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +47: [2023-04-29 11:37:30,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +57: [2023-04-29 11:37:30,123] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +50: [2023-04-29 11:37:30,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +50: [2023-04-29 11:37:30,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +43: [2023-04-29 11:37:30,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +61: [2023-04-29 11:37:30,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +61: [2023-04-29 11:37:30,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +61: [2023-04-29 11:37:30,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +34: [2023-04-29 11:37:30,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +61: [2023-04-29 11:37:30,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +55: [2023-04-29 11:37:30,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +34: [2023-04-29 11:37:30,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +47: [2023-04-29 11:37:30,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +57: [2023-04-29 11:37:30,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +21: [2023-04-29 11:37:30,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +21: [2023-04-29 11:37:30,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +39: [2023-04-29 11:37:30,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +39: [2023-04-29 11:37:30,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +57: [2023-04-29 11:37:30,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 0: [2023-04-29 11:37:30,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 0: [2023-04-29 11:37:30,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 0: [2023-04-29 11:37:30,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 0: [2023-04-29 11:37:30,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +50: [2023-04-29 11:37:30,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +50: [2023-04-29 11:37:30,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +46: [2023-04-29 11:37:30,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +46: [2023-04-29 11:37:30,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +46: [2023-04-29 11:37:30,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +49: [2023-04-29 11:37:30,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +57: [2023-04-29 11:37:30,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +49: [2023-04-29 11:37:30,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +46: [2023-04-29 11:37:30,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +43: [2023-04-29 11:37:30,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +51: [2023-04-29 11:37:30,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +55: [2023-04-29 11:37:30,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +55: [2023-04-29 11:37:30,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +51: [2023-04-29 11:37:30,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +43: [2023-04-29 11:37:30,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +43: [2023-04-29 11:37:30,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +39: [2023-04-29 11:37:30,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +39: [2023-04-29 11:37:30,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 8: [2023-04-29 11:37:30,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. + 0: [2023-04-29 11:37:30,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. + 8: [2023-04-29 11:37:30,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. + 8: [2023-04-29 11:37:30,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +34: [2023-04-29 11:37:30,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +49: [2023-04-29 11:37:30,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +50: [2023-04-29 11:37:30,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 0: [2023-04-29 11:37:30,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 0: [2023-04-29 11:37:30,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +51: [2023-04-29 11:37:30,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 0: [2023-04-29 11:37:30,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +55: [2023-04-29 11:37:30,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +46: [2023-04-29 11:37:30,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +54: [2023-04-29 11:37:30,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +54: [2023-04-29 11:37:30,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +21: [2023-04-29 11:37:30,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +46: [2023-04-29 11:37:30,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +46: [2023-04-29 11:37:30,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +46: [2023-04-29 11:37:30,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +27: [2023-04-29 11:37:30,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +27: [2023-04-29 11:37:30,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +27: [2023-04-29 11:37:30,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +54: [2023-04-29 11:37:30,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +29: [2023-04-29 11:37:30,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +29: [2023-04-29 11:37:30,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +27: [2023-04-29 11:37:30,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +29: [2023-04-29 11:37:30,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +34: [2023-04-29 11:37:30,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +54: [2023-04-29 11:37:30,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +29: [2023-04-29 11:37:30,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +50: [2023-04-29 11:37:30,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +21: [2023-04-29 11:37:30,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +50: [2023-04-29 11:37:30,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +54: [2023-04-29 11:37:30,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +33: [2023-04-29 11:37:30,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +33: [2023-04-29 11:37:30,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +33: [2023-04-29 11:37:30,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +33: [2023-04-29 11:37:30,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +54: [2023-04-29 11:37:30,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +27: [2023-04-29 11:37:30,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +27: [2023-04-29 11:37:30,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +27: [2023-04-29 11:37:30,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +54: [2023-04-29 11:37:30,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +37: [2023-04-29 11:37:30,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +49: [2023-04-29 11:37:30,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +27: [2023-04-29 11:37:30,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +54: [2023-04-29 11:37:30,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +34: [2023-04-29 11:37:30,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +37: [2023-04-29 11:37:30,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +29: [2023-04-29 11:37:30,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +29: [2023-04-29 11:37:30,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +29: [2023-04-29 11:37:30,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +29: [2023-04-29 11:37:30,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +37: [2023-04-29 11:37:30,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +43: [2023-04-29 11:37:30,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +33: [2023-04-29 11:37:30,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +18: [2023-04-29 11:37:30,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +18: [2023-04-29 11:37:30,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +33: [2023-04-29 11:37:30,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +33: [2023-04-29 11:37:30,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +61: [2023-04-29 11:37:30,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +61: [2023-04-29 11:37:30,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +50: [2023-04-29 11:37:30,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +33: [2023-04-29 11:37:30,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +61: [2023-04-29 11:37:30,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +34: [2023-04-29 11:37:30,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +61: [2023-04-29 11:37:30,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +34: [2023-04-29 11:37:30,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +27: [2023-04-29 11:37:30,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +27: [2023-04-29 11:37:30,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +61: [2023-04-29 11:37:30,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +27: [2023-04-29 11:37:30,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +27: [2023-04-29 11:37:30,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +18: [2023-04-29 11:37:30,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +18: [2023-04-29 11:37:30,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +55: [2023-04-29 11:37:30,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +55: [2023-04-29 11:37:30,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +55: [2023-04-29 11:37:30,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +55: [2023-04-29 11:37:30,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +18: [2023-04-29 11:37:30,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +61: [2023-04-29 11:37:30,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +49: [2023-04-29 11:37:30,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +49: [2023-04-29 11:37:30,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +34: [2023-04-29 11:37:30,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +49: [2023-04-29 11:37:30,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +55: [2023-04-29 11:37:30,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +18: [2023-04-29 11:37:30,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +39: [2023-04-29 11:37:30,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +39: [2023-04-29 11:37:30,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +49: [2023-04-29 11:37:30,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +21: [2023-04-29 11:37:30,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +61: [2023-04-29 11:37:30,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +61: [2023-04-29 11:37:30,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +18: [2023-04-29 11:37:30,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +61: [2023-04-29 11:37:30,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +61: [2023-04-29 11:37:30,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +61: [2023-04-29 11:37:30,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +61: [2023-04-29 11:37:30,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +43: [2023-04-29 11:37:30,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +21: [2023-04-29 11:37:30,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +40: [2023-04-29 11:37:30,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +40: [2023-04-29 11:37:30,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +40: [2023-04-29 11:37:30,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +18: [2023-04-29 11:37:30,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +40: [2023-04-29 11:37:30,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +39: [2023-04-29 11:37:30,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +55: [2023-04-29 11:37:30,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +55: [2023-04-29 11:37:30,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +39: [2023-04-29 11:37:30,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +37: [2023-04-29 11:37:30,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +37: [2023-04-29 11:37:30,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +43: [2023-04-29 11:37:30,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +43: [2023-04-29 11:37:30,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +56: [2023-04-29 11:37:30,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +56: [2023-04-29 11:37:30,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +21: [2023-04-29 11:37:30,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +34: [2023-04-29 11:37:30,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +50: [2023-04-29 11:37:30,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +50: [2023-04-29 11:37:30,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +50: [2023-04-29 11:37:30,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +50: [2023-04-29 11:37:30,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 8: [2023-04-29 11:37:30,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +37: [2023-04-29 11:37:30,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +56: [2023-04-29 11:37:30,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +56: [2023-04-29 11:37:30,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +60: [2023-04-29 11:37:30,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +60: [2023-04-29 11:37:30,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 0: [2023-04-29 11:37:30,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 0: [2023-04-29 11:37:30,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 0: [2023-04-29 11:37:30,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +60: [2023-04-29 11:37:30,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +60: [2023-04-29 11:37:30,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +56: [2023-04-29 11:37:30,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +50: [2023-04-29 11:37:30,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +18: [2023-04-29 11:37:30,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +18: [2023-04-29 11:37:30,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +45: [2023-04-29 11:37:30,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +45: [2023-04-29 11:37:30,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +37: [2023-04-29 11:37:30,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +34: [2023-04-29 11:37:30,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +50: [2023-04-29 11:37:30,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +37: [2023-04-29 11:37:30,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +52: [2023-04-29 11:37:30,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +52: [2023-04-29 11:37:30,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +60: [2023-04-29 11:37:30,175] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +60: [2023-04-29 11:37:30,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +56: [2023-04-29 11:37:30,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. + 0: [2023-04-29 11:37:30,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +50: [2023-04-29 11:37:30,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +60: [2023-04-29 11:37:30,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +52: [2023-04-29 11:37:30,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 0: [2023-04-29 11:37:30,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... + 0: [2023-04-29 11:37:30,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... + 0: [2023-04-29 11:37:30,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +52: [2023-04-29 11:37:30,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +45: [2023-04-29 11:37:30,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +45: [2023-04-29 11:37:30,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +18: [2023-04-29 11:37:30,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +18: [2023-04-29 11:37:30,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +50: [2023-04-29 11:37:30,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +56: [2023-04-29 11:37:30,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +48: [2023-04-29 11:37:30,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +48: [2023-04-29 11:37:30,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +60: [2023-04-29 11:37:30,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +37: [2023-04-29 11:37:30,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +52: [2023-04-29 11:37:30,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +52: [2023-04-29 11:37:30,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +56: [2023-04-29 11:37:30,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +52: [2023-04-29 11:37:30,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +37: [2023-04-29 11:37:30,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +48: [2023-04-29 11:37:30,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +52: [2023-04-29 11:37:30,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +37: [2023-04-29 11:37:30,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +37: [2023-04-29 11:37:30,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +48: [2023-04-29 11:37:30,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +49: [2023-04-29 11:37:30,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +42: [2023-04-29 11:37:30,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +34: [2023-04-29 11:37:30,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +34: [2023-04-29 11:37:30,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +27: [2023-04-29 11:37:30,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +27: [2023-04-29 11:37:30,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +55: [2023-04-29 11:37:30,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 0: [2023-04-29 11:37:30,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +49: [2023-04-29 11:37:30,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 8: [2023-04-29 11:37:30,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +55: [2023-04-29 11:37:30,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +27: [2023-04-29 11:37:30,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +56: [2023-04-29 11:37:30,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +56: [2023-04-29 11:37:30,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +56: [2023-04-29 11:37:30,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +27: [2023-04-29 11:37:30,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +42: [2023-04-29 11:37:30,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +42: [2023-04-29 11:37:30,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +42: [2023-04-29 11:37:30,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +55: [2023-04-29 11:37:30,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +55: [2023-04-29 11:37:30,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +40: [2023-04-29 11:37:30,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +40: [2023-04-29 11:37:30,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +49: [2023-04-29 11:37:30,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +49: [2023-04-29 11:37:30,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 8: [2023-04-29 11:37:30,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 8: [2023-04-29 11:37:30,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +56: [2023-04-29 11:37:30,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +40: [2023-04-29 11:37:30,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +32: [2023-04-29 11:37:30,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. + 8: [2023-04-29 11:37:30,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +32: [2023-04-29 11:37:30,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +32: [2023-04-29 11:37:30,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +40: [2023-04-29 11:37:30,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +32: [2023-04-29 11:37:30,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. + 8: [2023-04-29 11:37:30,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +36: [2023-04-29 11:37:30,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +36: [2023-04-29 11:37:30,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +36: [2023-04-29 11:37:30,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +62: [2023-04-29 11:37:30,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +36: [2023-04-29 11:37:30,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +18: [2023-04-29 11:37:30,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +46: [2023-04-29 11:37:30,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +18: [2023-04-29 11:37:30,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +34: [2023-04-29 11:37:30,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +62: [2023-04-29 11:37:30,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +62: [2023-04-29 11:37:30,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +44: [2023-04-29 11:37:30,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +44: [2023-04-29 11:37:30,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +44: [2023-04-29 11:37:30,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +44: [2023-04-29 11:37:30,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +46: [2023-04-29 11:37:30,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +62: [2023-04-29 11:37:30,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +54: [2023-04-29 11:37:30,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +45: [2023-04-29 11:37:30,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +45: [2023-04-29 11:37:30,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +45: [2023-04-29 11:37:30,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +17: [2023-04-29 11:37:30,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +17: [2023-04-29 11:37:30,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +45: [2023-04-29 11:37:30,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +17: [2023-04-29 11:37:30,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +17: [2023-04-29 11:37:30,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +44: [2023-04-29 11:37:30,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +45: [2023-04-29 11:37:30,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +34: [2023-04-29 11:37:30,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +45: [2023-04-29 11:37:30,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +45: [2023-04-29 11:37:30,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +45: [2023-04-29 11:37:30,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +33: [2023-04-29 11:37:30,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +44: [2023-04-29 11:37:30,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +44: [2023-04-29 11:37:30,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 0: [2023-04-29 11:37:30,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 0: [2023-04-29 11:37:30,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 0: [2023-04-29 11:37:30,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +44: [2023-04-29 11:37:30,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +34: [2023-04-29 11:37:30,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +48: [2023-04-29 11:37:30,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +62: [2023-04-29 11:37:30,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +62: [2023-04-29 11:37:30,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +62: [2023-04-29 11:37:30,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +48: [2023-04-29 11:37:30,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +61: [2023-04-29 11:37:30,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +18: [2023-04-29 11:37:30,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +18: [2023-04-29 11:37:30,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +34: [2023-04-29 11:37:30,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +62: [2023-04-29 11:37:30,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +29: [2023-04-29 11:37:30,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 0: [2023-04-29 11:37:30,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +56: [2023-04-29 11:37:30,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +46: [2023-04-29 11:37:30,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +46: [2023-04-29 11:37:30,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +54: [2023-04-29 11:37:30,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +56: [2023-04-29 11:37:30,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +27: [2023-04-29 11:37:30,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +62: [2023-04-29 11:37:30,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +62: [2023-04-29 11:37:30,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +48: [2023-04-29 11:37:30,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +48: [2023-04-29 11:37:30,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +61: [2023-04-29 11:37:30,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +56: [2023-04-29 11:37:30,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +42: [2023-04-29 11:37:30,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +42: [2023-04-29 11:37:30,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +62: [2023-04-29 11:37:30,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +29: [2023-04-29 11:37:30,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +29: [2023-04-29 11:37:30,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +29: [2023-04-29 11:37:30,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +62: [2023-04-29 11:37:30,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +42: [2023-04-29 11:37:30,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +54: [2023-04-29 11:37:30,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +42: [2023-04-29 11:37:30,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +62: [2023-04-29 11:37:30,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +62: [2023-04-29 11:37:30,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +56: [2023-04-29 11:37:30,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +32: [2023-04-29 11:37:30,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +12: [2023-04-29 11:37:30,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +12: [2023-04-29 11:37:30,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +32: [2023-04-29 11:37:30,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +20: [2023-04-29 11:37:30,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +20: [2023-04-29 11:37:30,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +41: [2023-04-29 11:37:30,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +41: [2023-04-29 11:37:30,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +41: [2023-04-29 11:37:30,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +41: [2023-04-29 11:37:30,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +20: [2023-04-29 11:37:30,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +33: [2023-04-29 11:37:30,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +33: [2023-04-29 11:37:30,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +33: [2023-04-29 11:37:30,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +12: [2023-04-29 11:37:30,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +51: [2023-04-29 11:37:30,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +51: [2023-04-29 11:37:30,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +51: [2023-04-29 11:37:30,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +12: [2023-04-29 11:37:30,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +51: [2023-04-29 11:37:30,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +32: [2023-04-29 11:37:30,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +20: [2023-04-29 11:37:30,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +54: [2023-04-29 11:37:30,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +32: [2023-04-29 11:37:30,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +61: [2023-04-29 11:37:30,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +62: [2023-04-29 11:37:30,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +36: [2023-04-29 11:37:30,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +61: [2023-04-29 11:37:30,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +62: [2023-04-29 11:37:30,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +36: [2023-04-29 11:37:30,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +46: [2023-04-29 11:37:30,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +36: [2023-04-29 11:37:30,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +18: [2023-04-29 11:37:30,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +45: [2023-04-29 11:37:30,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +45: [2023-04-29 11:37:30,229] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +61: [2023-04-29 11:37:30,229] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +17: [2023-04-29 11:37:30,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +63: [2023-04-29 11:37:30,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +63: [2023-04-29 11:37:30,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +61: [2023-04-29 11:37:30,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +63: [2023-04-29 11:37:30,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +63: [2023-04-29 11:37:30,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 4: [2023-04-29 11:37:30,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. + 4: [2023-04-29 11:37:30,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +46: [2023-04-29 11:37:30,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +36: [2023-04-29 11:37:30,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +35: [2023-04-29 11:37:30,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +35: [2023-04-29 11:37:30,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 4: [2023-04-29 11:37:30,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +35: [2023-04-29 11:37:30,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 4: [2023-04-29 11:37:30,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +45: [2023-04-29 11:37:30,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +45: [2023-04-29 11:37:30,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +35: [2023-04-29 11:37:30,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +17: [2023-04-29 11:37:30,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +61: [2023-04-29 11:37:30,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +33: [2023-04-29 11:37:30,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +27: [2023-04-29 11:37:30,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +61: [2023-04-29 11:37:30,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +34: [2023-04-29 11:37:30,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +52: [2023-04-29 11:37:30,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +54: [2023-04-29 11:37:30,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +52: [2023-04-29 11:37:30,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +17: [2023-04-29 11:37:30,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +52: [2023-04-29 11:37:30,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +52: [2023-04-29 11:37:30,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +63: [2023-04-29 11:37:30,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +61: [2023-04-29 11:37:30,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +63: [2023-04-29 11:37:30,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +60: [2023-04-29 11:37:30,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +50: [2023-04-29 11:37:30,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +27: [2023-04-29 11:37:30,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +18: [2023-04-29 11:37:30,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +50: [2023-04-29 11:37:30,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +11: [2023-04-29 11:37:30,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +11: [2023-04-29 11:37:30,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +27: [2023-04-29 11:37:30,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +61: [2023-04-29 11:37:30,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +63: [2023-04-29 11:37:30,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +63: [2023-04-29 11:37:30,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +17: [2023-04-29 11:37:30,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 0: [2023-04-29 11:37:30,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +35: [2023-04-29 11:37:30,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +29: [2023-04-29 11:37:30,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 0: [2023-04-29 11:37:30,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +54: [2023-04-29 11:37:30,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +34: [2023-04-29 11:37:30,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 0: [2023-04-29 11:37:30,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +11: [2023-04-29 11:37:30,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +11: [2023-04-29 11:37:30,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +27: [2023-04-29 11:37:30,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 0: [2023-04-29 11:37:30,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +35: [2023-04-29 11:37:30,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +35: [2023-04-29 11:37:30,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +11: [2023-04-29 11:37:30,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +35: [2023-04-29 11:37:30,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +11: [2023-04-29 11:37:30,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +46: [2023-04-29 11:37:30,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +11: [2023-04-29 11:37:30,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +46: [2023-04-29 11:37:30,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +61: [2023-04-29 11:37:30,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +61: [2023-04-29 11:37:30,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +11: [2023-04-29 11:37:30,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +39: [2023-04-29 11:37:30,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +39: [2023-04-29 11:37:30,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. + 3: [2023-04-29 11:37:30,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +39: [2023-04-29 11:37:30,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. + 3: [2023-04-29 11:37:30,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 3: [2023-04-29 11:37:30,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +39: [2023-04-29 11:37:30,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. + 3: [2023-04-29 11:37:30,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +54: [2023-04-29 11:37:30,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +60: [2023-04-29 11:37:30,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +49: [2023-04-29 11:37:30,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +40: [2023-04-29 11:37:30,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +29: [2023-04-29 11:37:30,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +12: [2023-04-29 11:37:30,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +60: [2023-04-29 11:37:30,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +41: [2023-04-29 11:37:30,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +41: [2023-04-29 11:37:30,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +29: [2023-04-29 11:37:30,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +52: [2023-04-29 11:37:30,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +52: [2023-04-29 11:37:30,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +20: [2023-04-29 11:37:30,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +29: [2023-04-29 11:37:30,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +49: [2023-04-29 11:37:30,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +20: [2023-04-29 11:37:30,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 3: [2023-04-29 11:37:30,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 3: [2023-04-29 11:37:30,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +12: [2023-04-29 11:37:30,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +49: [2023-04-29 11:37:30,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 8: [2023-04-29 11:37:30,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +40: [2023-04-29 11:37:30,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +33: [2023-04-29 11:37:30,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 3: [2023-04-29 11:37:30,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +12: [2023-04-29 11:37:30,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +18: [2023-04-29 11:37:30,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +52: [2023-04-29 11:37:30,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +61: [2023-04-29 11:37:30,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +63: [2023-04-29 11:37:30,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +63: [2023-04-29 11:37:30,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. + 8: [2023-04-29 11:37:30,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +33: [2023-04-29 11:37:30,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 3: [2023-04-29 11:37:30,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +33: [2023-04-29 11:37:30,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +20: [2023-04-29 11:37:30,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +63: [2023-04-29 11:37:30,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +63: [2023-04-29 11:37:30,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +18: [2023-04-29 11:37:30,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +51: [2023-04-29 11:37:30,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +20: [2023-04-29 11:37:30,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +51: [2023-04-29 11:37:30,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +40: [2023-04-29 11:37:30,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +40: [2023-04-29 11:37:30,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +12: [2023-04-29 11:37:30,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +18: [2023-04-29 11:37:30,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 8: [2023-04-29 11:37:30,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +38: [2023-04-29 11:37:30,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +38: [2023-04-29 11:37:30,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +38: [2023-04-29 11:37:30,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +41: [2023-04-29 11:37:30,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +38: [2023-04-29 11:37:30,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +47: [2023-04-29 11:37:30,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +47: [2023-04-29 11:37:30,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +47: [2023-04-29 11:37:30,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +61: [2023-04-29 11:37:30,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 6: [2023-04-29 11:37:30,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 6: [2023-04-29 11:37:30,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +60: [2023-04-29 11:37:30,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +47: [2023-04-29 11:37:30,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +27: [2023-04-29 11:37:30,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +41: [2023-04-29 11:37:30,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +54: [2023-04-29 11:37:30,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +49: [2023-04-29 11:37:30,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... + 4: [2023-04-29 11:37:30,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 6: [2023-04-29 11:37:30,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 6: [2023-04-29 11:37:30,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 8: [2023-04-29 11:37:30,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +55: [2023-04-29 11:37:30,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +55: [2023-04-29 11:37:30,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +55: [2023-04-29 11:37:30,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +49: [2023-04-29 11:37:30,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +50: [2023-04-29 11:37:30,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +50: [2023-04-29 11:37:30,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 4: [2023-04-29 11:37:30,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +17: [2023-04-29 11:37:30,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +17: [2023-04-29 11:37:30,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +17: [2023-04-29 11:37:30,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +17: [2023-04-29 11:37:30,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +40: [2023-04-29 11:37:30,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... + 6: [2023-04-29 11:37:30,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +57: [2023-04-29 11:37:30,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +57: [2023-04-29 11:37:30,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +57: [2023-04-29 11:37:30,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +49: [2023-04-29 11:37:30,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +57: [2023-04-29 11:37:30,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +40: [2023-04-29 11:37:30,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +38: [2023-04-29 11:37:30,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +51: [2023-04-29 11:37:30,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +51: [2023-04-29 11:37:30,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +44: [2023-04-29 11:37:30,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +47: [2023-04-29 11:37:30,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +50: [2023-04-29 11:37:30,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 6: [2023-04-29 11:37:30,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +47: [2023-04-29 11:37:30,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +27: [2023-04-29 11:37:30,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +27: [2023-04-29 11:37:30,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... + 4: [2023-04-29 11:37:30,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +47: [2023-04-29 11:37:30,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +47: [2023-04-29 11:37:30,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +38: [2023-04-29 11:37:30,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 6: [2023-04-29 11:37:30,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +38: [2023-04-29 11:37:30,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +38: [2023-04-29 11:37:30,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +60: [2023-04-29 11:37:30,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... + 6: [2023-04-29 11:37:30,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +55: [2023-04-29 11:37:30,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +61: [2023-04-29 11:37:30,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +42: [2023-04-29 11:37:30,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +42: [2023-04-29 11:37:30,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +42: [2023-04-29 11:37:30,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. + 4: [2023-04-29 11:37:30,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +42: [2023-04-29 11:37:30,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +52: [2023-04-29 11:37:30,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +35: [2023-04-29 11:37:30,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. + 8: [2023-04-29 11:37:30,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +35: [2023-04-29 11:37:30,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +55: [2023-04-29 11:37:30,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +55: [2023-04-29 11:37:30,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +49: [2023-04-29 11:37:30,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +35: [2023-04-29 11:37:30,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +55: [2023-04-29 11:37:30,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +35: [2023-04-29 11:37:30,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +21: [2023-04-29 11:37:30,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +21: [2023-04-29 11:37:30,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +21: [2023-04-29 11:37:30,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +52: [2023-04-29 11:37:30,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +21: [2023-04-29 11:37:30,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +17: [2023-04-29 11:37:30,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +52: [2023-04-29 11:37:30,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +27: [2023-04-29 11:37:30,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +17: [2023-04-29 11:37:30,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +17: [2023-04-29 11:37:30,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +49: [2023-04-29 11:37:30,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +40: [2023-04-29 11:37:30,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +17: [2023-04-29 11:37:30,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 6: [2023-04-29 11:37:30,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. + 6: [2023-04-29 11:37:30,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +61: [2023-04-29 11:37:30,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 6: [2023-04-29 11:37:30,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +27: [2023-04-29 11:37:30,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 6: [2023-04-29 11:37:30,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +55: [2023-04-29 11:37:30,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +18: [2023-04-29 11:37:30,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +52: [2023-04-29 11:37:30,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +50: [2023-04-29 11:37:30,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +27: [2023-04-29 11:37:30,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +27: [2023-04-29 11:37:30,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... + 8: [2023-04-29 11:37:30,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +44: [2023-04-29 11:37:30,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +52: [2023-04-29 11:37:30,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +18: [2023-04-29 11:37:30,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +18: [2023-04-29 11:37:30,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +40: [2023-04-29 11:37:30,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +36: [2023-04-29 11:37:30,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +36: [2023-04-29 11:37:30,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +23: [2023-04-29 11:37:30,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +23: [2023-04-29 11:37:30,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +23: [2023-04-29 11:37:30,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +39: [2023-04-29 11:37:30,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +23: [2023-04-29 11:37:30,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +58: [2023-04-29 11:37:30,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +58: [2023-04-29 11:37:30,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +58: [2023-04-29 11:37:30,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +39: [2023-04-29 11:37:30,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +58: [2023-04-29 11:37:30,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +40: [2023-04-29 11:37:30,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +40: [2023-04-29 11:37:30,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +40: [2023-04-29 11:37:30,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +27: [2023-04-29 11:37:30,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +27: [2023-04-29 11:37:30,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +39: [2023-04-29 11:37:30,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +40: [2023-04-29 11:37:30,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +46: [2023-04-29 11:37:30,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +46: [2023-04-29 11:37:30,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +60: [2023-04-29 11:37:30,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +60: [2023-04-29 11:37:30,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +52: [2023-04-29 11:37:30,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +44: [2023-04-29 11:37:30,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +36: [2023-04-29 11:37:30,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +36: [2023-04-29 11:37:30,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +22: [2023-04-29 11:37:30,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +22: [2023-04-29 11:37:30,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +22: [2023-04-29 11:37:30,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +22: [2023-04-29 11:37:30,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +18: [2023-04-29 11:37:30,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +36: [2023-04-29 11:37:30,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +36: [2023-04-29 11:37:30,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +46: [2023-04-29 11:37:30,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +46: [2023-04-29 11:37:30,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +39: [2023-04-29 11:37:30,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +40: [2023-04-29 11:37:30,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +58: [2023-04-29 11:37:30,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +58: [2023-04-29 11:37:30,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +40: [2023-04-29 11:37:30,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +58: [2023-04-29 11:37:30,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +58: [2023-04-29 11:37:30,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +52: [2023-04-29 11:37:30,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +52: [2023-04-29 11:37:30,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +44: [2023-04-29 11:37:30,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +27: [2023-04-29 11:37:30,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +27: [2023-04-29 11:37:30,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +18: [2023-04-29 11:37:30,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +40: [2023-04-29 11:37:30,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 8: [2023-04-29 11:37:30,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +40: [2023-04-29 11:37:30,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +63: [2023-04-29 11:37:30,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +63: [2023-04-29 11:37:30,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +57: [2023-04-29 11:37:30,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +44: [2023-04-29 11:37:30,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +22: [2023-04-29 11:37:30,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +63: [2023-04-29 11:37:30,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +62: [2023-04-29 11:37:30,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +62: [2023-04-29 11:37:30,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +62: [2023-04-29 11:37:30,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +60: [2023-04-29 11:37:30,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +36: [2023-04-29 11:37:30,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +22: [2023-04-29 11:37:30,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +22: [2023-04-29 11:37:30,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +22: [2023-04-29 11:37:30,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +36: [2023-04-29 11:37:30,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +63: [2023-04-29 11:37:30,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +42: [2023-04-29 11:37:30,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +21: [2023-04-29 11:37:30,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +57: [2023-04-29 11:37:30,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +32: [2023-04-29 11:37:30,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +32: [2023-04-29 11:37:30,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +57: [2023-04-29 11:37:30,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +57: [2023-04-29 11:37:30,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +24: [2023-04-29 11:37:30,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +24: [2023-04-29 11:37:30,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +21: [2023-04-29 11:37:30,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +36: [2023-04-29 11:37:30,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +32: [2023-04-29 11:37:30,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +24: [2023-04-29 11:37:30,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +43: [2023-04-29 11:37:30,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +43: [2023-04-29 11:37:30,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +18: [2023-04-29 11:37:30,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +24: [2023-04-29 11:37:30,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +35: [2023-04-29 11:37:30,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +42: [2023-04-29 11:37:30,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +43: [2023-04-29 11:37:30,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +43: [2023-04-29 11:37:30,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +45: [2023-04-29 11:37:30,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +52: [2023-04-29 11:37:30,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +50: [2023-04-29 11:37:30,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +50: [2023-04-29 11:37:30,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +18: [2023-04-29 11:37:30,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +35: [2023-04-29 11:37:30,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +36: [2023-04-29 11:37:30,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +36: [2023-04-29 11:37:30,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +32: [2023-04-29 11:37:30,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +21: [2023-04-29 11:37:30,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +11: [2023-04-29 11:37:30,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +42: [2023-04-29 11:37:30,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +17: [2023-04-29 11:37:30,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 6: [2023-04-29 11:37:30,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +45: [2023-04-29 11:37:30,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +32: [2023-04-29 11:37:30,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +32: [2023-04-29 11:37:30,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +32: [2023-04-29 11:37:30,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +44: [2023-04-29 11:37:30,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +35: [2023-04-29 11:37:30,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +35: [2023-04-29 11:37:30,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +45: [2023-04-29 11:37:30,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +42: [2023-04-29 11:37:30,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +36: [2023-04-29 11:37:30,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +21: [2023-04-29 11:37:30,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 6: [2023-04-29 11:37:30,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +45: [2023-04-29 11:37:30,301] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. + 6: [2023-04-29 11:37:30,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +36: [2023-04-29 11:37:30,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... + 6: [2023-04-29 11:37:30,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +17: [2023-04-29 11:37:30,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +46: [2023-04-29 11:37:30,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +45: [2023-04-29 11:37:30,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +46: [2023-04-29 11:37:30,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +32: [2023-04-29 11:37:30,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +23: [2023-04-29 11:37:30,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +23: [2023-04-29 11:37:30,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +62: [2023-04-29 11:37:30,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +33: [2023-04-29 11:37:30,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +33: [2023-04-29 11:37:30,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +33: [2023-04-29 11:37:30,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +18: [2023-04-29 11:37:30,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +18: [2023-04-29 11:37:30,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +45: [2023-04-29 11:37:30,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +23: [2023-04-29 11:37:30,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +46: [2023-04-29 11:37:30,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +63: [2023-04-29 11:37:30,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +45: [2023-04-29 11:37:30,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +33: [2023-04-29 11:37:30,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +44: [2023-04-29 11:37:30,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +35: [2023-04-29 11:37:30,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +36: [2023-04-29 11:37:30,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +36: [2023-04-29 11:37:30,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +23: [2023-04-29 11:37:30,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +46: [2023-04-29 11:37:30,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +45: [2023-04-29 11:37:30,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +10: [2023-04-29 11:37:30,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +10: [2023-04-29 11:37:30,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +10: [2023-04-29 11:37:30,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +44: [2023-04-29 11:37:30,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +62: [2023-04-29 11:37:30,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +17: [2023-04-29 11:37:30,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +17: [2023-04-29 11:37:30,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +10: [2023-04-29 11:37:30,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +62: [2023-04-29 11:37:30,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +11: [2023-04-29 11:37:30,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +18: [2023-04-29 11:37:30,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... + 4: [2023-04-29 11:37:30,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +17: [2023-04-29 11:37:30,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 8: [2023-04-29 11:37:30,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +18: [2023-04-29 11:37:30,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +11: [2023-04-29 11:37:30,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 8: [2023-04-29 11:37:30,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 3: [2023-04-29 11:37:30,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +20: [2023-04-29 11:37:30,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +20: [2023-04-29 11:37:30,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +11: [2023-04-29 11:37:30,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 4: [2023-04-29 11:37:30,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +53: [2023-04-29 11:37:30,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +53: [2023-04-29 11:37:30,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +53: [2023-04-29 11:37:30,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +53: [2023-04-29 11:37:30,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +14: [2023-04-29 11:37:30,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +14: [2023-04-29 11:37:30,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +14: [2023-04-29 11:37:30,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +53: [2023-04-29 11:37:30,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +53: [2023-04-29 11:37:30,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +53: [2023-04-29 11:37:30,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +14: [2023-04-29 11:37:30,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +53: [2023-04-29 11:37:30,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +62: [2023-04-29 11:37:30,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +36: [2023-04-29 11:37:30,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +24: [2023-04-29 11:37:30,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +17: [2023-04-29 11:37:30,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +17: [2023-04-29 11:37:30,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +51: [2023-04-29 11:37:30,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +41: [2023-04-29 11:37:30,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +19: [2023-04-29 11:37:30,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +19: [2023-04-29 11:37:30,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +19: [2023-04-29 11:37:30,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +24: [2023-04-29 11:37:30,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +19: [2023-04-29 11:37:30,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +11: [2023-04-29 11:37:30,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +17: [2023-04-29 11:37:30,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... + 3: [2023-04-29 11:37:30,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +13: [2023-04-29 11:37:30,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +13: [2023-04-29 11:37:30,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +13: [2023-04-29 11:37:30,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +41: [2023-04-29 11:37:30,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +13: [2023-04-29 11:37:30,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +24: [2023-04-29 11:37:30,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +24: [2023-04-29 11:37:30,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +63: [2023-04-29 11:37:30,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +43: [2023-04-29 11:37:30,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +32: [2023-04-29 11:37:30,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +32: [2023-04-29 11:37:30,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +43: [2023-04-29 11:37:30,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +32: [2023-04-29 11:37:30,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +20: [2023-04-29 11:37:30,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +20: [2023-04-29 11:37:30,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... + 3: [2023-04-29 11:37:30,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +53: [2023-04-29 11:37:30,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 3: [2023-04-29 11:37:30,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +32: [2023-04-29 11:37:30,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +43: [2023-04-29 11:37:30,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +14: [2023-04-29 11:37:30,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +14: [2023-04-29 11:37:30,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +14: [2023-04-29 11:37:30,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +20: [2023-04-29 11:37:30,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +14: [2023-04-29 11:37:30,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +14: [2023-04-29 11:37:30,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +14: [2023-04-29 11:37:30,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +60: [2023-04-29 11:37:30,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +60: [2023-04-29 11:37:30,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +60: [2023-04-29 11:37:30,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +53: [2023-04-29 11:37:30,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +60: [2023-04-29 11:37:30,326] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +53: [2023-04-29 11:37:30,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +51: [2023-04-29 11:37:30,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +14: [2023-04-29 11:37:30,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +43: [2023-04-29 11:37:30,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +47: [2023-04-29 11:37:30,326] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +14: [2023-04-29 11:37:30,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +63: [2023-04-29 11:37:30,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +53: [2023-04-29 11:37:30,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +63: [2023-04-29 11:37:30,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +51: [2023-04-29 11:37:30,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +41: [2023-04-29 11:37:30,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +38: [2023-04-29 11:37:30,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +38: [2023-04-29 11:37:30,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +20: [2023-04-29 11:37:30,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +28: [2023-04-29 11:37:30,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +28: [2023-04-29 11:37:30,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +28: [2023-04-29 11:37:30,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +28: [2023-04-29 11:37:30,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +41: [2023-04-29 11:37:30,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +41: [2023-04-29 11:37:30,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... + 5: [2023-04-29 11:37:30,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 5: [2023-04-29 11:37:30,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 5: [2023-04-29 11:37:30,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +32: [2023-04-29 11:37:30,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 4: [2023-04-29 11:37:30,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +44: [2023-04-29 11:37:30,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +44: [2023-04-29 11:37:30,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +32: [2023-04-29 11:37:30,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +38: [2023-04-29 11:37:30,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +38: [2023-04-29 11:37:30,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +63: [2023-04-29 11:37:30,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +44: [2023-04-29 11:37:30,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +44: [2023-04-29 11:37:30,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +32: [2023-04-29 11:37:30,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +38: [2023-04-29 11:37:30,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +47: [2023-04-29 11:37:30,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +12: [2023-04-29 11:37:30,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +12: [2023-04-29 11:37:30,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +12: [2023-04-29 11:37:30,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +12: [2023-04-29 11:37:30,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +12: [2023-04-29 11:37:30,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +12: [2023-04-29 11:37:30,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +12: [2023-04-29 11:37:30,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +20: [2023-04-29 11:37:30,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +32: [2023-04-29 11:37:30,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 5: [2023-04-29 11:37:30,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +38: [2023-04-29 11:37:30,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +12: [2023-04-29 11:37:30,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +33: [2023-04-29 11:37:30,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +51: [2023-04-29 11:37:30,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +41: [2023-04-29 11:37:30,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... + 4: [2023-04-29 11:37:30,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +12: [2023-04-29 11:37:30,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... + 4: [2023-04-29 11:37:30,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 4: [2023-04-29 11:37:30,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +35: [2023-04-29 11:37:30,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 4: [2023-04-29 11:37:30,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +35: [2023-04-29 11:37:30,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +28: [2023-04-29 11:37:30,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +28: [2023-04-29 11:37:30,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +17: [2023-04-29 11:37:30,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 4: [2023-04-29 11:37:30,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 6: [2023-04-29 11:37:30,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 4: [2023-04-29 11:37:30,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +47: [2023-04-29 11:37:30,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +28: [2023-04-29 11:37:30,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +20: [2023-04-29 11:37:30,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +28: [2023-04-29 11:37:30,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 6: [2023-04-29 11:37:30,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +62: [2023-04-29 11:37:30,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +35: [2023-04-29 11:37:30,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +38: [2023-04-29 11:37:30,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +33: [2023-04-29 11:37:30,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 5: [2023-04-29 11:37:30,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 5: [2023-04-29 11:37:30,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 5: [2023-04-29 11:37:30,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +52: [2023-04-29 11:37:30,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +39: [2023-04-29 11:37:30,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +12: [2023-04-29 11:37:30,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +12: [2023-04-29 11:37:30,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +10: [2023-04-29 11:37:30,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +41: [2023-04-29 11:37:30,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. + 4: [2023-04-29 11:37:30,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +12: [2023-04-29 11:37:30,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 6: [2023-04-29 11:37:30,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 6: [2023-04-29 11:37:30,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +12: [2023-04-29 11:37:30,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +17: [2023-04-29 11:37:30,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 3: [2023-04-29 11:37:30,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +12: [2023-04-29 11:37:30,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +12: [2023-04-29 11:37:30,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +35: [2023-04-29 11:37:30,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 5: [2023-04-29 11:37:30,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +48: [2023-04-29 11:37:30,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +48: [2023-04-29 11:37:30,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +48: [2023-04-29 11:37:30,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +48: [2023-04-29 11:37:30,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +12: [2023-04-29 11:37:30,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +51: [2023-04-29 11:37:30,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +47: [2023-04-29 11:37:30,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 4: [2023-04-29 11:37:30,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +11: [2023-04-29 11:37:30,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +33: [2023-04-29 11:37:30,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 4: [2023-04-29 11:37:30,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 4: [2023-04-29 11:37:30,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +33: [2023-04-29 11:37:30,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 4: [2023-04-29 11:37:30,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 4: [2023-04-29 11:37:30,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +57: [2023-04-29 11:37:30,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +57: [2023-04-29 11:37:30,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +11: [2023-04-29 11:37:30,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +52: [2023-04-29 11:37:30,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +10: [2023-04-29 11:37:30,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +10: [2023-04-29 11:37:30,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +39: [2023-04-29 11:37:30,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +10: [2023-04-29 11:37:30,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +21: [2023-04-29 11:37:30,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +39: [2023-04-29 11:37:30,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +11: [2023-04-29 11:37:30,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +57: [2023-04-29 11:37:30,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +57: [2023-04-29 11:37:30,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +41: [2023-04-29 11:37:30,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +59: [2023-04-29 11:37:30,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +59: [2023-04-29 11:37:30,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +13: [2023-04-29 11:37:30,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +38: [2023-04-29 11:37:30,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +52: [2023-04-29 11:37:30,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. + 4: [2023-04-29 11:37:30,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +59: [2023-04-29 11:37:30,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 3: [2023-04-29 11:37:30,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +59: [2023-04-29 11:37:30,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +19: [2023-04-29 11:37:30,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +21: [2023-04-29 11:37:30,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +14: [2023-04-29 11:37:30,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +57: [2023-04-29 11:37:30,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +57: [2023-04-29 11:37:30,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +40: [2023-04-29 11:37:30,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +51: [2023-04-29 11:37:30,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +59: [2023-04-29 11:37:30,349] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +59: [2023-04-29 11:37:30,349] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +57: [2023-04-29 11:37:30,349] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +39: [2023-04-29 11:37:30,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +53: [2023-04-29 11:37:30,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +53: [2023-04-29 11:37:30,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +57: [2023-04-29 11:37:30,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +53: [2023-04-29 11:37:30,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +51: [2023-04-29 11:37:30,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +58: [2023-04-29 11:37:30,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +58: [2023-04-29 11:37:30,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +22: [2023-04-29 11:37:30,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +63: [2023-04-29 11:37:30,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +36: [2023-04-29 11:37:30,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +36: [2023-04-29 11:37:30,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +57: [2023-04-29 11:37:30,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +47: [2023-04-29 11:37:30,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +53: [2023-04-29 11:37:30,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 3: [2023-04-29 11:37:30,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +52: [2023-04-29 11:37:30,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +13: [2023-04-29 11:37:30,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +59: [2023-04-29 11:37:30,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +59: [2023-04-29 11:37:30,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +17: [2023-04-29 11:37:30,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +59: [2023-04-29 11:37:30,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_34-model_01-model_states.pt. +59: [2023-04-29 11:37:30,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +59: [2023-04-29 11:37:30,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +17: [2023-04-29 11:37:30,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +59: [2023-04-29 11:37:30,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +13: [2023-04-29 11:37:30,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +19: [2023-04-29 11:37:30,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +13: [2023-04-29 11:37:30,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +52: [2023-04-29 11:37:30,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +52: [2023-04-29 11:37:30,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +19: [2023-04-29 11:37:30,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +42: [2023-04-29 11:37:30,354] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +21: [2023-04-29 11:37:30,354] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +19: [2023-04-29 11:37:30,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 3: [2023-04-29 11:37:30,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +57: [2023-04-29 11:37:30,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +58: [2023-04-29 11:37:30,354] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +14: [2023-04-29 11:37:30,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +44: [2023-04-29 11:37:30,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +51: [2023-04-29 11:37:30,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +60: [2023-04-29 11:37:30,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +31: [2023-04-29 11:37:30,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +31: [2023-04-29 11:37:30,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +39: [2023-04-29 11:37:30,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +60: [2023-04-29 11:37:30,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +44: [2023-04-29 11:37:30,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +58: [2023-04-29 11:37:30,357] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +38: [2023-04-29 11:37:30,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +44: [2023-04-29 11:37:30,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +13: [2023-04-29 11:37:30,357] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +13: [2023-04-29 11:37:30,357] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +31: [2023-04-29 11:37:30,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +47: [2023-04-29 11:37:30,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +39: [2023-04-29 11:37:30,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +31: [2023-04-29 11:37:30,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +41: [2023-04-29 11:37:30,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +41: [2023-04-29 11:37:30,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +41: [2023-04-29 11:37:30,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +44: [2023-04-29 11:37:30,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +63: [2023-04-29 11:37:30,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +22: [2023-04-29 11:37:30,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +22: [2023-04-29 11:37:30,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +22: [2023-04-29 11:37:30,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +21: [2023-04-29 11:37:30,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +41: [2023-04-29 11:37:30,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +63: [2023-04-29 11:37:30,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +14: [2023-04-29 11:37:30,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +14: [2023-04-29 11:37:30,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +35: [2023-04-29 11:37:30,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +38: [2023-04-29 11:37:30,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +60: [2023-04-29 11:37:30,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +17: [2023-04-29 11:37:30,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 6: [2023-04-29 11:37:30,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +52: [2023-04-29 11:37:30,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... + 6: [2023-04-29 11:37:30,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +47: [2023-04-29 11:37:30,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +36: [2023-04-29 11:37:30,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +42: [2023-04-29 11:37:30,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +40: [2023-04-29 11:37:30,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +40: [2023-04-29 11:37:30,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +60: [2023-04-29 11:37:30,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +38: [2023-04-29 11:37:30,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +52: [2023-04-29 11:37:30,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +13: [2023-04-29 11:37:30,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +38: [2023-04-29 11:37:30,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +13: [2023-04-29 11:37:30,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +63: [2023-04-29 11:37:30,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +55: [2023-04-29 11:37:30,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +55: [2023-04-29 11:37:30,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +35: [2023-04-29 11:37:30,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +57: [2023-04-29 11:37:30,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +57: [2023-04-29 11:37:30,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +57: [2023-04-29 11:37:30,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +13: [2023-04-29 11:37:30,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +13: [2023-04-29 11:37:30,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +39: [2023-04-29 11:37:30,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +41: [2023-04-29 11:37:30,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +38: [2023-04-29 11:37:30,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +41: [2023-04-29 11:37:30,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +21: [2023-04-29 11:37:30,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +38: [2023-04-29 11:37:30,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 6: [2023-04-29 11:37:30,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +54: [2023-04-29 11:37:30,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +54: [2023-04-29 11:37:30,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +39: [2023-04-29 11:37:30,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +41: [2023-04-29 11:37:30,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +35: [2023-04-29 11:37:30,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +55: [2023-04-29 11:37:30,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +54: [2023-04-29 11:37:30,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +55: [2023-04-29 11:37:30,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +54: [2023-04-29 11:37:30,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +17: [2023-04-29 11:37:30,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +63: [2023-04-29 11:37:30,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. + 6: [2023-04-29 11:37:30,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +41: [2023-04-29 11:37:30,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +63: [2023-04-29 11:37:30,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +46: [2023-04-29 11:37:30,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +63: [2023-04-29 11:37:30,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +36: [2023-04-29 11:37:30,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +42: [2023-04-29 11:37:30,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +48: [2023-04-29 11:37:30,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +48: [2023-04-29 11:37:30,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +55: [2023-04-29 11:37:30,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +55: [2023-04-29 11:37:30,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +48: [2023-04-29 11:37:30,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +57: [2023-04-29 11:37:30,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +57: [2023-04-29 11:37:30,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +43: [2023-04-29 11:37:30,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +43: [2023-04-29 11:37:30,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +55: [2023-04-29 11:37:30,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +57: [2023-04-29 11:37:30,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +28: [2023-04-29 11:37:30,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +28: [2023-04-29 11:37:30,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +46: [2023-04-29 11:37:30,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +13: [2023-04-29 11:37:30,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +13: [2023-04-29 11:37:30,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +21: [2023-04-29 11:37:30,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +43: [2023-04-29 11:37:30,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +48: [2023-04-29 11:37:30,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +43: [2023-04-29 11:37:30,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +63: [2023-04-29 11:37:30,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +35: [2023-04-29 11:37:30,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +55: [2023-04-29 11:37:30,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +21: [2023-04-29 11:37:30,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +28: [2023-04-29 11:37:30,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. + 2: [2023-04-29 11:37:30,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 2: [2023-04-29 11:37:30,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +38: [2023-04-29 11:37:30,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +28: [2023-04-29 11:37:30,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +46: [2023-04-29 11:37:30,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +47: [2023-04-29 11:37:30,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +46: [2023-04-29 11:37:30,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +30: [2023-04-29 11:37:30,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +30: [2023-04-29 11:37:30,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +63: [2023-04-29 11:37:30,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +15: [2023-04-29 11:37:30,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +15: [2023-04-29 11:37:30,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +22: [2023-04-29 11:37:30,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +59: [2023-04-29 11:37:30,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +59: [2023-04-29 11:37:30,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +15: [2023-04-29 11:37:30,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +46: [2023-04-29 11:37:30,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +40: [2023-04-29 11:37:30,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 2: [2023-04-29 11:37:30,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +15: [2023-04-29 11:37:30,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +63: [2023-04-29 11:37:30,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. + 2: [2023-04-29 11:37:30,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +35: [2023-04-29 11:37:30,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +25: [2023-04-29 11:37:30,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +25: [2023-04-29 11:37:30,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 6: [2023-04-29 11:37:30,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 6: [2023-04-29 11:37:30,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +40: [2023-04-29 11:37:30,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +35: [2023-04-29 11:37:30,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +25: [2023-04-29 11:37:30,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +42: [2023-04-29 11:37:30,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +25: [2023-04-29 11:37:30,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +30: [2023-04-29 11:37:30,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +43: [2023-04-29 11:37:30,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +43: [2023-04-29 11:37:30,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +43: [2023-04-29 11:37:30,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +47: [2023-04-29 11:37:30,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +47: [2023-04-29 11:37:30,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +30: [2023-04-29 11:37:30,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +30: [2023-04-29 11:37:30,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +30: [2023-04-29 11:37:30,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +47: [2023-04-29 11:37:30,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +47: [2023-04-29 11:37:30,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +38: [2023-04-29 11:37:30,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +42: [2023-04-29 11:37:30,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +58: [2023-04-29 11:37:30,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +43: [2023-04-29 11:37:30,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +58: [2023-04-29 11:37:30,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +30: [2023-04-29 11:37:30,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 2: [2023-04-29 11:37:30,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +30: [2023-04-29 11:37:30,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +46: [2023-04-29 11:37:30,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +21: [2023-04-29 11:37:30,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... + 6: [2023-04-29 11:37:30,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +25: [2023-04-29 11:37:30,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +25: [2023-04-29 11:37:30,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +42: [2023-04-29 11:37:30,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +17: [2023-04-29 11:37:30,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +63: [2023-04-29 11:37:30,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... + 6: [2023-04-29 11:37:30,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 2: [2023-04-29 11:37:30,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 2: [2023-04-29 11:37:30,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +36: [2023-04-29 11:37:30,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +36: [2023-04-29 11:37:30,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +15: [2023-04-29 11:37:30,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +15: [2023-04-29 11:37:30,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +11: [2023-04-29 11:37:30,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +11: [2023-04-29 11:37:30,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +11: [2023-04-29 11:37:30,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +25: [2023-04-29 11:37:30,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +11: [2023-04-29 11:37:30,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +15: [2023-04-29 11:37:30,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +16: [2023-04-29 11:37:30,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +16: [2023-04-29 11:37:30,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +25: [2023-04-29 11:37:30,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +15: [2023-04-29 11:37:30,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +17: [2023-04-29 11:37:30,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +25: [2023-04-29 11:37:30,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 2: [2023-04-29 11:37:30,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +46: [2023-04-29 11:37:30,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +26: [2023-04-29 11:37:30,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +26: [2023-04-29 11:37:30,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +58: [2023-04-29 11:37:30,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +25: [2023-04-29 11:37:30,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +35: [2023-04-29 11:37:30,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +15: [2023-04-29 11:37:30,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +15: [2023-04-29 11:37:30,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +25: [2023-04-29 11:37:30,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +31: [2023-04-29 11:37:30,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +31: [2023-04-29 11:37:30,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +31: [2023-04-29 11:37:30,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +59: [2023-04-29 11:37:30,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... +26: [2023-04-29 11:37:30,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +26: [2023-04-29 11:37:30,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +26: [2023-04-29 11:37:30,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 1: [2023-04-29 11:37:30,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. + 1: [2023-04-29 11:37:30,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +59: [2023-04-29 11:37:30,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt... + 1: [2023-04-29 11:37:30,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +30: [2023-04-29 11:37:30,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +42: [2023-04-29 11:37:30,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +26: [2023-04-29 11:37:30,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. + 6: [2023-04-29 11:37:30,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... + 6: [2023-04-29 11:37:30,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +58: [2023-04-29 11:37:30,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 6: [2023-04-29 11:37:30,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... + 1: [2023-04-29 11:37:30,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +25: [2023-04-29 11:37:30,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +30: [2023-04-29 11:37:30,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +15: [2023-04-29 11:37:30,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +30: [2023-04-29 11:37:30,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +30: [2023-04-29 11:37:30,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +15: [2023-04-29 11:37:30,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +16: [2023-04-29 11:37:30,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +16: [2023-04-29 11:37:30,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +33: [2023-04-29 11:37:30,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +31: [2023-04-29 11:37:30,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 3: [2023-04-29 11:37:30,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. + 3: [2023-04-29 11:37:30,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. + 3: [2023-04-29 11:37:30,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +26: [2023-04-29 11:37:30,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +31: [2023-04-29 11:37:30,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +26: [2023-04-29 11:37:30,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +46: [2023-04-29 11:37:30,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +22: [2023-04-29 11:37:30,389] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 6: [2023-04-29 11:37:30,389] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +31: [2023-04-29 11:37:30,389] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +42: [2023-04-29 11:37:30,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +22: [2023-04-29 11:37:30,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +43: [2023-04-29 11:37:30,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. + 3: [2023-04-29 11:37:30,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +22: [2023-04-29 11:37:30,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +31: [2023-04-29 11:37:30,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +31: [2023-04-29 11:37:30,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +31: [2023-04-29 11:37:30,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +53: [2023-04-29 11:37:30,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +26: [2023-04-29 11:37:30,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +33: [2023-04-29 11:37:30,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +10: [2023-04-29 11:37:30,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +10: [2023-04-29 11:37:30,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +26: [2023-04-29 11:37:30,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +40: [2023-04-29 11:37:30,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +31: [2023-04-29 11:37:30,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +31: [2023-04-29 11:37:30,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +54: [2023-04-29 11:37:30,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +12: [2023-04-29 11:37:30,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +40: [2023-04-29 11:37:30,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +26: [2023-04-29 11:37:30,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +36: [2023-04-29 11:37:30,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +26: [2023-04-29 11:37:30,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +31: [2023-04-29 11:37:30,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +22: [2023-04-29 11:37:30,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +22: [2023-04-29 11:37:30,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +22: [2023-04-29 11:37:30,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +54: [2023-04-29 11:37:30,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +32: [2023-04-29 11:37:30,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +43: [2023-04-29 11:37:30,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +35: [2023-04-29 11:37:30,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +10: [2023-04-29 11:37:30,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +10: [2023-04-29 11:37:30,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 5: [2023-04-29 11:37:30,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. + 5: [2023-04-29 11:37:30,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. + 5: [2023-04-29 11:37:30,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. + 4: [2023-04-29 11:37:30,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 5: [2023-04-29 11:37:30,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. + 9: [2023-04-29 11:37:30,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. + 9: [2023-04-29 11:37:30,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +22: [2023-04-29 11:37:30,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +54: [2023-04-29 11:37:30,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +54: [2023-04-29 11:37:30,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +43: [2023-04-29 11:37:30,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +32: [2023-04-29 11:37:30,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +10: [2023-04-29 11:37:30,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +35: [2023-04-29 11:37:30,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +36: [2023-04-29 11:37:30,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +14: [2023-04-29 11:37:30,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +10: [2023-04-29 11:37:30,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +14: [2023-04-29 11:37:30,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +14: [2023-04-29 11:37:30,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 9: [2023-04-29 11:37:30,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. + 9: [2023-04-29 11:37:30,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +10: [2023-04-29 11:37:30,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +28: [2023-04-29 11:37:30,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +10: [2023-04-29 11:37:30,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +43: [2023-04-29 11:37:30,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +28: [2023-04-29 11:37:30,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +43: [2023-04-29 11:37:30,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +43: [2023-04-29 11:37:30,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +10: [2023-04-29 11:37:30,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +40: [2023-04-29 11:37:30,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +29: [2023-04-29 11:37:30,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +29: [2023-04-29 11:37:30,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +29: [2023-04-29 11:37:30,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +30: [2023-04-29 11:37:30,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +29: [2023-04-29 11:37:30,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +12: [2023-04-29 11:37:30,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +30: [2023-04-29 11:37:30,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +30: [2023-04-29 11:37:30,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +35: [2023-04-29 11:37:30,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +28: [2023-04-29 11:37:30,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +47: [2023-04-29 11:37:30,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +30: [2023-04-29 11:37:30,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +28: [2023-04-29 11:37:30,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +33: [2023-04-29 11:37:30,405] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +32: [2023-04-29 11:37:30,405] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +32: [2023-04-29 11:37:30,405] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +25: [2023-04-29 11:37:30,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +47: [2023-04-29 11:37:30,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +47: [2023-04-29 11:37:30,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +25: [2023-04-29 11:37:30,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +35: [2023-04-29 11:37:30,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +28: [2023-04-29 11:37:30,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +28: [2023-04-29 11:37:30,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 4: [2023-04-29 11:37:30,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 4: [2023-04-29 11:37:30,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 4: [2023-04-29 11:37:30,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +12: [2023-04-29 11:37:30,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +47: [2023-04-29 11:37:30,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +13: [2023-04-29 11:37:30,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +43: [2023-04-29 11:37:30,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +12: [2023-04-29 11:37:30,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +53: [2023-04-29 11:37:30,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +53: [2023-04-29 11:37:30,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +53: [2023-04-29 11:37:30,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +43: [2023-04-29 11:37:30,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +10: [2023-04-29 11:37:30,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +25: [2023-04-29 11:37:30,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +14: [2023-04-29 11:37:30,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +16: [2023-04-29 11:37:30,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +16: [2023-04-29 11:37:30,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +25: [2023-04-29 11:37:30,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +33: [2023-04-29 11:37:30,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... + 1: [2023-04-29 11:37:30,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +11: [2023-04-29 11:37:30,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +11: [2023-04-29 11:37:30,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 5: [2023-04-29 11:37:30,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 5: [2023-04-29 11:37:30,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +11: [2023-04-29 11:37:30,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 5: [2023-04-29 11:37:30,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 5: [2023-04-29 11:37:30,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +44: [2023-04-29 11:37:30,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +28: [2023-04-29 11:37:30,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +28: [2023-04-29 11:37:30,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +11: [2023-04-29 11:37:30,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 1: [2023-04-29 11:37:30,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 1: [2023-04-29 11:37:30,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 1: [2023-04-29 11:37:30,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +10: [2023-04-29 11:37:30,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +57: [2023-04-29 11:37:30,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +57: [2023-04-29 11:37:30,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +14: [2023-04-29 11:37:30,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +13: [2023-04-29 11:37:30,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +26: [2023-04-29 11:37:30,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +33: [2023-04-29 11:37:30,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +26: [2023-04-29 11:37:30,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +15: [2023-04-29 11:37:30,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +10: [2023-04-29 11:37:30,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +16: [2023-04-29 11:37:30,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +53: [2023-04-29 11:37:30,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +44: [2023-04-29 11:37:30,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +15: [2023-04-29 11:37:30,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +57: [2023-04-29 11:37:30,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +15: [2023-04-29 11:37:30,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 3: [2023-04-29 11:37:30,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 3: [2023-04-29 11:37:30,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +51: [2023-04-29 11:37:30,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +51: [2023-04-29 11:37:30,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +51: [2023-04-29 11:37:30,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +16: [2023-04-29 11:37:30,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +51: [2023-04-29 11:37:30,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 3: [2023-04-29 11:37:30,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 3: [2023-04-29 11:37:30,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +10: [2023-04-29 11:37:30,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +10: [2023-04-29 11:37:30,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +15: [2023-04-29 11:37:30,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +33: [2023-04-29 11:37:30,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +26: [2023-04-29 11:37:30,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +14: [2023-04-29 11:37:30,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... + 1: [2023-04-29 11:37:30,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 1: [2023-04-29 11:37:30,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 1: [2023-04-29 11:37:30,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 4: [2023-04-29 11:37:30,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +44: [2023-04-29 11:37:30,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 1: [2023-04-29 11:37:30,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +12: [2023-04-29 11:37:30,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +53: [2023-04-29 11:37:30,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +53: [2023-04-29 11:37:30,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +53: [2023-04-29 11:37:30,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +60: [2023-04-29 11:37:30,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +22: [2023-04-29 11:37:30,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +33: [2023-04-29 11:37:30,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +10: [2023-04-29 11:37:30,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +44: [2023-04-29 11:37:30,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +23: [2023-04-29 11:37:30,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +57: [2023-04-29 11:37:30,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +23: [2023-04-29 11:37:30,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +23: [2023-04-29 11:37:30,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +23: [2023-04-29 11:37:30,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +23: [2023-04-29 11:37:30,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +51: [2023-04-29 11:37:30,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +44: [2023-04-29 11:37:30,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +34: [2023-04-29 11:37:30,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +34: [2023-04-29 11:37:30,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +23: [2023-04-29 11:37:30,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +23: [2023-04-29 11:37:30,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +23: [2023-04-29 11:37:30,425] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +34: [2023-04-29 11:37:30,425] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +33: [2023-04-29 11:37:30,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +34: [2023-04-29 11:37:30,425] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. + 9: [2023-04-29 11:37:30,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +10: [2023-04-29 11:37:30,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +32: [2023-04-29 11:37:30,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +22: [2023-04-29 11:37:30,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +22: [2023-04-29 11:37:30,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +32: [2023-04-29 11:37:30,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 1: [2023-04-29 11:37:30,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 1: [2023-04-29 11:37:30,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +44: [2023-04-29 11:37:30,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +60: [2023-04-29 11:37:30,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... + 1: [2023-04-29 11:37:30,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +51: [2023-04-29 11:37:30,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +51: [2023-04-29 11:37:30,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 9: [2023-04-29 11:37:30,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +53: [2023-04-29 11:37:30,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +53: [2023-04-29 11:37:30,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +53: [2023-04-29 11:37:30,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... + 5: [2023-04-29 11:37:30,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +26: [2023-04-29 11:37:30,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +58: [2023-04-29 11:37:30,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +58: [2023-04-29 11:37:30,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +58: [2023-04-29 11:37:30,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. + 1: [2023-04-29 11:37:30,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +41: [2023-04-29 11:37:30,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +22: [2023-04-29 11:37:30,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +29: [2023-04-29 11:37:30,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 5: [2023-04-29 11:37:30,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 9: [2023-04-29 11:37:30,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 5: [2023-04-29 11:37:30,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 5: [2023-04-29 11:37:30,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +51: [2023-04-29 11:37:30,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +23: [2023-04-29 11:37:30,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +58: [2023-04-29 11:37:30,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +14: [2023-04-29 11:37:30,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +19: [2023-04-29 11:37:30,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +19: [2023-04-29 11:37:30,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +59: [2023-04-29 11:37:30,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +59: [2023-04-29 11:37:30,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +29: [2023-04-29 11:37:30,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +37: [2023-04-29 11:37:30,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +37: [2023-04-29 11:37:30,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +37: [2023-04-29 11:37:30,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +44: [2023-04-29 11:37:30,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +14: [2023-04-29 11:37:30,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +60: [2023-04-29 11:37:30,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +37: [2023-04-29 11:37:30,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +13: [2023-04-29 11:37:30,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +50: [2023-04-29 11:37:30,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +50: [2023-04-29 11:37:30,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +23: [2023-04-29 11:37:30,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +23: [2023-04-29 11:37:30,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +23: [2023-04-29 11:37:30,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +60: [2023-04-29 11:37:30,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +44: [2023-04-29 11:37:30,432] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +13: [2023-04-29 11:37:30,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +19: [2023-04-29 11:37:30,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 7: [2023-04-29 11:37:30,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 7: [2023-04-29 11:37:30,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +19: [2023-04-29 11:37:30,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +24: [2023-04-29 11:37:30,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +24: [2023-04-29 11:37:30,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +59: [2023-04-29 11:37:30,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +59: [2023-04-29 11:37:30,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +19: [2023-04-29 11:37:30,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 9: [2023-04-29 11:37:30,432] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +19: [2023-04-29 11:37:30,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +19: [2023-04-29 11:37:30,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +39: [2023-04-29 11:37:30,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +39: [2023-04-29 11:37:30,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +29: [2023-04-29 11:37:30,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +14: [2023-04-29 11:37:30,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +19: [2023-04-29 11:37:30,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +24: [2023-04-29 11:37:30,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +24: [2023-04-29 11:37:30,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +24: [2023-04-29 11:37:30,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +24: [2023-04-29 11:37:30,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +24: [2023-04-29 11:37:30,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +48: [2023-04-29 11:37:30,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +29: [2023-04-29 11:37:30,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +23: [2023-04-29 11:37:30,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +24: [2023-04-29 11:37:30,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +19: [2023-04-29 11:37:30,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +23: [2023-04-29 11:37:30,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +23: [2023-04-29 11:37:30,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +55: [2023-04-29 11:37:30,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +23: [2023-04-29 11:37:30,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +19: [2023-04-29 11:37:30,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 7: [2023-04-29 11:37:30,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. + 7: [2023-04-29 11:37:30,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +12: [2023-04-29 11:37:30,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +50: [2023-04-29 11:37:30,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +38: [2023-04-29 11:37:30,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +38: [2023-04-29 11:37:30,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +50: [2023-04-29 11:37:30,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. + 7: [2023-04-29 11:37:30,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +60: [2023-04-29 11:37:30,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +39: [2023-04-29 11:37:30,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 7: [2023-04-29 11:37:30,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +13: [2023-04-29 11:37:30,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +13: [2023-04-29 11:37:30,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +60: [2023-04-29 11:37:30,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +39: [2023-04-29 11:37:30,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +24: [2023-04-29 11:37:30,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +24: [2023-04-29 11:37:30,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +32: [2023-04-29 11:37:30,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 7: [2023-04-29 11:37:30,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +32: [2023-04-29 11:37:30,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +28: [2023-04-29 11:37:30,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +28: [2023-04-29 11:37:30,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +48: [2023-04-29 11:37:30,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +60: [2023-04-29 11:37:30,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +24: [2023-04-29 11:37:30,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +39: [2023-04-29 11:37:30,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +19: [2023-04-29 11:37:30,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +39: [2023-04-29 11:37:30,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +24: [2023-04-29 11:37:30,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +19: [2023-04-29 11:37:30,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +12: [2023-04-29 11:37:30,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 4: [2023-04-29 11:37:30,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +43: [2023-04-29 11:37:30,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 7: [2023-04-29 11:37:30,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +14: [2023-04-29 11:37:30,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +39: [2023-04-29 11:37:30,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +24: [2023-04-29 11:37:30,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +57: [2023-04-29 11:37:30,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +24: [2023-04-29 11:37:30,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... + 7: [2023-04-29 11:37:30,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +24: [2023-04-29 11:37:30,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +41: [2023-04-29 11:37:30,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +24: [2023-04-29 11:37:30,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +28: [2023-04-29 11:37:30,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 7: [2023-04-29 11:37:30,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +41: [2023-04-29 11:37:30,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +41: [2023-04-29 11:37:30,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +59: [2023-04-29 11:37:30,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +19: [2023-04-29 11:37:30,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +57: [2023-04-29 11:37:30,442] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +55: [2023-04-29 11:37:30,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +19: [2023-04-29 11:37:30,442] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... + 4: [2023-04-29 11:37:30,442] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 2: [2023-04-29 11:37:30,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. + 2: [2023-04-29 11:37:30,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. +53: [2023-04-29 11:37:30,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +19: [2023-04-29 11:37:30,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 7: [2023-04-29 11:37:30,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +19: [2023-04-29 11:37:30,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +38: [2023-04-29 11:37:30,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +38: [2023-04-29 11:37:30,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +12: [2023-04-29 11:37:30,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +14: [2023-04-29 11:37:30,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +14: [2023-04-29 11:37:30,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +53: [2023-04-29 11:37:30,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +53: [2023-04-29 11:37:30,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +13: [2023-04-29 11:37:30,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +14: [2023-04-29 11:37:30,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +53: [2023-04-29 11:37:30,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +28: [2023-04-29 11:37:30,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +34: [2023-04-29 11:37:30,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +34: [2023-04-29 11:37:30,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +13: [2023-04-29 11:37:30,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +13: [2023-04-29 11:37:30,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +59: [2023-04-29 11:37:30,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. + 4: [2023-04-29 11:37:30,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +39: [2023-04-29 11:37:30,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 7: [2023-04-29 11:37:30,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +54: [2023-04-29 11:37:30,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +55: [2023-04-29 11:37:30,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +60: [2023-04-29 11:37:30,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +38: [2023-04-29 11:37:30,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +57: [2023-04-29 11:37:30,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 5: [2023-04-29 11:37:30,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +48: [2023-04-29 11:37:30,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +48: [2023-04-29 11:37:30,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +48: [2023-04-29 11:37:30,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 2: [2023-04-29 11:37:30,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. + 5: [2023-04-29 11:37:30,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +55: [2023-04-29 11:37:30,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 2: [2023-04-29 11:37:30,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_10-model_01-model_states.pt. + 2: [2023-04-29 11:37:30,447] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 2: [2023-04-29 11:37:30,447] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 5: [2023-04-29 11:37:30,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 5: [2023-04-29 11:37:30,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +38: [2023-04-29 11:37:30,447] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +54: [2023-04-29 11:37:30,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +59: [2023-04-29 11:37:30,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +34: [2023-04-29 11:37:30,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +34: [2023-04-29 11:37:30,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +59: [2023-04-29 11:37:30,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +53: [2023-04-29 11:37:30,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +14: [2023-04-29 11:37:30,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +14: [2023-04-29 11:37:30,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +13: [2023-04-29 11:37:30,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +14: [2023-04-29 11:37:30,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +38: [2023-04-29 11:37:30,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +34: [2023-04-29 11:37:30,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +43: [2023-04-29 11:37:30,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +43: [2023-04-29 11:37:30,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +57: [2023-04-29 11:37:30,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +48: [2023-04-29 11:37:30,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +48: [2023-04-29 11:37:30,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +48: [2023-04-29 11:37:30,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +34: [2023-04-29 11:37:30,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +43: [2023-04-29 11:37:30,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +37: [2023-04-29 11:37:30,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +25: [2023-04-29 11:37:30,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +38: [2023-04-29 11:37:30,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +58: [2023-04-29 11:37:30,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +34: [2023-04-29 11:37:30,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +55: [2023-04-29 11:37:30,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +56: [2023-04-29 11:37:30,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +56: [2023-04-29 11:37:30,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +59: [2023-04-29 11:37:30,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +34: [2023-04-29 11:37:30,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +34: [2023-04-29 11:37:30,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +30: [2023-04-29 11:37:30,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +13: [2023-04-29 11:37:30,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 2: [2023-04-29 11:37:30,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +13: [2023-04-29 11:37:30,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 2: [2023-04-29 11:37:30,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +13: [2023-04-29 11:37:30,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +45: [2023-04-29 11:37:30,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +13: [2023-04-29 11:37:30,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +45: [2023-04-29 11:37:30,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +45: [2023-04-29 11:37:30,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +41: [2023-04-29 11:37:30,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +50: [2023-04-29 11:37:30,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +45: [2023-04-29 11:37:30,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +50: [2023-04-29 11:37:30,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +34: [2023-04-29 11:37:30,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +58: [2023-04-29 11:37:30,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +30: [2023-04-29 11:37:30,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +58: [2023-04-29 11:37:30,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +58: [2023-04-29 11:37:30,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +37: [2023-04-29 11:37:30,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +37: [2023-04-29 11:37:30,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +37: [2023-04-29 11:37:30,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +31: [2023-04-29 11:37:30,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +56: [2023-04-29 11:37:30,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +56: [2023-04-29 11:37:30,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +54: [2023-04-29 11:37:30,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +43: [2023-04-29 11:37:30,463] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +59: [2023-04-29 11:37:30,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +59: [2023-04-29 11:37:30,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +59: [2023-04-29 11:37:30,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +56: [2023-04-29 11:37:30,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +45: [2023-04-29 11:37:30,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +25: [2023-04-29 11:37:30,464] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +16: [2023-04-29 11:37:30,464] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +16: [2023-04-29 11:37:30,464] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +56: [2023-04-29 11:37:30,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +16: [2023-04-29 11:37:30,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +45: [2023-04-29 11:37:30,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +16: [2023-04-29 11:37:30,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +59: [2023-04-29 11:37:30,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +31: [2023-04-29 11:37:30,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +31: [2023-04-29 11:37:30,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +31: [2023-04-29 11:37:30,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +31: [2023-04-29 11:37:30,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +34: [2023-04-29 11:37:30,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +34: [2023-04-29 11:37:30,466] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +45: [2023-04-29 11:37:30,466] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +54: [2023-04-29 11:37:30,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +56: [2023-04-29 11:37:30,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +56: [2023-04-29 11:37:30,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +15: [2023-04-29 11:37:30,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +15: [2023-04-29 11:37:30,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +50: [2023-04-29 11:37:30,466] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +45: [2023-04-29 11:37:30,466] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +25: [2023-04-29 11:37:30,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +56: [2023-04-29 11:37:30,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +26: [2023-04-29 11:37:30,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 7: [2023-04-29 11:37:30,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +56: [2023-04-29 11:37:30,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +26: [2023-04-29 11:37:30,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 7: [2023-04-29 11:37:30,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +54: [2023-04-29 11:37:30,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +59: [2023-04-29 11:37:30,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_00-model_states.pt. +56: [2023-04-29 11:37:30,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +15: [2023-04-29 11:37:30,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 7: [2023-04-29 11:37:30,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +56: [2023-04-29 11:37:30,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +10: [2023-04-29 11:37:30,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +10: [2023-04-29 11:37:30,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +54: [2023-04-29 11:37:30,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +55: [2023-04-29 11:37:30,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +59: [2023-04-29 11:37:30,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +50: [2023-04-29 11:37:30,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +31: [2023-04-29 11:37:30,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +10: [2023-04-29 11:37:30,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +30: [2023-04-29 11:37:30,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +55: [2023-04-29 11:37:30,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +20: [2023-04-29 11:37:30,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +20: [2023-04-29 11:37:30,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +20: [2023-04-29 11:37:30,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +31: [2023-04-29 11:37:30,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +31: [2023-04-29 11:37:30,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +20: [2023-04-29 11:37:30,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +25: [2023-04-29 11:37:30,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +10: [2023-04-29 11:37:30,473] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +25: [2023-04-29 11:37:30,473] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +54: [2023-04-29 11:37:30,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +59: [2023-04-29 11:37:30,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt... +30: [2023-04-29 11:37:30,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +30: [2023-04-29 11:37:30,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +16: [2023-04-29 11:37:30,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +16: [2023-04-29 11:37:30,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 1: [2023-04-29 11:37:30,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +55: [2023-04-29 11:37:30,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +15: [2023-04-29 11:37:30,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +16: [2023-04-29 11:37:30,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +47: [2023-04-29 11:37:30,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +11: [2023-04-29 11:37:30,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +54: [2023-04-29 11:37:30,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +31: [2023-04-29 11:37:30,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +42: [2023-04-29 11:37:30,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +41: [2023-04-29 11:37:30,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +42: [2023-04-29 11:37:30,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +42: [2023-04-29 11:37:30,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 7: [2023-04-29 11:37:30,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 9: [2023-04-29 11:37:30,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +42: [2023-04-29 11:37:30,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 9: [2023-04-29 11:37:30,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +16: [2023-04-29 11:37:30,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 9: [2023-04-29 11:37:30,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 1: [2023-04-29 11:37:30,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +20: [2023-04-29 11:37:30,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +28: [2023-04-29 11:37:30,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +28: [2023-04-29 11:37:30,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +28: [2023-04-29 11:37:30,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 9: [2023-04-29 11:37:30,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 2: [2023-04-29 11:37:30,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +20: [2023-04-29 11:37:30,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +41: [2023-04-29 11:37:30,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +41: [2023-04-29 11:37:30,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +31: [2023-04-29 11:37:30,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +20: [2023-04-29 11:37:30,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +25: [2023-04-29 11:37:30,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +20: [2023-04-29 11:37:30,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 1: [2023-04-29 11:37:30,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +11: [2023-04-29 11:37:30,479] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +11: [2023-04-29 11:37:30,479] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +30: [2023-04-29 11:37:30,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... + 2: [2023-04-29 11:37:30,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 2: [2023-04-29 11:37:30,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 2: [2023-04-29 11:37:30,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 2: [2023-04-29 11:37:30,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 2: [2023-04-29 11:37:30,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +31: [2023-04-29 11:37:30,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +31: [2023-04-29 11:37:30,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +25: [2023-04-29 11:37:30,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +11: [2023-04-29 11:37:30,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +28: [2023-04-29 11:37:30,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +11: [2023-04-29 11:37:30,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 3: [2023-04-29 11:37:30,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 3: [2023-04-29 11:37:30,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +26: [2023-04-29 11:37:30,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +26: [2023-04-29 11:37:30,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +47: [2023-04-29 11:37:30,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +42: [2023-04-29 11:37:30,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +47: [2023-04-29 11:37:30,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +42: [2023-04-29 11:37:30,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +42: [2023-04-29 11:37:30,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 1: [2023-04-29 11:37:30,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +15: [2023-04-29 11:37:30,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +42: [2023-04-29 11:37:30,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +16: [2023-04-29 11:37:30,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +16: [2023-04-29 11:37:30,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 9: [2023-04-29 11:37:30,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +47: [2023-04-29 11:37:30,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +47: [2023-04-29 11:37:30,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +13: [2023-04-29 11:37:30,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +30: [2023-04-29 11:37:30,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +28: [2023-04-29 11:37:30,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +28: [2023-04-29 11:37:30,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +28: [2023-04-29 11:37:30,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +22: [2023-04-29 11:37:30,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +43: [2023-04-29 11:37:30,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +11: [2023-04-29 11:37:30,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +43: [2023-04-29 11:37:30,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +11: [2023-04-29 11:37:30,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +43: [2023-04-29 11:37:30,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 9: [2023-04-29 11:37:30,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 3: [2023-04-29 11:37:30,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 9: [2023-04-29 11:37:30,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... + 9: [2023-04-29 11:37:30,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt... +11: [2023-04-29 11:37:30,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +28: [2023-04-29 11:37:30,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... + 1: [2023-04-29 11:37:30,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 3: [2023-04-29 11:37:30,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +13: [2023-04-29 11:37:30,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 3: [2023-04-29 11:37:30,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +47: [2023-04-29 11:37:30,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +30: [2023-04-29 11:37:30,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +30: [2023-04-29 11:37:30,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +30: [2023-04-29 11:37:30,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 3: [2023-04-29 11:37:30,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +30: [2023-04-29 11:37:30,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +16: [2023-04-29 11:37:30,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +16: [2023-04-29 11:37:30,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +30: [2023-04-29 11:37:30,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +22: [2023-04-29 11:37:30,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +29: [2023-04-29 11:37:30,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +15: [2023-04-29 11:37:30,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... + 1: [2023-04-29 11:37:30,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +19: [2023-04-29 11:37:30,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +25: [2023-04-29 11:37:30,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +26: [2023-04-29 11:37:30,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +47: [2023-04-29 11:37:30,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +23: [2023-04-29 11:37:30,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +47: [2023-04-29 11:37:30,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... + 3: [2023-04-29 11:37:30,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +29: [2023-04-29 11:37:30,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 1: [2023-04-29 11:37:30,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +61: [2023-04-29 11:37:30,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +61: [2023-04-29 11:37:30,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +61: [2023-04-29 11:37:30,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +61: [2023-04-29 11:37:30,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +31: [2023-04-29 11:37:30,493] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 3: [2023-04-29 11:37:30,493] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +29: [2023-04-29 11:37:30,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +51: [2023-04-29 11:37:30,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +25: [2023-04-29 11:37:30,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +26: [2023-04-29 11:37:30,495] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +25: [2023-04-29 11:37:30,495] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +26: [2023-04-29 11:37:30,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +30: [2023-04-29 11:37:30,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +30: [2023-04-29 11:37:30,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +22: [2023-04-29 11:37:30,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +22: [2023-04-29 11:37:30,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 1: [2023-04-29 11:37:30,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +23: [2023-04-29 11:37:30,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +25: [2023-04-29 11:37:30,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 9: [2023-04-29 11:37:30,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +15: [2023-04-29 11:37:30,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 2: [2023-04-29 11:37:30,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 2: [2023-04-29 11:37:30,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +25: [2023-04-29 11:37:30,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +31: [2023-04-29 11:37:30,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +31: [2023-04-29 11:37:30,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +26: [2023-04-29 11:37:30,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +29: [2023-04-29 11:37:30,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... + 1: [2023-04-29 11:37:30,497] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +61: [2023-04-29 11:37:30,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +61: [2023-04-29 11:37:30,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +24: [2023-04-29 11:37:30,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +24: [2023-04-29 11:37:30,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +62: [2023-04-29 11:37:30,499] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +62: [2023-04-29 11:37:30,499] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +62: [2023-04-29 11:37:30,499] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +56: [2023-04-29 11:37:30,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +26: [2023-04-29 11:37:30,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +22: [2023-04-29 11:37:30,499] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +10: [2023-04-29 11:37:30,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +62: [2023-04-29 11:37:30,499] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +10: [2023-04-29 11:37:30,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +39: [2023-04-29 11:37:30,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +56: [2023-04-29 11:37:30,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +10: [2023-04-29 11:37:30,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +26: [2023-04-29 11:37:30,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +61: [2023-04-29 11:37:30,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +24: [2023-04-29 11:37:30,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +25: [2023-04-29 11:37:30,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +10: [2023-04-29 11:37:30,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +25: [2023-04-29 11:37:30,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 1: [2023-04-29 11:37:30,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +25: [2023-04-29 11:37:30,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +61: [2023-04-29 11:37:30,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +29: [2023-04-29 11:37:30,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 1: [2023-04-29 11:37:30,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +15: [2023-04-29 11:37:30,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +56: [2023-04-29 11:37:30,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +16: [2023-04-29 11:37:30,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 1: [2023-04-29 11:37:30,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 5: [2023-04-29 11:37:30,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +29: [2023-04-29 11:37:30,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +22: [2023-04-29 11:37:30,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +15: [2023-04-29 11:37:30,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +15: [2023-04-29 11:37:30,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 5: [2023-04-29 11:37:30,502] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +22: [2023-04-29 11:37:30,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... + 9: [2023-04-29 11:37:30,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +56: [2023-04-29 11:37:30,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +25: [2023-04-29 11:37:30,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +19: [2023-04-29 11:37:30,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +23: [2023-04-29 11:37:30,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +23: [2023-04-29 11:37:30,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +31: [2023-04-29 11:37:30,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 9: [2023-04-29 11:37:30,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +19: [2023-04-29 11:37:30,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +22: [2023-04-29 11:37:30,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... + 5: [2023-04-29 11:37:30,505] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 5: [2023-04-29 11:37:30,505] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +16: [2023-04-29 11:37:30,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +29: [2023-04-29 11:37:30,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +39: [2023-04-29 11:37:30,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +30: [2023-04-29 11:37:30,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +30: [2023-04-29 11:37:30,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +29: [2023-04-29 11:37:30,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +15: [2023-04-29 11:37:30,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +15: [2023-04-29 11:37:30,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 5: [2023-04-29 11:37:30,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... + 5: [2023-04-29 11:37:30,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +24: [2023-04-29 11:37:30,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +19: [2023-04-29 11:37:30,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +15: [2023-04-29 11:37:30,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +15: [2023-04-29 11:37:30,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... + 9: [2023-04-29 11:37:30,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 9: [2023-04-29 11:37:30,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +39: [2023-04-29 11:37:30,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +51: [2023-04-29 11:37:30,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +16: [2023-04-29 11:37:30,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... + 7: [2023-04-29 11:37:30,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 5: [2023-04-29 11:37:30,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... + 5: [2023-04-29 11:37:30,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +34: [2023-04-29 11:37:30,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +26: [2023-04-29 11:37:30,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +26: [2023-04-29 11:37:30,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +15: [2023-04-29 11:37:30,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +15: [2023-04-29 11:37:30,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +19: [2023-04-29 11:37:30,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +26: [2023-04-29 11:37:30,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +58: [2023-04-29 11:37:30,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +16: [2023-04-29 11:37:30,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +51: [2023-04-29 11:37:30,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 9: [2023-04-29 11:37:30,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 9: [2023-04-29 11:37:30,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +60: [2023-04-29 11:37:30,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +60: [2023-04-29 11:37:30,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +39: [2023-04-29 11:37:30,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +34: [2023-04-29 11:37:30,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +34: [2023-04-29 11:37:30,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +34: [2023-04-29 11:37:30,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +23: [2023-04-29 11:37:30,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +37: [2023-04-29 11:37:30,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +34: [2023-04-29 11:37:30,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +58: [2023-04-29 11:37:30,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +34: [2023-04-29 11:37:30,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +26: [2023-04-29 11:37:30,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +60: [2023-04-29 11:37:30,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +60: [2023-04-29 11:37:30,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 9: [2023-04-29 11:37:30,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +51: [2023-04-29 11:37:30,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +26: [2023-04-29 11:37:30,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +37: [2023-04-29 11:37:30,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +60: [2023-04-29 11:37:30,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +60: [2023-04-29 11:37:30,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +23: [2023-04-29 11:37:30,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +34: [2023-04-29 11:37:30,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +24: [2023-04-29 11:37:30,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +24: [2023-04-29 11:37:30,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 7: [2023-04-29 11:37:30,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +34: [2023-04-29 11:37:30,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +24: [2023-04-29 11:37:30,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +50: [2023-04-29 11:37:30,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +50: [2023-04-29 11:37:30,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 1: [2023-04-29 11:37:30,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +60: [2023-04-29 11:37:30,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +39: [2023-04-29 11:37:30,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +60: [2023-04-29 11:37:30,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +26: [2023-04-29 11:37:30,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +19: [2023-04-29 11:37:30,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 7: [2023-04-29 11:37:30,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +19: [2023-04-29 11:37:30,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +45: [2023-04-29 11:37:30,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +58: [2023-04-29 11:37:30,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +58: [2023-04-29 11:37:30,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +39: [2023-04-29 11:37:30,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +51: [2023-04-29 11:37:30,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 1: [2023-04-29 11:37:30,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +20: [2023-04-29 11:37:30,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +50: [2023-04-29 11:37:30,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +50: [2023-04-29 11:37:30,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +37: [2023-04-29 11:37:30,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 7: [2023-04-29 11:37:30,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 1: [2023-04-29 11:37:30,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +24: [2023-04-29 11:37:30,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +23: [2023-04-29 11:37:30,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +23: [2023-04-29 11:37:30,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 1: [2023-04-29 11:37:30,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +58: [2023-04-29 11:37:30,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +45: [2023-04-29 11:37:30,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +58: [2023-04-29 11:37:30,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +58: [2023-04-29 11:37:30,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +19: [2023-04-29 11:37:30,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +37: [2023-04-29 11:37:30,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +39: [2023-04-29 11:37:30,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +56: [2023-04-29 11:37:30,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +20: [2023-04-29 11:37:30,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 7: [2023-04-29 11:37:30,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +62: [2023-04-29 11:37:30,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +37: [2023-04-29 11:37:30,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +37: [2023-04-29 11:37:30,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +56: [2023-04-29 11:37:30,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +56: [2023-04-29 11:37:30,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +45: [2023-04-29 11:37:30,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +45: [2023-04-29 11:37:30,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +62: [2023-04-29 11:37:30,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +34: [2023-04-29 11:37:30,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 7: [2023-04-29 11:37:30,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +20: [2023-04-29 11:37:30,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +50: [2023-04-29 11:37:30,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 7: [2023-04-29 11:37:30,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 2: [2023-04-29 11:37:30,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 2: [2023-04-29 11:37:30,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +58: [2023-04-29 11:37:30,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +34: [2023-04-29 11:37:30,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +34: [2023-04-29 11:37:30,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +62: [2023-04-29 11:37:30,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +62: [2023-04-29 11:37:30,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +63: [2023-04-29 11:37:30,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +63: [2023-04-29 11:37:30,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +50: [2023-04-29 11:37:30,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +63: [2023-04-29 11:37:30,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +63: [2023-04-29 11:37:30,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 7: [2023-04-29 11:37:30,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +37: [2023-04-29 11:37:30,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +37: [2023-04-29 11:37:30,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +39: [2023-04-29 11:37:30,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +51: [2023-04-29 11:37:30,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +50: [2023-04-29 11:37:30,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... + 2: [2023-04-29 11:37:30,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... + 2: [2023-04-29 11:37:30,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +34: [2023-04-29 11:37:30,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +34: [2023-04-29 11:37:30,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +34: [2023-04-29 11:37:30,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +56: [2023-04-29 11:37:30,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +63: [2023-04-29 11:37:30,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 7: [2023-04-29 11:37:30,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... + 2: [2023-04-29 11:37:30,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 2: [2023-04-29 11:37:30,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +42: [2023-04-29 11:37:30,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +50: [2023-04-29 11:37:30,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +63: [2023-04-29 11:37:30,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 9: [2023-04-29 11:37:30,551] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. + 7: [2023-04-29 11:37:30,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +63: [2023-04-29 11:37:30,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 7: [2023-04-29 11:37:30,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +63: [2023-04-29 11:37:30,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +20: [2023-04-29 11:37:30,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +16: [2023-04-29 11:37:30,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +16: [2023-04-29 11:37:30,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +16: [2023-04-29 11:37:30,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +51: [2023-04-29 11:37:30,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +61: [2023-04-29 11:37:30,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 2: [2023-04-29 11:37:30,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... + 2: [2023-04-29 11:37:30,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... + 7: [2023-04-29 11:37:30,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +42: [2023-04-29 11:37:30,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +42: [2023-04-29 11:37:30,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +42: [2023-04-29 11:37:30,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +45: [2023-04-29 11:37:30,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 7: [2023-04-29 11:37:30,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 9: [2023-04-29 11:37:30,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +49: [2023-04-29 11:37:30,558] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +49: [2023-04-29 11:37:30,558] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. + 9: [2023-04-29 11:37:30,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +49: [2023-04-29 11:37:30,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +49: [2023-04-29 11:37:30,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +20: [2023-04-29 11:37:30,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +16: [2023-04-29 11:37:30,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +61: [2023-04-29 11:37:30,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +51: [2023-04-29 11:37:30,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 9: [2023-04-29 11:37:30,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +20: [2023-04-29 11:37:30,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +61: [2023-04-29 11:37:30,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +45: [2023-04-29 11:37:30,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +20: [2023-04-29 11:37:30,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 7: [2023-04-29 11:37:30,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +47: [2023-04-29 11:37:30,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +47: [2023-04-29 11:37:30,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 7: [2023-04-29 11:37:30,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_00-model_states.pt. +56: [2023-04-29 11:37:30,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +47: [2023-04-29 11:37:30,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +47: [2023-04-29 11:37:30,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +45: [2023-04-29 11:37:30,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +56: [2023-04-29 11:37:30,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +56: [2023-04-29 11:37:30,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +45: [2023-04-29 11:37:30,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +56: [2023-04-29 11:37:30,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +56: [2023-04-29 11:37:30,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +33: [2023-04-29 11:37:30,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +33: [2023-04-29 11:37:30,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +32: [2023-04-29 11:37:30,574] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +32: [2023-04-29 11:37:30,574] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +32: [2023-04-29 11:37:30,574] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +32: [2023-04-29 11:37:30,574] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +33: [2023-04-29 11:37:30,574] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +47: [2023-04-29 11:37:30,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +47: [2023-04-29 11:37:30,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +47: [2023-04-29 11:37:30,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +27: [2023-04-29 11:37:30,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +27: [2023-04-29 11:37:30,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +33: [2023-04-29 11:37:30,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +61: [2023-04-29 11:37:30,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 7: [2023-04-29 11:37:30,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt... +27: [2023-04-29 11:37:30,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +27: [2023-04-29 11:37:30,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +47: [2023-04-29 11:37:30,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +56: [2023-04-29 11:37:30,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +56: [2023-04-29 11:37:30,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +56: [2023-04-29 11:37:30,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +56: [2023-04-29 11:37:30,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +56: [2023-04-29 11:37:30,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +33: [2023-04-29 11:37:30,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +27: [2023-04-29 11:37:30,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +34: [2023-04-29 11:37:30,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +33: [2023-04-29 11:37:30,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +20: [2023-04-29 11:37:30,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +33: [2023-04-29 11:37:30,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +27: [2023-04-29 11:37:30,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +27: [2023-04-29 11:37:30,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +27: [2023-04-29 11:37:30,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 9: [2023-04-29 11:37:30,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +33: [2023-04-29 11:37:30,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +42: [2023-04-29 11:37:30,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +49: [2023-04-29 11:37:30,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +61: [2023-04-29 11:37:30,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +60: [2023-04-29 11:37:30,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +35: [2023-04-29 11:37:30,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +35: [2023-04-29 11:37:30,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +34: [2023-04-29 11:37:30,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +35: [2023-04-29 11:37:30,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +42: [2023-04-29 11:37:30,584] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +35: [2023-04-29 11:37:30,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +16: [2023-04-29 11:37:30,584] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +16: [2023-04-29 11:37:30,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +56: [2023-04-29 11:37:30,584] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +56: [2023-04-29 11:37:30,584] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +16: [2023-04-29 11:37:30,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +61: [2023-04-29 11:37:30,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +49: [2023-04-29 11:37:30,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +38: [2023-04-29 11:37:30,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +38: [2023-04-29 11:37:30,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +42: [2023-04-29 11:37:30,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +42: [2023-04-29 11:37:30,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +60: [2023-04-29 11:37:30,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +49: [2023-04-29 11:37:30,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +35: [2023-04-29 11:37:30,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +35: [2023-04-29 11:37:30,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +49: [2023-04-29 11:37:30,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 9: [2023-04-29 11:37:30,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +61: [2023-04-29 11:37:30,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +35: [2023-04-29 11:37:30,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +46: [2023-04-29 11:37:30,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +46: [2023-04-29 11:37:30,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +46: [2023-04-29 11:37:30,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +46: [2023-04-29 11:37:30,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +35: [2023-04-29 11:37:30,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 9: [2023-04-29 11:37:30,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +38: [2023-04-29 11:37:30,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +38: [2023-04-29 11:37:30,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 9: [2023-04-29 11:37:30,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +38: [2023-04-29 11:37:30,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +38: [2023-04-29 11:37:30,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +16: [2023-04-29 11:37:30,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +38: [2023-04-29 11:37:30,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +46: [2023-04-29 11:37:30,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +46: [2023-04-29 11:37:30,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +49: [2023-04-29 11:37:30,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +49: [2023-04-29 11:37:30,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +49: [2023-04-29 11:37:30,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +38: [2023-04-29 11:37:30,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +46: [2023-04-29 11:37:30,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +49: [2023-04-29 11:37:30,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +46: [2023-04-29 11:37:30,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 0: [2023-04-29 11:37:30,600] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 0: [2023-04-29 11:37:30,600] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 0: [2023-04-29 11:37:30,600] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 0: [2023-04-29 11:37:30,600] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +60: [2023-04-29 11:37:30,601] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +60: [2023-04-29 11:37:30,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +50: [2023-04-29 11:37:30,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +50: [2023-04-29 11:37:30,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +32: [2023-04-29 11:37:30,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +32: [2023-04-29 11:37:30,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +49: [2023-04-29 11:37:30,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +50: [2023-04-29 11:37:30,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +50: [2023-04-29 11:37:30,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 0: [2023-04-29 11:37:30,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +61: [2023-04-29 11:37:30,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +32: [2023-04-29 11:37:30,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +63: [2023-04-29 11:37:30,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +32: [2023-04-29 11:37:30,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 0: [2023-04-29 11:37:30,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +49: [2023-04-29 11:37:30,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 0: [2023-04-29 11:37:30,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +49: [2023-04-29 11:37:30,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 0: [2023-04-29 11:37:30,607] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +49: [2023-04-29 11:37:30,607] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 8: [2023-04-29 11:37:30,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +50: [2023-04-29 11:37:30,608] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +60: [2023-04-29 11:37:30,609] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 8: [2023-04-29 11:37:30,610] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +51: [2023-04-29 11:37:30,611] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +51: [2023-04-29 11:37:30,611] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +51: [2023-04-29 11:37:30,611] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +51: [2023-04-29 11:37:30,611] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +50: [2023-04-29 11:37:30,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +50: [2023-04-29 11:37:30,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +50: [2023-04-29 11:37:30,614] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,614] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,614] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +62: [2023-04-29 11:37:30,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +63: [2023-04-29 11:37:30,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +60: [2023-04-29 11:37:30,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +36: [2023-04-29 11:37:30,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +36: [2023-04-29 11:37:30,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +62: [2023-04-29 11:37:30,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +62: [2023-04-29 11:37:30,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +36: [2023-04-29 11:37:30,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +63: [2023-04-29 11:37:30,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +63: [2023-04-29 11:37:30,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +36: [2023-04-29 11:37:30,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +62: [2023-04-29 11:37:30,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +36: [2023-04-29 11:37:30,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +36: [2023-04-29 11:37:30,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +36: [2023-04-29 11:37:30,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +21: [2023-04-29 11:37:30,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +21: [2023-04-29 11:37:30,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +21: [2023-04-29 11:37:30,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +21: [2023-04-29 11:37:30,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +62: [2023-04-29 11:37:30,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +62: [2023-04-29 11:37:30,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +62: [2023-04-29 11:37:30,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +63: [2023-04-29 11:37:30,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +36: [2023-04-29 11:37:30,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +60: [2023-04-29 11:37:30,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +21: [2023-04-29 11:37:30,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +21: [2023-04-29 11:37:30,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +21: [2023-04-29 11:37:30,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +60: [2023-04-29 11:37:30,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +21: [2023-04-29 11:37:30,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +62: [2023-04-29 11:37:30,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +49: [2023-04-29 11:37:30,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +35: [2023-04-29 11:37:30,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +35: [2023-04-29 11:37:30,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +35: [2023-04-29 11:37:30,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +35: [2023-04-29 11:37:30,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +51: [2023-04-29 11:37:30,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +49: [2023-04-29 11:37:30,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +51: [2023-04-29 11:37:30,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +27: [2023-04-29 11:37:30,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +61: [2023-04-29 11:37:30,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +61: [2023-04-29 11:37:30,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +47: [2023-04-29 11:37:30,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +61: [2023-04-29 11:37:30,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +61: [2023-04-29 11:37:30,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +63: [2023-04-29 11:37:30,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +51: [2023-04-29 11:37:30,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +51: [2023-04-29 11:37:30,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +27: [2023-04-29 11:37:30,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +47: [2023-04-29 11:37:30,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +27: [2023-04-29 11:37:30,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +27: [2023-04-29 11:37:30,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +37: [2023-04-29 11:37:30,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +37: [2023-04-29 11:37:30,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +37: [2023-04-29 11:37:30,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +37: [2023-04-29 11:37:30,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +38: [2023-04-29 11:37:30,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +33: [2023-04-29 11:37:30,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +47: [2023-04-29 11:37:30,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +47: [2023-04-29 11:37:30,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +33: [2023-04-29 11:37:30,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +33: [2023-04-29 11:37:30,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +33: [2023-04-29 11:37:30,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +63: [2023-04-29 11:37:30,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +63: [2023-04-29 11:37:30,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +37: [2023-04-29 11:37:30,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +29: [2023-04-29 11:37:30,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +29: [2023-04-29 11:37:30,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +29: [2023-04-29 11:37:30,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +29: [2023-04-29 11:37:30,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +32: [2023-04-29 11:37:30,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +37: [2023-04-29 11:37:30,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 0: [2023-04-29 11:37:30,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +37: [2023-04-29 11:37:30,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +49: [2023-04-29 11:37:30,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +37: [2023-04-29 11:37:30,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +33: [2023-04-29 11:37:30,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +33: [2023-04-29 11:37:30,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +29: [2023-04-29 11:37:30,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +29: [2023-04-29 11:37:30,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +33: [2023-04-29 11:37:30,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +32: [2023-04-29 11:37:30,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +33: [2023-04-29 11:37:30,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +49: [2023-04-29 11:37:30,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +29: [2023-04-29 11:37:30,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +46: [2023-04-29 11:37:30,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +29: [2023-04-29 11:37:30,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +49: [2023-04-29 11:37:30,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +27: [2023-04-29 11:37:30,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +35: [2023-04-29 11:37:30,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +32: [2023-04-29 11:37:30,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +55: [2023-04-29 11:37:30,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +55: [2023-04-29 11:37:30,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +55: [2023-04-29 11:37:30,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +55: [2023-04-29 11:37:30,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +35: [2023-04-29 11:37:30,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +35: [2023-04-29 11:37:30,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +43: [2023-04-29 11:37:30,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +43: [2023-04-29 11:37:30,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +35: [2023-04-29 11:37:30,667] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +43: [2023-04-29 11:37:30,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +43: [2023-04-29 11:37:30,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +61: [2023-04-29 11:37:30,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +38: [2023-04-29 11:37:30,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +38: [2023-04-29 11:37:30,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +32: [2023-04-29 11:37:30,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +46: [2023-04-29 11:37:30,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +46: [2023-04-29 11:37:30,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +46: [2023-04-29 11:37:30,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +35: [2023-04-29 11:37:30,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +50: [2023-04-29 11:37:30,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +43: [2023-04-29 11:37:30,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +35: [2023-04-29 11:37:30,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +43: [2023-04-29 11:37:30,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +61: [2023-04-29 11:37:30,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +61: [2023-04-29 11:37:30,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +42: [2023-04-29 11:37:30,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +42: [2023-04-29 11:37:30,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +42: [2023-04-29 11:37:30,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +32: [2023-04-29 11:37:30,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +61: [2023-04-29 11:37:30,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +42: [2023-04-29 11:37:30,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +43: [2023-04-29 11:37:30,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +38: [2023-04-29 11:37:30,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +43: [2023-04-29 11:37:30,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +47: [2023-04-29 11:37:30,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +27: [2023-04-29 11:37:30,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +32: [2023-04-29 11:37:30,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 0: [2023-04-29 11:37:30,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 0: [2023-04-29 11:37:30,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 0: [2023-04-29 11:37:30,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +35: [2023-04-29 11:37:30,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +38: [2023-04-29 11:37:30,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 8: [2023-04-29 11:37:30,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +27: [2023-04-29 11:37:30,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +27: [2023-04-29 11:37:30,677] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +49: [2023-04-29 11:37:30,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +49: [2023-04-29 11:37:30,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +47: [2023-04-29 11:37:30,677] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +36: [2023-04-29 11:37:30,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 8: [2023-04-29 11:37:30,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +32: [2023-04-29 11:37:30,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +47: [2023-04-29 11:37:30,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +32: [2023-04-29 11:37:30,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... + 0: [2023-04-29 11:37:30,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +57: [2023-04-29 11:37:30,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 8: [2023-04-29 11:37:30,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 8: [2023-04-29 11:37:30,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +57: [2023-04-29 11:37:30,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +57: [2023-04-29 11:37:30,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +57: [2023-04-29 11:37:30,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +50: [2023-04-29 11:37:30,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +33: [2023-04-29 11:37:30,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +47: [2023-04-29 11:37:30,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +50: [2023-04-29 11:37:30,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +33: [2023-04-29 11:37:30,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +49: [2023-04-29 11:37:30,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +33: [2023-04-29 11:37:30,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +49: [2023-04-29 11:37:30,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +33: [2023-04-29 11:37:30,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +49: [2023-04-29 11:37:30,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +55: [2023-04-29 11:37:30,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +55: [2023-04-29 11:37:30,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +57: [2023-04-29 11:37:30,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +57: [2023-04-29 11:37:30,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +57: [2023-04-29 11:37:30,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +57: [2023-04-29 11:37:30,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +55: [2023-04-29 11:37:30,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +50: [2023-04-29 11:37:30,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +46: [2023-04-29 11:37:30,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +55: [2023-04-29 11:37:30,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +33: [2023-04-29 11:37:30,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +35: [2023-04-29 11:37:30,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +36: [2023-04-29 11:37:30,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +36: [2023-04-29 11:37:30,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +55: [2023-04-29 11:37:30,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +49: [2023-04-29 11:37:30,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +49: [2023-04-29 11:37:30,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +49: [2023-04-29 11:37:30,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +21: [2023-04-29 11:37:30,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +21: [2023-04-29 11:37:30,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +55: [2023-04-29 11:37:30,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +33: [2023-04-29 11:37:30,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +55: [2023-04-29 11:37:30,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +33: [2023-04-29 11:37:30,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +55: [2023-04-29 11:37:30,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +55: [2023-04-29 11:37:30,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +55: [2023-04-29 11:37:30,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +42: [2023-04-29 11:37:30,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +35: [2023-04-29 11:37:30,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +50: [2023-04-29 11:37:30,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +33: [2023-04-29 11:37:30,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +55: [2023-04-29 11:37:30,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +55: [2023-04-29 11:37:30,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +38: [2023-04-29 11:37:30,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +38: [2023-04-29 11:37:30,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +40: [2023-04-29 11:37:30,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +40: [2023-04-29 11:37:30,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +40: [2023-04-29 11:37:30,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +40: [2023-04-29 11:37:30,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +46: [2023-04-29 11:37:30,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +46: [2023-04-29 11:37:30,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +21: [2023-04-29 11:37:30,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +21: [2023-04-29 11:37:30,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +36: [2023-04-29 11:37:30,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +42: [2023-04-29 11:37:30,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +35: [2023-04-29 11:37:30,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +46: [2023-04-29 11:37:30,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +35: [2023-04-29 11:37:30,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +38: [2023-04-29 11:37:30,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 0: [2023-04-29 11:37:30,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 0: [2023-04-29 11:37:30,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +51: [2023-04-29 11:37:30,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +42: [2023-04-29 11:37:30,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +42: [2023-04-29 11:37:30,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 0: [2023-04-29 11:37:30,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +36: [2023-04-29 11:37:30,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +48: [2023-04-29 11:37:30,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +48: [2023-04-29 11:37:30,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +48: [2023-04-29 11:37:30,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +51: [2023-04-29 11:37:30,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +48: [2023-04-29 11:37:30,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +51: [2023-04-29 11:37:30,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +50: [2023-04-29 11:37:30,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +51: [2023-04-29 11:37:30,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +36: [2023-04-29 11:37:30,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +36: [2023-04-29 11:37:30,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +29: [2023-04-29 11:37:30,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +53: [2023-04-29 11:37:30,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +53: [2023-04-29 11:37:30,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +53: [2023-04-29 11:37:30,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +53: [2023-04-29 11:37:30,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +21: [2023-04-29 11:37:30,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +37: [2023-04-29 11:37:30,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +21: [2023-04-29 11:37:30,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +44: [2023-04-29 11:37:30,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +44: [2023-04-29 11:37:30,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +43: [2023-04-29 11:37:30,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +29: [2023-04-29 11:37:30,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +51: [2023-04-29 11:37:30,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +50: [2023-04-29 11:37:30,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +44: [2023-04-29 11:37:30,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +44: [2023-04-29 11:37:30,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +29: [2023-04-29 11:37:30,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +37: [2023-04-29 11:37:30,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +51: [2023-04-29 11:37:30,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +43: [2023-04-29 11:37:30,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +49: [2023-04-29 11:37:30,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +50: [2023-04-29 11:37:30,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +49: [2023-04-29 11:37:30,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +49: [2023-04-29 11:37:30,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +40: [2023-04-29 11:37:30,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +44: [2023-04-29 11:37:30,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +40: [2023-04-29 11:37:30,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +44: [2023-04-29 11:37:30,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +40: [2023-04-29 11:37:30,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +40: [2023-04-29 11:37:30,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +44: [2023-04-29 11:37:30,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +44: [2023-04-29 11:37:30,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +44: [2023-04-29 11:37:30,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +44: [2023-04-29 11:37:30,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +35: [2023-04-29 11:37:30,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +11: [2023-04-29 11:37:30,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +11: [2023-04-29 11:37:30,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +11: [2023-04-29 11:37:30,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +51: [2023-04-29 11:37:30,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +11: [2023-04-29 11:37:30,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +51: [2023-04-29 11:37:30,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +21: [2023-04-29 11:37:30,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +21: [2023-04-29 11:37:30,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +36: [2023-04-29 11:37:30,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +11: [2023-04-29 11:37:30,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +11: [2023-04-29 11:37:30,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +44: [2023-04-29 11:37:30,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +61: [2023-04-29 11:37:30,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +11: [2023-04-29 11:37:30,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +11: [2023-04-29 11:37:30,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +61: [2023-04-29 11:37:30,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +54: [2023-04-29 11:37:30,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +54: [2023-04-29 11:37:30,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +44: [2023-04-29 11:37:30,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +29: [2023-04-29 11:37:30,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +37: [2023-04-29 11:37:30,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +37: [2023-04-29 11:37:30,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +43: [2023-04-29 11:37:30,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +43: [2023-04-29 11:37:30,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +61: [2023-04-29 11:37:30,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +61: [2023-04-29 11:37:30,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +54: [2023-04-29 11:37:30,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +54: [2023-04-29 11:37:30,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +35: [2023-04-29 11:37:30,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +43: [2023-04-29 11:37:30,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +61: [2023-04-29 11:37:30,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +29: [2023-04-29 11:37:30,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +29: [2023-04-29 11:37:30,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +37: [2023-04-29 11:37:30,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +57: [2023-04-29 11:37:30,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +28: [2023-04-29 11:37:30,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +28: [2023-04-29 11:37:30,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +61: [2023-04-29 11:37:30,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +53: [2023-04-29 11:37:30,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +28: [2023-04-29 11:37:30,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +28: [2023-04-29 11:37:30,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +57: [2023-04-29 11:37:30,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +61: [2023-04-29 11:37:30,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +53: [2023-04-29 11:37:30,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +44: [2023-04-29 11:37:30,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +53: [2023-04-29 11:37:30,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +44: [2023-04-29 11:37:30,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +48: [2023-04-29 11:37:30,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +53: [2023-04-29 11:37:30,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +48: [2023-04-29 11:37:30,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +48: [2023-04-29 11:37:30,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +48: [2023-04-29 11:37:30,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +35: [2023-04-29 11:37:30,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +43: [2023-04-29 11:37:30,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +54: [2023-04-29 11:37:30,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +33: [2023-04-29 11:37:30,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +35: [2023-04-29 11:37:30,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +57: [2023-04-29 11:37:30,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +57: [2023-04-29 11:37:30,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +54: [2023-04-29 11:37:30,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +28: [2023-04-29 11:37:30,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 6: [2023-04-29 11:37:30,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 6: [2023-04-29 11:37:30,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 6: [2023-04-29 11:37:30,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 6: [2023-04-29 11:37:30,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +28: [2023-04-29 11:37:30,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 3: [2023-04-29 11:37:30,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 3: [2023-04-29 11:37:30,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 3: [2023-04-29 11:37:30,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +40: [2023-04-29 11:37:30,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +55: [2023-04-29 11:37:30,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 3: [2023-04-29 11:37:30,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +54: [2023-04-29 11:37:30,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +61: [2023-04-29 11:37:30,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +44: [2023-04-29 11:37:30,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +54: [2023-04-29 11:37:30,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +29: [2023-04-29 11:37:30,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +28: [2023-04-29 11:37:30,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +54: [2023-04-29 11:37:30,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +40: [2023-04-29 11:37:30,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +40: [2023-04-29 11:37:30,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +40: [2023-04-29 11:37:30,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +33: [2023-04-29 11:37:30,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +28: [2023-04-29 11:37:30,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +37: [2023-04-29 11:37:30,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +35: [2023-04-29 11:37:30,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +45: [2023-04-29 11:37:30,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +45: [2023-04-29 11:37:30,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +45: [2023-04-29 11:37:30,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +44: [2023-04-29 11:37:30,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +45: [2023-04-29 11:37:30,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +42: [2023-04-29 11:37:30,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 6: [2023-04-29 11:37:30,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 6: [2023-04-29 11:37:30,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 6: [2023-04-29 11:37:30,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 6: [2023-04-29 11:37:30,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +40: [2023-04-29 11:37:30,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 3: [2023-04-29 11:37:30,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 3: [2023-04-29 11:37:30,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +35: [2023-04-29 11:37:30,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +54: [2023-04-29 11:37:30,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 3: [2023-04-29 11:37:30,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +46: [2023-04-29 11:37:30,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +46: [2023-04-29 11:37:30,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +46: [2023-04-29 11:37:30,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +54: [2023-04-29 11:37:30,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +46: [2023-04-29 11:37:30,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. + 3: [2023-04-29 11:37:30,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +54: [2023-04-29 11:37:30,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +55: [2023-04-29 11:37:30,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +33: [2023-04-29 11:37:30,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +33: [2023-04-29 11:37:30,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +33: [2023-04-29 11:37:30,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +52: [2023-04-29 11:37:30,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +52: [2023-04-29 11:37:30,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +52: [2023-04-29 11:37:30,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +52: [2023-04-29 11:37:30,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +35: [2023-04-29 11:37:30,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +55: [2023-04-29 11:37:30,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +40: [2023-04-29 11:37:30,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +40: [2023-04-29 11:37:30,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +40: [2023-04-29 11:37:30,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +56: [2023-04-29 11:37:30,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +56: [2023-04-29 11:37:30,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +56: [2023-04-29 11:37:30,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +52: [2023-04-29 11:37:30,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +56: [2023-04-29 11:37:30,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +55: [2023-04-29 11:37:30,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +42: [2023-04-29 11:37:30,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +29: [2023-04-29 11:37:30,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +52: [2023-04-29 11:37:30,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +52: [2023-04-29 11:37:30,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +52: [2023-04-29 11:37:30,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +33: [2023-04-29 11:37:30,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +33: [2023-04-29 11:37:30,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +33: [2023-04-29 11:37:30,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +18: [2023-04-29 11:37:30,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +18: [2023-04-29 11:37:30,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +37: [2023-04-29 11:37:30,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +18: [2023-04-29 11:37:30,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +55: [2023-04-29 11:37:30,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +55: [2023-04-29 11:37:30,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +12: [2023-04-29 11:37:30,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +12: [2023-04-29 11:37:30,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +54: [2023-04-29 11:37:30,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +57: [2023-04-29 11:37:30,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +18: [2023-04-29 11:37:30,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +54: [2023-04-29 11:37:30,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +54: [2023-04-29 11:37:30,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +56: [2023-04-29 11:37:30,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +43: [2023-04-29 11:37:30,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +43: [2023-04-29 11:37:30,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +56: [2023-04-29 11:37:30,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +56: [2023-04-29 11:37:30,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +56: [2023-04-29 11:37:30,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +35: [2023-04-29 11:37:30,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +37: [2023-04-29 11:37:30,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +55: [2023-04-29 11:37:30,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +22: [2023-04-29 11:37:30,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +22: [2023-04-29 11:37:30,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +22: [2023-04-29 11:37:30,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +54: [2023-04-29 11:37:30,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +22: [2023-04-29 11:37:30,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +12: [2023-04-29 11:37:30,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +57: [2023-04-29 11:37:30,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +12: [2023-04-29 11:37:30,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +18: [2023-04-29 11:37:30,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +55: [2023-04-29 11:37:30,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +12: [2023-04-29 11:37:30,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +34: [2023-04-29 11:37:30,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +34: [2023-04-29 11:37:30,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +12: [2023-04-29 11:37:30,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +34: [2023-04-29 11:37:30,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +34: [2023-04-29 11:37:30,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +55: [2023-04-29 11:37:30,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +17: [2023-04-29 11:37:30,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +17: [2023-04-29 11:37:30,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +17: [2023-04-29 11:37:30,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +18: [2023-04-29 11:37:30,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +57: [2023-04-29 11:37:30,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +18: [2023-04-29 11:37:30,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +57: [2023-04-29 11:37:30,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +42: [2023-04-29 11:37:30,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +42: [2023-04-29 11:37:30,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +17: [2023-04-29 11:37:30,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +14: [2023-04-29 11:37:30,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +14: [2023-04-29 11:37:30,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +18: [2023-04-29 11:37:30,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +22: [2023-04-29 11:37:30,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +35: [2023-04-29 11:37:30,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +60: [2023-04-29 11:37:30,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +60: [2023-04-29 11:37:30,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +60: [2023-04-29 11:37:30,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +60: [2023-04-29 11:37:30,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +22: [2023-04-29 11:37:30,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +22: [2023-04-29 11:37:30,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +55: [2023-04-29 11:37:30,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +55: [2023-04-29 11:37:30,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +22: [2023-04-29 11:37:30,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +12: [2023-04-29 11:37:30,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +14: [2023-04-29 11:37:30,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +14: [2023-04-29 11:37:30,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +34: [2023-04-29 11:37:30,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +17: [2023-04-29 11:37:30,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +34: [2023-04-29 11:37:30,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +17: [2023-04-29 11:37:30,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +12: [2023-04-29 11:37:30,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +42: [2023-04-29 11:37:30,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +17: [2023-04-29 11:37:30,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +17: [2023-04-29 11:37:30,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +34: [2023-04-29 11:37:30,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +42: [2023-04-29 11:37:30,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +42: [2023-04-29 11:37:30,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +34: [2023-04-29 11:37:30,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +14: [2023-04-29 11:37:30,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +45: [2023-04-29 11:37:30,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +45: [2023-04-29 11:37:30,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +14: [2023-04-29 11:37:30,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +46: [2023-04-29 11:37:30,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +46: [2023-04-29 11:37:30,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +45: [2023-04-29 11:37:30,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +45: [2023-04-29 11:37:30,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +45: [2023-04-29 11:37:30,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +14: [2023-04-29 11:37:30,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +14: [2023-04-29 11:37:30,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +46: [2023-04-29 11:37:30,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +55: [2023-04-29 11:37:30,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +55: [2023-04-29 11:37:30,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +45: [2023-04-29 11:37:30,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +45: [2023-04-29 11:37:30,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +45: [2023-04-29 11:37:30,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +42: [2023-04-29 11:37:30,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +46: [2023-04-29 11:37:30,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +11: [2023-04-29 11:37:30,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +45: [2023-04-29 11:37:30,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +40: [2023-04-29 11:37:30,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +45: [2023-04-29 11:37:30,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 5: [2023-04-29 11:37:30,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 5: [2023-04-29 11:37:30,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 5: [2023-04-29 11:37:30,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +45: [2023-04-29 11:37:30,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 5: [2023-04-29 11:37:30,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +45: [2023-04-29 11:37:30,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +40: [2023-04-29 11:37:30,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +55: [2023-04-29 11:37:30,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +11: [2023-04-29 11:37:30,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +11: [2023-04-29 11:37:30,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +40: [2023-04-29 11:37:30,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +40: [2023-04-29 11:37:30,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... + 5: [2023-04-29 11:37:30,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 5: [2023-04-29 11:37:30,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 5: [2023-04-29 11:37:30,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 5: [2023-04-29 11:37:30,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +61: [2023-04-29 11:37:30,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +61: [2023-04-29 11:37:30,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +61: [2023-04-29 11:37:30,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +61: [2023-04-29 11:37:30,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +55: [2023-04-29 11:37:30,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +58: [2023-04-29 11:37:30,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +58: [2023-04-29 11:37:30,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +58: [2023-04-29 11:37:30,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +58: [2023-04-29 11:37:30,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +62: [2023-04-29 11:37:30,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +62: [2023-04-29 11:37:30,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +62: [2023-04-29 11:37:30,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +62: [2023-04-29 11:37:30,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +55: [2023-04-29 11:37:30,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +53: [2023-04-29 11:37:30,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +13: [2023-04-29 11:37:30,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +13: [2023-04-29 11:37:30,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +13: [2023-04-29 11:37:30,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +13: [2023-04-29 11:37:30,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 4: [2023-04-29 11:37:30,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 4: [2023-04-29 11:37:30,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 4: [2023-04-29 11:37:30,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +44: [2023-04-29 11:37:30,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 4: [2023-04-29 11:37:30,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +61: [2023-04-29 11:37:30,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +61: [2023-04-29 11:37:30,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +61: [2023-04-29 11:37:30,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +53: [2023-04-29 11:37:30,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +62: [2023-04-29 11:37:30,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +62: [2023-04-29 11:37:30,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +60: [2023-04-29 11:37:30,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +13: [2023-04-29 11:37:30,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +38: [2023-04-29 11:37:30,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +38: [2023-04-29 11:37:30,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +13: [2023-04-29 11:37:30,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +44: [2023-04-29 11:37:30,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +38: [2023-04-29 11:37:30,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +13: [2023-04-29 11:37:30,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +38: [2023-04-29 11:37:30,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +61: [2023-04-29 11:37:30,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +62: [2023-04-29 11:37:30,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 4: [2023-04-29 11:37:30,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +44: [2023-04-29 11:37:30,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +13: [2023-04-29 11:37:30,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +62: [2023-04-29 11:37:30,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 4: [2023-04-29 11:37:30,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 4: [2023-04-29 11:37:30,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 4: [2023-04-29 11:37:30,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +60: [2023-04-29 11:37:30,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +60: [2023-04-29 11:37:30,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +40: [2023-04-29 11:37:30,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +11: [2023-04-29 11:37:30,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +60: [2023-04-29 11:37:30,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +44: [2023-04-29 11:37:30,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +53: [2023-04-29 11:37:30,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +53: [2023-04-29 11:37:30,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +53: [2023-04-29 11:37:30,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +36: [2023-04-29 11:37:30,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +36: [2023-04-29 11:37:30,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +36: [2023-04-29 11:37:30,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +36: [2023-04-29 11:37:30,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +54: [2023-04-29 11:37:30,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +37: [2023-04-29 11:37:30,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +40: [2023-04-29 11:37:30,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +40: [2023-04-29 11:37:30,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +11: [2023-04-29 11:37:30,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +28: [2023-04-29 11:37:30,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +28: [2023-04-29 11:37:30,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +37: [2023-04-29 11:37:30,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +37: [2023-04-29 11:37:30,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +37: [2023-04-29 11:37:30,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +11: [2023-04-29 11:37:30,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +47: [2023-04-29 11:37:30,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +47: [2023-04-29 11:37:30,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. + 3: [2023-04-29 11:37:30,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 6: [2023-04-29 11:37:30,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +47: [2023-04-29 11:37:30,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +47: [2023-04-29 11:37:30,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +40: [2023-04-29 11:37:30,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +11: [2023-04-29 11:37:30,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 3: [2023-04-29 11:37:30,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +53: [2023-04-29 11:37:30,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +41: [2023-04-29 11:37:30,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +41: [2023-04-29 11:37:30,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +53: [2023-04-29 11:37:30,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +41: [2023-04-29 11:37:30,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +53: [2023-04-29 11:37:30,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +41: [2023-04-29 11:37:30,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +44: [2023-04-29 11:37:30,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 3: [2023-04-29 11:37:30,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 6: [2023-04-29 11:37:30,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 6: [2023-04-29 11:37:30,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 6: [2023-04-29 11:37:30,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +40: [2023-04-29 11:37:30,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +28: [2023-04-29 11:37:30,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +28: [2023-04-29 11:37:30,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 3: [2023-04-29 11:37:30,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +52: [2023-04-29 11:37:30,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +58: [2023-04-29 11:37:30,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +58: [2023-04-29 11:37:30,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +44: [2023-04-29 11:37:30,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +58: [2023-04-29 11:37:30,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +58: [2023-04-29 11:37:30,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +44: [2023-04-29 11:37:30,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +54: [2023-04-29 11:37:30,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +26: [2023-04-29 11:37:30,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +26: [2023-04-29 11:37:30,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +44: [2023-04-29 11:37:30,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +18: [2023-04-29 11:37:30,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +18: [2023-04-29 11:37:30,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +18: [2023-04-29 11:37:30,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +18: [2023-04-29 11:37:30,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +44: [2023-04-29 11:37:30,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +15: [2023-04-29 11:37:30,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +15: [2023-04-29 11:37:30,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +15: [2023-04-29 11:37:30,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +15: [2023-04-29 11:37:30,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +44: [2023-04-29 11:37:30,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +44: [2023-04-29 11:37:30,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +52: [2023-04-29 11:37:30,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +52: [2023-04-29 11:37:30,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +26: [2023-04-29 11:37:30,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +26: [2023-04-29 11:37:30,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +52: [2023-04-29 11:37:30,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +18: [2023-04-29 11:37:30,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +22: [2023-04-29 11:37:30,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +46: [2023-04-29 11:37:30,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +26: [2023-04-29 11:37:30,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +26: [2023-04-29 11:37:30,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +56: [2023-04-29 11:37:30,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +56: [2023-04-29 11:37:30,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +56: [2023-04-29 11:37:30,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +38: [2023-04-29 11:37:30,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +38: [2023-04-29 11:37:30,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +40: [2023-04-29 11:37:30,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +15: [2023-04-29 11:37:30,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +15: [2023-04-29 11:37:30,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +15: [2023-04-29 11:37:30,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +15: [2023-04-29 11:37:30,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +38: [2023-04-29 11:37:30,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +26: [2023-04-29 11:37:30,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +26: [2023-04-29 11:37:30,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +44: [2023-04-29 11:37:30,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +44: [2023-04-29 11:37:30,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +38: [2023-04-29 11:37:30,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +46: [2023-04-29 11:37:30,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +54: [2023-04-29 11:37:30,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +17: [2023-04-29 11:37:30,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +11: [2023-04-29 11:37:30,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +54: [2023-04-29 11:37:30,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +28: [2023-04-29 11:37:30,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +12: [2023-04-29 11:37:30,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +12: [2023-04-29 11:37:30,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +44: [2023-04-29 11:37:30,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +14: [2023-04-29 11:37:30,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +37: [2023-04-29 11:37:30,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +54: [2023-04-29 11:37:30,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +44: [2023-04-29 11:37:30,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +40: [2023-04-29 11:37:30,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +40: [2023-04-29 11:37:30,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +40: [2023-04-29 11:37:30,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +63: [2023-04-29 11:37:30,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +63: [2023-04-29 11:37:30,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +63: [2023-04-29 11:37:30,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +28: [2023-04-29 11:37:30,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +63: [2023-04-29 11:37:30,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +36: [2023-04-29 11:37:30,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 3: [2023-04-29 11:37:30,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +34: [2023-04-29 11:37:30,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +34: [2023-04-29 11:37:30,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +45: [2023-04-29 11:37:30,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +56: [2023-04-29 11:37:30,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +47: [2023-04-29 11:37:30,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +47: [2023-04-29 11:37:30,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +22: [2023-04-29 11:37:30,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +22: [2023-04-29 11:37:30,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +22: [2023-04-29 11:37:30,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +17: [2023-04-29 11:37:30,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +47: [2023-04-29 11:37:30,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +36: [2023-04-29 11:37:30,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +54: [2023-04-29 11:37:30,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +44: [2023-04-29 11:37:30,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +12: [2023-04-29 11:37:30,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +12: [2023-04-29 11:37:30,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +17: [2023-04-29 11:37:30,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +54: [2023-04-29 11:37:30,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +46: [2023-04-29 11:37:30,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +52: [2023-04-29 11:37:30,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +54: [2023-04-29 11:37:30,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 3: [2023-04-29 11:37:30,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +47: [2023-04-29 11:37:30,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 3: [2023-04-29 11:37:30,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +14: [2023-04-29 11:37:30,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +41: [2023-04-29 11:37:30,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +36: [2023-04-29 11:37:30,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +37: [2023-04-29 11:37:30,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +45: [2023-04-29 11:37:30,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +36: [2023-04-29 11:37:30,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 6: [2023-04-29 11:37:30,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +46: [2023-04-29 11:37:30,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +46: [2023-04-29 11:37:30,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +54: [2023-04-29 11:37:30,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +28: [2023-04-29 11:37:30,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +41: [2023-04-29 11:37:30,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +54: [2023-04-29 11:37:30,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +34: [2023-04-29 11:37:30,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 3: [2023-04-29 11:37:30,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +34: [2023-04-29 11:37:30,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 6: [2023-04-29 11:37:30,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 6: [2023-04-29 11:37:30,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 6: [2023-04-29 11:37:30,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +45: [2023-04-29 11:37:30,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +37: [2023-04-29 11:37:30,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +37: [2023-04-29 11:37:30,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +45: [2023-04-29 11:37:30,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +28: [2023-04-29 11:37:30,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +14: [2023-04-29 11:37:30,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +54: [2023-04-29 11:37:30,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +18: [2023-04-29 11:37:30,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +18: [2023-04-29 11:37:30,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +10: [2023-04-29 11:37:30,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +10: [2023-04-29 11:37:30,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +54: [2023-04-29 11:37:30,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +10: [2023-04-29 11:37:30,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +41: [2023-04-29 11:37:30,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +46: [2023-04-29 11:37:30,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +10: [2023-04-29 11:37:30,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +18: [2023-04-29 11:37:30,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +41: [2023-04-29 11:37:30,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +46: [2023-04-29 11:37:30,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +45: [2023-04-29 11:37:30,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +17: [2023-04-29 11:37:30,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +18: [2023-04-29 11:37:30,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +18: [2023-04-29 11:37:30,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +54: [2023-04-29 11:37:30,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +18: [2023-04-29 11:37:30,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +18: [2023-04-29 11:37:30,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +45: [2023-04-29 11:37:30,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +52: [2023-04-29 11:37:30,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +52: [2023-04-29 11:37:30,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +22: [2023-04-29 11:37:30,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +10: [2023-04-29 11:37:30,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +13: [2023-04-29 11:37:30,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +10: [2023-04-29 11:37:30,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +17: [2023-04-29 11:37:30,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +17: [2023-04-29 11:37:30,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +10: [2023-04-29 11:37:30,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +52: [2023-04-29 11:37:30,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +45: [2023-04-29 11:37:30,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +10: [2023-04-29 11:37:30,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +57: [2023-04-29 11:37:30,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +14: [2023-04-29 11:37:30,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +57: [2023-04-29 11:37:30,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +57: [2023-04-29 11:37:30,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +57: [2023-04-29 11:37:30,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +30: [2023-04-29 11:37:30,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +30: [2023-04-29 11:37:30,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +52: [2023-04-29 11:37:30,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +52: [2023-04-29 11:37:30,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +52: [2023-04-29 11:37:30,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +52: [2023-04-29 11:37:30,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. + 8: [2023-04-29 11:37:30,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. + 8: [2023-04-29 11:37:30,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. + 8: [2023-04-29 11:37:30,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +46: [2023-04-29 11:37:30,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +17: [2023-04-29 11:37:30,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +30: [2023-04-29 11:37:30,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 8: [2023-04-29 11:37:30,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +54: [2023-04-29 11:37:30,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... + 5: [2023-04-29 11:37:30,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 5: [2023-04-29 11:37:30,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 5: [2023-04-29 11:37:30,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 5: [2023-04-29 11:37:30,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +30: [2023-04-29 11:37:30,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +18: [2023-04-29 11:37:30,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +56: [2023-04-29 11:37:30,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +13: [2023-04-29 11:37:30,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +56: [2023-04-29 11:37:30,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +12: [2023-04-29 11:37:30,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 4: [2023-04-29 11:37:30,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +12: [2023-04-29 11:37:30,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +14: [2023-04-29 11:37:30,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +34: [2023-04-29 11:37:30,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +34: [2023-04-29 11:37:30,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +17: [2023-04-29 11:37:30,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +58: [2023-04-29 11:37:30,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +58: [2023-04-29 11:37:30,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +58: [2023-04-29 11:37:30,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +58: [2023-04-29 11:37:30,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +56: [2023-04-29 11:37:30,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +30: [2023-04-29 11:37:30,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +30: [2023-04-29 11:37:30,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +30: [2023-04-29 11:37:30,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +30: [2023-04-29 11:37:30,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +17: [2023-04-29 11:37:30,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +45: [2023-04-29 11:37:30,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +61: [2023-04-29 11:37:30,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +56: [2023-04-29 11:37:30,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +62: [2023-04-29 11:37:30,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +45: [2023-04-29 11:37:30,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +63: [2023-04-29 11:37:30,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +61: [2023-04-29 11:37:30,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +62: [2023-04-29 11:37:30,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +54: [2023-04-29 11:37:30,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +22: [2023-04-29 11:37:30,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +60: [2023-04-29 11:37:30,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +40: [2023-04-29 11:37:30,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +40: [2023-04-29 11:37:30,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +58: [2023-04-29 11:37:30,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +22: [2023-04-29 11:37:30,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +22: [2023-04-29 11:37:30,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +12: [2023-04-29 11:37:30,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +17: [2023-04-29 11:37:30,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +63: [2023-04-29 11:37:30,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +58: [2023-04-29 11:37:30,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +58: [2023-04-29 11:37:30,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +58: [2023-04-29 11:37:30,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +13: [2023-04-29 11:37:30,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +45: [2023-04-29 11:37:30,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +54: [2023-04-29 11:37:30,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +40: [2023-04-29 11:37:30,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +45: [2023-04-29 11:37:30,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +17: [2023-04-29 11:37:30,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +50: [2023-04-29 11:37:30,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +50: [2023-04-29 11:37:30,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +14: [2023-04-29 11:37:30,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +61: [2023-04-29 11:37:30,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +12: [2023-04-29 11:37:30,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +60: [2023-04-29 11:37:30,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 4: [2023-04-29 11:37:30,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 4: [2023-04-29 11:37:30,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 4: [2023-04-29 11:37:30,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +60: [2023-04-29 11:37:30,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +61: [2023-04-29 11:37:30,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +45: [2023-04-29 11:37:30,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +63: [2023-04-29 11:37:30,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +50: [2023-04-29 11:37:30,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +63: [2023-04-29 11:37:30,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +50: [2023-04-29 11:37:30,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +13: [2023-04-29 11:37:30,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +45: [2023-04-29 11:37:30,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +60: [2023-04-29 11:37:30,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +34: [2023-04-29 11:37:30,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +45: [2023-04-29 11:37:30,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +62: [2023-04-29 11:37:30,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +60: [2023-04-29 11:37:30,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +14: [2023-04-29 11:37:30,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +34: [2023-04-29 11:37:30,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +17: [2023-04-29 11:37:30,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +34: [2023-04-29 11:37:30,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +34: [2023-04-29 11:37:30,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +39: [2023-04-29 11:37:30,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +39: [2023-04-29 11:37:30,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +60: [2023-04-29 11:37:30,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +34: [2023-04-29 11:37:30,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +34: [2023-04-29 11:37:30,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +39: [2023-04-29 11:37:30,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +62: [2023-04-29 11:37:30,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +39: [2023-04-29 11:37:30,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +17: [2023-04-29 11:37:30,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 4: [2023-04-29 11:37:30,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +18: [2023-04-29 11:37:30,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +13: [2023-04-29 11:37:30,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +23: [2023-04-29 11:37:30,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +23: [2023-04-29 11:37:30,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +23: [2023-04-29 11:37:30,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +57: [2023-04-29 11:37:30,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +23: [2023-04-29 11:37:30,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +49: [2023-04-29 11:37:30,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +49: [2023-04-29 11:37:30,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +57: [2023-04-29 11:37:30,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +60: [2023-04-29 11:37:30,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +52: [2023-04-29 11:37:30,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +52: [2023-04-29 11:37:30,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +49: [2023-04-29 11:37:30,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +57: [2023-04-29 11:37:30,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +14: [2023-04-29 11:37:30,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +31: [2023-04-29 11:37:30,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +31: [2023-04-29 11:37:30,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +31: [2023-04-29 11:37:30,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +49: [2023-04-29 11:37:30,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +57: [2023-04-29 11:37:30,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +31: [2023-04-29 11:37:30,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +13: [2023-04-29 11:37:30,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +39: [2023-04-29 11:37:30,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +39: [2023-04-29 11:37:30,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +39: [2023-04-29 11:37:30,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +37: [2023-04-29 11:37:30,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +39: [2023-04-29 11:37:30,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +17: [2023-04-29 11:37:30,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +18: [2023-04-29 11:37:30,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +60: [2023-04-29 11:37:30,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +45: [2023-04-29 11:37:30,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +58: [2023-04-29 11:37:30,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +58: [2023-04-29 11:37:30,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +23: [2023-04-29 11:37:30,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +53: [2023-04-29 11:37:30,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +53: [2023-04-29 11:37:30,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +53: [2023-04-29 11:37:30,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +19: [2023-04-29 11:37:30,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +19: [2023-04-29 11:37:30,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 5: [2023-04-29 11:37:30,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +23: [2023-04-29 11:37:30,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +23: [2023-04-29 11:37:30,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +53: [2023-04-29 11:37:30,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +19: [2023-04-29 11:37:30,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 5: [2023-04-29 11:37:30,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +23: [2023-04-29 11:37:30,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +62: [2023-04-29 11:37:30,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +32: [2023-04-29 11:37:30,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +19: [2023-04-29 11:37:30,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 8: [2023-04-29 11:37:30,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +32: [2023-04-29 11:37:30,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +31: [2023-04-29 11:37:30,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 5: [2023-04-29 11:37:30,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 5: [2023-04-29 11:37:30,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +31: [2023-04-29 11:37:30,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +37: [2023-04-29 11:37:30,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +62: [2023-04-29 11:37:30,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +61: [2023-04-29 11:37:30,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +17: [2023-04-29 11:37:30,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +15: [2023-04-29 11:37:30,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +31: [2023-04-29 11:37:30,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +32: [2023-04-29 11:37:30,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +32: [2023-04-29 11:37:30,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +26: [2023-04-29 11:37:30,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +26: [2023-04-29 11:37:30,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +26: [2023-04-29 11:37:30,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +31: [2023-04-29 11:37:30,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +58: [2023-04-29 11:37:30,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +58: [2023-04-29 11:37:30,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +52: [2023-04-29 11:37:30,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +52: [2023-04-29 11:37:30,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +18: [2023-04-29 11:37:30,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +61: [2023-04-29 11:37:30,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +38: [2023-04-29 11:37:30,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +27: [2023-04-29 11:37:30,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +27: [2023-04-29 11:37:30,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +27: [2023-04-29 11:37:30,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +19: [2023-04-29 11:37:30,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +13: [2023-04-29 11:37:30,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +19: [2023-04-29 11:37:30,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +19: [2023-04-29 11:37:30,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +32: [2023-04-29 11:37:30,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +17: [2023-04-29 11:37:30,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +19: [2023-04-29 11:37:30,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +53: [2023-04-29 11:37:30,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +32: [2023-04-29 11:37:30,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +27: [2023-04-29 11:37:30,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +26: [2023-04-29 11:37:30,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +53: [2023-04-29 11:37:30,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +53: [2023-04-29 11:37:30,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +36: [2023-04-29 11:37:30,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +32: [2023-04-29 11:37:30,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +53: [2023-04-29 11:37:30,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +15: [2023-04-29 11:37:30,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +15: [2023-04-29 11:37:30,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +15: [2023-04-29 11:37:30,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +50: [2023-04-29 11:37:30,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +58: [2023-04-29 11:37:30,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +58: [2023-04-29 11:37:30,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +38: [2023-04-29 11:37:30,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +13: [2023-04-29 11:37:30,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +48: [2023-04-29 11:37:30,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +48: [2023-04-29 11:37:30,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +48: [2023-04-29 11:37:30,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +48: [2023-04-29 11:37:30,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +48: [2023-04-29 11:37:30,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +48: [2023-04-29 11:37:30,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +48: [2023-04-29 11:37:30,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +13: [2023-04-29 11:37:30,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +41: [2023-04-29 11:37:30,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +13: [2023-04-29 11:37:30,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +48: [2023-04-29 11:37:30,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +13: [2023-04-29 11:37:30,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +45: [2023-04-29 11:37:30,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +32: [2023-04-29 11:37:30,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +38: [2023-04-29 11:37:30,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +32: [2023-04-29 11:37:30,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +50: [2023-04-29 11:37:30,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +58: [2023-04-29 11:37:30,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +38: [2023-04-29 11:37:30,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +32: [2023-04-29 11:37:30,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +61: [2023-04-29 11:37:30,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +58: [2023-04-29 11:37:30,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +38: [2023-04-29 11:37:30,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 4: [2023-04-29 11:37:30,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +48: [2023-04-29 11:37:30,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 4: [2023-04-29 11:37:30,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 4: [2023-04-29 11:37:30,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +61: [2023-04-29 11:37:30,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +36: [2023-04-29 11:37:30,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +41: [2023-04-29 11:37:30,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +48: [2023-04-29 11:37:30,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +48: [2023-04-29 11:37:30,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +34: [2023-04-29 11:37:30,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +13: [2023-04-29 11:37:30,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +38: [2023-04-29 11:37:30,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +50: [2023-04-29 11:37:30,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +38: [2023-04-29 11:37:30,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +34: [2023-04-29 11:37:30,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +47: [2023-04-29 11:37:30,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +48: [2023-04-29 11:37:30,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +48: [2023-04-29 11:37:30,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +48: [2023-04-29 11:37:30,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +48: [2023-04-29 11:37:30,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +48: [2023-04-29 11:37:30,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +38: [2023-04-29 11:37:30,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +36: [2023-04-29 11:37:30,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +49: [2023-04-29 11:37:30,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +32: [2023-04-29 11:37:30,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +50: [2023-04-29 11:37:30,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +47: [2023-04-29 11:37:30,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +62: [2023-04-29 11:37:30,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +62: [2023-04-29 11:37:30,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +34: [2023-04-29 11:37:30,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +49: [2023-04-29 11:37:30,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +32: [2023-04-29 11:37:30,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +47: [2023-04-29 11:37:30,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +47: [2023-04-29 11:37:30,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +41: [2023-04-29 11:37:30,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +34: [2023-04-29 11:37:30,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +36: [2023-04-29 11:37:30,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +47: [2023-04-29 11:37:30,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +49: [2023-04-29 11:37:30,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +49: [2023-04-29 11:37:30,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +10: [2023-04-29 11:37:30,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +36: [2023-04-29 11:37:30,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +36: [2023-04-29 11:37:30,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +18: [2023-04-29 11:37:30,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +18: [2023-04-29 11:37:30,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +47: [2023-04-29 11:37:30,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +41: [2023-04-29 11:37:30,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +26: [2023-04-29 11:37:30,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +15: [2023-04-29 11:37:30,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +41: [2023-04-29 11:37:30,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +47: [2023-04-29 11:37:30,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +26: [2023-04-29 11:37:30,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +26: [2023-04-29 11:37:30,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +32: [2023-04-29 11:37:30,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +32: [2023-04-29 11:37:30,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 2: [2023-04-29 11:37:30,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 2: [2023-04-29 11:37:30,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +32: [2023-04-29 11:37:30,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 2: [2023-04-29 11:37:30,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +26: [2023-04-29 11:37:30,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +37: [2023-04-29 11:37:30,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +37: [2023-04-29 11:37:30,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +41: [2023-04-29 11:37:30,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 2: [2023-04-29 11:37:30,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +24: [2023-04-29 11:37:30,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +24: [2023-04-29 11:37:30,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +30: [2023-04-29 11:37:30,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +30: [2023-04-29 11:37:30,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +37: [2023-04-29 11:37:30,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +32: [2023-04-29 11:37:30,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +13: [2023-04-29 11:37:30,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +36: [2023-04-29 11:37:30,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +10: [2023-04-29 11:37:30,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +10: [2023-04-29 11:37:30,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +10: [2023-04-29 11:37:30,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +27: [2023-04-29 11:37:30,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +47: [2023-04-29 11:37:30,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +27: [2023-04-29 11:37:30,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +27: [2023-04-29 11:37:30,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +36: [2023-04-29 11:37:30,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +15: [2023-04-29 11:37:30,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +15: [2023-04-29 11:37:30,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +27: [2023-04-29 11:37:30,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 2: [2023-04-29 11:37:30,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +41: [2023-04-29 11:37:30,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +24: [2023-04-29 11:37:30,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 2: [2023-04-29 11:37:30,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +24: [2023-04-29 11:37:30,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 2: [2023-04-29 11:37:30,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +24: [2023-04-29 11:37:30,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 2: [2023-04-29 11:37:30,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +24: [2023-04-29 11:37:30,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +30: [2023-04-29 11:37:30,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +30: [2023-04-29 11:37:30,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +41: [2023-04-29 11:37:30,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +15: [2023-04-29 11:37:30,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +58: [2023-04-29 11:37:30,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +18: [2023-04-29 11:37:30,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +18: [2023-04-29 11:37:30,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +13: [2023-04-29 11:37:30,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +37: [2023-04-29 11:37:30,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +24: [2023-04-29 11:37:30,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +24: [2023-04-29 11:37:30,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +37: [2023-04-29 11:37:30,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +37: [2023-04-29 11:37:30,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +13: [2023-04-29 11:37:30,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +13: [2023-04-29 11:37:30,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 0: [2023-04-29 11:37:30,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. + 0: [2023-04-29 11:37:30,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. + 0: [2023-04-29 11:37:30,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. + 0: [2023-04-29 11:37:30,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +59: [2023-04-29 11:37:30,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +59: [2023-04-29 11:37:30,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +59: [2023-04-29 11:37:30,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +59: [2023-04-29 11:37:30,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +51: [2023-04-29 11:37:30,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +51: [2023-04-29 11:37:30,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +51: [2023-04-29 11:37:30,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +51: [2023-04-29 11:37:30,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +63: [2023-04-29 11:37:30,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +63: [2023-04-29 11:37:30,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 7: [2023-04-29 11:37:30,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 7: [2023-04-29 11:37:30,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 7: [2023-04-29 11:37:30,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +18: [2023-04-29 11:37:30,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 7: [2023-04-29 11:37:30,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +25: [2023-04-29 11:37:30,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +25: [2023-04-29 11:37:30,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +25: [2023-04-29 11:37:30,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +58: [2023-04-29 11:37:30,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +58: [2023-04-29 11:37:30,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +17: [2023-04-29 11:37:30,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +25: [2023-04-29 11:37:30,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 1: [2023-04-29 11:37:30,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 1: [2023-04-29 11:37:30,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 1: [2023-04-29 11:37:30,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 1: [2023-04-29 11:37:30,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +59: [2023-04-29 11:37:30,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +59: [2023-04-29 11:37:30,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +59: [2023-04-29 11:37:30,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +63: [2023-04-29 11:37:30,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +63: [2023-04-29 11:37:30,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +59: [2023-04-29 11:37:30,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +42: [2023-04-29 11:37:30,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +42: [2023-04-29 11:37:30,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +57: [2023-04-29 11:37:30,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +42: [2023-04-29 11:37:30,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 7: [2023-04-29 11:37:30,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +63: [2023-04-29 11:37:30,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +63: [2023-04-29 11:37:30,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +42: [2023-04-29 11:37:30,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +17: [2023-04-29 11:37:30,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +25: [2023-04-29 11:37:30,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +51: [2023-04-29 11:37:30,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +51: [2023-04-29 11:37:30,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +25: [2023-04-29 11:37:30,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +51: [2023-04-29 11:37:30,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +18: [2023-04-29 11:37:30,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +58: [2023-04-29 11:37:30,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +18: [2023-04-29 11:37:30,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +51: [2023-04-29 11:37:30,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 7: [2023-04-29 11:37:30,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 1: [2023-04-29 11:37:30,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 1: [2023-04-29 11:37:30,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 7: [2023-04-29 11:37:30,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +25: [2023-04-29 11:37:30,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 1: [2023-04-29 11:37:30,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 7: [2023-04-29 11:37:30,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +25: [2023-04-29 11:37:30,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +63: [2023-04-29 11:37:30,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +63: [2023-04-29 11:37:30,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... + 1: [2023-04-29 11:37:30,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +57: [2023-04-29 11:37:30,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +52: [2023-04-29 11:37:30,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +23: [2023-04-29 11:37:30,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +10: [2023-04-29 11:37:30,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +31: [2023-04-29 11:37:30,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 8: [2023-04-29 11:37:30,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +42: [2023-04-29 11:37:30,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +42: [2023-04-29 11:37:30,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +20: [2023-04-29 11:37:30,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +20: [2023-04-29 11:37:30,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +20: [2023-04-29 11:37:30,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +42: [2023-04-29 11:37:30,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +42: [2023-04-29 11:37:30,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +20: [2023-04-29 11:37:30,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +57: [2023-04-29 11:37:30,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +18: [2023-04-29 11:37:30,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +39: [2023-04-29 11:37:30,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +52: [2023-04-29 11:37:30,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +19: [2023-04-29 11:37:30,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +23: [2023-04-29 11:37:30,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +10: [2023-04-29 11:37:30,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +30: [2023-04-29 11:37:30,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +30: [2023-04-29 11:37:30,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +20: [2023-04-29 11:37:30,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +30: [2023-04-29 11:37:30,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +31: [2023-04-29 11:37:30,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +20: [2023-04-29 11:37:30,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +10: [2023-04-29 11:37:30,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +20: [2023-04-29 11:37:30,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +19: [2023-04-29 11:37:30,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +57: [2023-04-29 11:37:30,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +20: [2023-04-29 11:37:30,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +50: [2023-04-29 11:37:30,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +39: [2023-04-29 11:37:30,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +39: [2023-04-29 11:37:30,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +39: [2023-04-29 11:37:30,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +10: [2023-04-29 11:37:30,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +17: [2023-04-29 11:37:30,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +51: [2023-04-29 11:37:30,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +19: [2023-04-29 11:37:30,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +19: [2023-04-29 11:37:30,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +30: [2023-04-29 11:37:30,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +57: [2023-04-29 11:37:30,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +51: [2023-04-29 11:37:30,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +23: [2023-04-29 11:37:30,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +51: [2023-04-29 11:37:30,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +51: [2023-04-29 11:37:30,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +58: [2023-04-29 11:37:30,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +34: [2023-04-29 11:37:30,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +23: [2023-04-29 11:37:30,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +17: [2023-04-29 11:37:30,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +42: [2023-04-29 11:37:30,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +42: [2023-04-29 11:37:30,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +50: [2023-04-29 11:37:30,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +53: [2023-04-29 11:37:30,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +57: [2023-04-29 11:37:30,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 8: [2023-04-29 11:37:30,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +17: [2023-04-29 11:37:30,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +17: [2023-04-29 11:37:30,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +57: [2023-04-29 11:37:30,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +48: [2023-04-29 11:37:30,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +34: [2023-04-29 11:37:30,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +62: [2023-04-29 11:37:30,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +62: [2023-04-29 11:37:30,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +62: [2023-04-29 11:37:30,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +62: [2023-04-29 11:37:30,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +51: [2023-04-29 11:37:30,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +50: [2023-04-29 11:37:30,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +52: [2023-04-29 11:37:30,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +52: [2023-04-29 11:37:30,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... + 0: [2023-04-29 11:37:30,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +52: [2023-04-29 11:37:30,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +31: [2023-04-29 11:37:30,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +31: [2023-04-29 11:37:30,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 0: [2023-04-29 11:37:30,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +42: [2023-04-29 11:37:30,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +42: [2023-04-29 11:37:30,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +57: [2023-04-29 11:37:30,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +51: [2023-04-29 11:37:30,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +32: [2023-04-29 11:37:30,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 0: [2023-04-29 11:37:30,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +17: [2023-04-29 11:37:30,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +17: [2023-04-29 11:37:30,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... + 0: [2023-04-29 11:37:30,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 8: [2023-04-29 11:37:30,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +51: [2023-04-29 11:37:30,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +49: [2023-04-29 11:37:30,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +52: [2023-04-29 11:37:30,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +50: [2023-04-29 11:37:30,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +51: [2023-04-29 11:37:30,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +58: [2023-04-29 11:37:30,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +58: [2023-04-29 11:37:30,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 9: [2023-04-29 11:37:30,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 9: [2023-04-29 11:37:30,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +53: [2023-04-29 11:37:30,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +53: [2023-04-29 11:37:30,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +53: [2023-04-29 11:37:30,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +23: [2023-04-29 11:37:30,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 8: [2023-04-29 11:37:30,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +63: [2023-04-29 11:37:30,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +52: [2023-04-29 11:37:30,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +63: [2023-04-29 11:37:30,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 9: [2023-04-29 11:37:30,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 9: [2023-04-29 11:37:30,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +48: [2023-04-29 11:37:30,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +48: [2023-04-29 11:37:30,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 8: [2023-04-29 11:37:30,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +49: [2023-04-29 11:37:30,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +34: [2023-04-29 11:37:30,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +35: [2023-04-29 11:37:30,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +35: [2023-04-29 11:37:30,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +49: [2023-04-29 11:37:30,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +63: [2023-04-29 11:37:30,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +63: [2023-04-29 11:37:30,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 9: [2023-04-29 11:37:30,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +31: [2023-04-29 11:37:30,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +52: [2023-04-29 11:37:30,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... + 9: [2023-04-29 11:37:30,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +48: [2023-04-29 11:37:30,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +35: [2023-04-29 11:37:30,992] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +24: [2023-04-29 11:37:30,992] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +35: [2023-04-29 11:37:30,992] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. + 9: [2023-04-29 11:37:30,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +34: [2023-04-29 11:37:30,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +31: [2023-04-29 11:37:30,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +34: [2023-04-29 11:37:30,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +58: [2023-04-29 11:37:30,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +63: [2023-04-29 11:37:30,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +23: [2023-04-29 11:37:30,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +63: [2023-04-29 11:37:30,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +63: [2023-04-29 11:37:30,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +50: [2023-04-29 11:37:30,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +49: [2023-04-29 11:37:30,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +53: [2023-04-29 11:37:30,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +53: [2023-04-29 11:37:30,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +53: [2023-04-29 11:37:30,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. + 9: [2023-04-29 11:37:30,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +50: [2023-04-29 11:37:30,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +63: [2023-04-29 11:37:30,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +39: [2023-04-29 11:37:30,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 2: [2023-04-29 11:37:30,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +19: [2023-04-29 11:37:30,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +39: [2023-04-29 11:37:30,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +39: [2023-04-29 11:37:30,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +39: [2023-04-29 11:37:30,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +13: [2023-04-29 11:37:30,998] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +32: [2023-04-29 11:37:30,998] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +19: [2023-04-29 11:37:30,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +19: [2023-04-29 11:37:30,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +53: [2023-04-29 11:37:30,999] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +19: [2023-04-29 11:37:30,999] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +53: [2023-04-29 11:37:30,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +39: [2023-04-29 11:37:31,000] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +41: [2023-04-29 11:37:31,000] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +41: [2023-04-29 11:37:31,000] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +23: [2023-04-29 11:37:31,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +39: [2023-04-29 11:37:31,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +39: [2023-04-29 11:37:31,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +39: [2023-04-29 11:37:31,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +48: [2023-04-29 11:37:31,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +24: [2023-04-29 11:37:31,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +24: [2023-04-29 11:37:31,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +34: [2023-04-29 11:37:31,001] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +34: [2023-04-29 11:37:31,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +23: [2023-04-29 11:37:31,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +32: [2023-04-29 11:37:31,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +41: [2023-04-29 11:37:31,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +50: [2023-04-29 11:37:31,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +41: [2023-04-29 11:37:31,003] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +13: [2023-04-29 11:37:31,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +50: [2023-04-29 11:37:31,004] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... + 2: [2023-04-29 11:37:31,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 2: [2023-04-29 11:37:31,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 2: [2023-04-29 11:37:31,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +49: [2023-04-29 11:37:31,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +49: [2023-04-29 11:37:31,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +42: [2023-04-29 11:37:31,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +42: [2023-04-29 11:37:31,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +42: [2023-04-29 11:37:31,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +60: [2023-04-29 11:37:31,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +60: [2023-04-29 11:37:31,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +27: [2023-04-29 11:37:31,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +27: [2023-04-29 11:37:31,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +41: [2023-04-29 11:37:31,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +32: [2023-04-29 11:37:31,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +32: [2023-04-29 11:37:31,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +24: [2023-04-29 11:37:31,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +59: [2023-04-29 11:37:31,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +32: [2023-04-29 11:37:31,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +60: [2023-04-29 11:37:31,009] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +32: [2023-04-29 11:37:31,009] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +41: [2023-04-29 11:37:31,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +34: [2023-04-29 11:37:31,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +60: [2023-04-29 11:37:31,009] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +32: [2023-04-29 11:37:31,009] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +41: [2023-04-29 11:37:31,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +49: [2023-04-29 11:37:31,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +49: [2023-04-29 11:37:31,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +41: [2023-04-29 11:37:31,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +31: [2023-04-29 11:37:31,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +27: [2023-04-29 11:37:31,012] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +27: [2023-04-29 11:37:31,012] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +25: [2023-04-29 11:37:31,012] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +16: [2023-04-29 11:37:31,013] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +16: [2023-04-29 11:37:31,013] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +16: [2023-04-29 11:37:31,013] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +16: [2023-04-29 11:37:31,013] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +32: [2023-04-29 11:37:31,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +60: [2023-04-29 11:37:31,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +27: [2023-04-29 11:37:31,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +27: [2023-04-29 11:37:31,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +60: [2023-04-29 11:37:31,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +32: [2023-04-29 11:37:31,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +13: [2023-04-29 11:37:31,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +31: [2023-04-29 11:37:31,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +62: [2023-04-29 11:37:31,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +56: [2023-04-29 11:37:31,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +56: [2023-04-29 11:37:31,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +56: [2023-04-29 11:37:31,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +56: [2023-04-29 11:37:31,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +32: [2023-04-29 11:37:31,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +42: [2023-04-29 11:37:31,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +60: [2023-04-29 11:37:31,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +62: [2023-04-29 11:37:31,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 7: [2023-04-29 11:37:31,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +48: [2023-04-29 11:37:31,016] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +27: [2023-04-29 11:37:31,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +13: [2023-04-29 11:37:31,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +13: [2023-04-29 11:37:31,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +60: [2023-04-29 11:37:31,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +27: [2023-04-29 11:37:31,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +38: [2023-04-29 11:37:31,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +38: [2023-04-29 11:37:31,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +48: [2023-04-29 11:37:31,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +38: [2023-04-29 11:37:31,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +35: [2023-04-29 11:37:31,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +35: [2023-04-29 11:37:31,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +59: [2023-04-29 11:37:31,020] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +59: [2023-04-29 11:37:31,020] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +62: [2023-04-29 11:37:31,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +62: [2023-04-29 11:37:31,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +13: [2023-04-29 11:37:31,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +53: [2023-04-29 11:37:31,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +53: [2023-04-29 11:37:31,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +53: [2023-04-29 11:37:31,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +24: [2023-04-29 11:37:31,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 2: [2023-04-29 11:37:31,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +16: [2023-04-29 11:37:31,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +16: [2023-04-29 11:37:31,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +16: [2023-04-29 11:37:31,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +25: [2023-04-29 11:37:31,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +38: [2023-04-29 11:37:31,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +32: [2023-04-29 11:37:31,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +35: [2023-04-29 11:37:31,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +35: [2023-04-29 11:37:31,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +13: [2023-04-29 11:37:31,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +48: [2023-04-29 11:37:31,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +16: [2023-04-29 11:37:31,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +13: [2023-04-29 11:37:31,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +32: [2023-04-29 11:37:31,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +35: [2023-04-29 11:37:31,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +35: [2023-04-29 11:37:31,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +38: [2023-04-29 11:37:31,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +35: [2023-04-29 11:37:31,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +35: [2023-04-29 11:37:31,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +53: [2023-04-29 11:37:31,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +35: [2023-04-29 11:37:31,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +38: [2023-04-29 11:37:31,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 7: [2023-04-29 11:37:31,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 7: [2023-04-29 11:37:31,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +38: [2023-04-29 11:37:31,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +59: [2023-04-29 11:37:31,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +20: [2023-04-29 11:37:31,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +20: [2023-04-29 11:37:31,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +24: [2023-04-29 11:37:31,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +20: [2023-04-29 11:37:31,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. + 7: [2023-04-29 11:37:31,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +20: [2023-04-29 11:37:31,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +24: [2023-04-29 11:37:31,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +47: [2023-04-29 11:37:31,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +47: [2023-04-29 11:37:31,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +47: [2023-04-29 11:37:31,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +32: [2023-04-29 11:37:31,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +35: [2023-04-29 11:37:31,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +47: [2023-04-29 11:37:31,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +25: [2023-04-29 11:37:31,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +39: [2023-04-29 11:37:31,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +25: [2023-04-29 11:37:31,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +39: [2023-04-29 11:37:31,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +38: [2023-04-29 11:37:31,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +39: [2023-04-29 11:37:31,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +20: [2023-04-29 11:37:31,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +39: [2023-04-29 11:37:31,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +53: [2023-04-29 11:37:31,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +53: [2023-04-29 11:37:31,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +53: [2023-04-29 11:37:31,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +35: [2023-04-29 11:37:31,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 2: [2023-04-29 11:37:31,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +47: [2023-04-29 11:37:31,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +47: [2023-04-29 11:37:31,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 2: [2023-04-29 11:37:31,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 2: [2023-04-29 11:37:31,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +47: [2023-04-29 11:37:31,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +59: [2023-04-29 11:37:31,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +35: [2023-04-29 11:37:31,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +24: [2023-04-29 11:37:31,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +25: [2023-04-29 11:37:31,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +42: [2023-04-29 11:37:31,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +42: [2023-04-29 11:37:31,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +42: [2023-04-29 11:37:31,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +47: [2023-04-29 11:37:31,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +56: [2023-04-29 11:37:31,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +56: [2023-04-29 11:37:31,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +56: [2023-04-29 11:37:31,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +51: [2023-04-29 11:37:31,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +32: [2023-04-29 11:37:31,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 0: [2023-04-29 11:37:31,044] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +56: [2023-04-29 11:37:31,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 7: [2023-04-29 11:37:31,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 0: [2023-04-29 11:37:31,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 0: [2023-04-29 11:37:31,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 0: [2023-04-29 11:37:31,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 0: [2023-04-29 11:37:31,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +32: [2023-04-29 11:37:31,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +25: [2023-04-29 11:37:31,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 0: [2023-04-29 11:37:31,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +59: [2023-04-29 11:37:31,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +20: [2023-04-29 11:37:31,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +51: [2023-04-29 11:37:31,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +51: [2023-04-29 11:37:31,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +59: [2023-04-29 11:37:31,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +20: [2023-04-29 11:37:31,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 0: [2023-04-29 11:37:31,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... + 6: [2023-04-29 11:37:31,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. + 6: [2023-04-29 11:37:31,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. + 6: [2023-04-29 11:37:31,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +20: [2023-04-29 11:37:31,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 6: [2023-04-29 11:37:31,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. + 0: [2023-04-29 11:37:31,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 0: [2023-04-29 11:37:31,052] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,052] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +51: [2023-04-29 11:37:31,052] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... + 0: [2023-04-29 11:37:31,052] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 0: [2023-04-29 11:37:31,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +42: [2023-04-29 11:37:31,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 7: [2023-04-29 11:37:31,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 0: [2023-04-29 11:37:31,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... + 0: [2023-04-29 11:37:31,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 9: [2023-04-29 11:37:31,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 9: [2023-04-29 11:37:31,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 0: [2023-04-29 11:37:31,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +59: [2023-04-29 11:37:31,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +63: [2023-04-29 11:37:31,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 7: [2023-04-29 11:37:31,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +20: [2023-04-29 11:37:31,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 9: [2023-04-29 11:37:31,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +20: [2023-04-29 11:37:31,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +25: [2023-04-29 11:37:31,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +20: [2023-04-29 11:37:31,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 0: [2023-04-29 11:37:31,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +25: [2023-04-29 11:37:31,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 0: [2023-04-29 11:37:31,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +20: [2023-04-29 11:37:31,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +20: [2023-04-29 11:37:31,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +63: [2023-04-29 11:37:31,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 7: [2023-04-29 11:37:31,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +63: [2023-04-29 11:37:31,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +63: [2023-04-29 11:37:31,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +43: [2023-04-29 11:37:31,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +43: [2023-04-29 11:37:31,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +43: [2023-04-29 11:37:31,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +43: [2023-04-29 11:37:31,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +51: [2023-04-29 11:37:31,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +42: [2023-04-29 11:37:31,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 9: [2023-04-29 11:37:31,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +42: [2023-04-29 11:37:31,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +42: [2023-04-29 11:37:31,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +51: [2023-04-29 11:37:31,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +51: [2023-04-29 11:37:31,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +43: [2023-04-29 11:37:31,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +43: [2023-04-29 11:37:31,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +43: [2023-04-29 11:37:31,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +43: [2023-04-29 11:37:31,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +36: [2023-04-29 11:37:31,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +36: [2023-04-29 11:37:31,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +36: [2023-04-29 11:37:31,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +36: [2023-04-29 11:37:31,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +49: [2023-04-29 11:37:31,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +49: [2023-04-29 11:37:31,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +51: [2023-04-29 11:37:31,075] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +49: [2023-04-29 11:37:31,076] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +49: [2023-04-29 11:37:31,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +41: [2023-04-29 11:37:31,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +36: [2023-04-29 11:37:31,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +36: [2023-04-29 11:37:31,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +42: [2023-04-29 11:37:31,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +20: [2023-04-29 11:37:31,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +41: [2023-04-29 11:37:31,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +20: [2023-04-29 11:37:31,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +63: [2023-04-29 11:37:31,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +36: [2023-04-29 11:37:31,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 6: [2023-04-29 11:37:31,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 6: [2023-04-29 11:37:31,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 6: [2023-04-29 11:37:31,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +36: [2023-04-29 11:37:31,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +49: [2023-04-29 11:37:31,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +60: [2023-04-29 11:37:31,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +60: [2023-04-29 11:37:31,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +49: [2023-04-29 11:37:31,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +20: [2023-04-29 11:37:31,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +42: [2023-04-29 11:37:31,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +49: [2023-04-29 11:37:31,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +51: [2023-04-29 11:37:31,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +14: [2023-04-29 11:37:31,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +14: [2023-04-29 11:37:31,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +49: [2023-04-29 11:37:31,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 6: [2023-04-29 11:37:31,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 9: [2023-04-29 11:37:31,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +41: [2023-04-29 11:37:31,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 9: [2023-04-29 11:37:31,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +14: [2023-04-29 11:37:31,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +42: [2023-04-29 11:37:31,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +14: [2023-04-29 11:37:31,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +62: [2023-04-29 11:37:31,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +35: [2023-04-29 11:37:31,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 9: [2023-04-29 11:37:31,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +60: [2023-04-29 11:37:31,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +60: [2023-04-29 11:37:31,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +50: [2023-04-29 11:37:31,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +50: [2023-04-29 11:37:31,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +62: [2023-04-29 11:37:31,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +50: [2023-04-29 11:37:31,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +50: [2023-04-29 11:37:31,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +39: [2023-04-29 11:37:31,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +41: [2023-04-29 11:37:31,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +38: [2023-04-29 11:37:31,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +35: [2023-04-29 11:37:31,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +42: [2023-04-29 11:37:31,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +42: [2023-04-29 11:37:31,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +50: [2023-04-29 11:37:31,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +50: [2023-04-29 11:37:31,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +63: [2023-04-29 11:37:31,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +63: [2023-04-29 11:37:31,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +63: [2023-04-29 11:37:31,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 4: [2023-04-29 11:37:31,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. + 4: [2023-04-29 11:37:31,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. + 4: [2023-04-29 11:37:31,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. + 4: [2023-04-29 11:37:31,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +16: [2023-04-29 11:37:31,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +16: [2023-04-29 11:37:31,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +16: [2023-04-29 11:37:31,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +42: [2023-04-29 11:37:31,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +51: [2023-04-29 11:37:31,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +51: [2023-04-29 11:37:31,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +35: [2023-04-29 11:37:31,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +50: [2023-04-29 11:37:31,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +62: [2023-04-29 11:37:31,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +23: [2023-04-29 11:37:31,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +23: [2023-04-29 11:37:31,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +23: [2023-04-29 11:37:31,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +62: [2023-04-29 11:37:31,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +23: [2023-04-29 11:37:31,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +38: [2023-04-29 11:37:31,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +38: [2023-04-29 11:37:31,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 9: [2023-04-29 11:37:31,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +62: [2023-04-29 11:37:31,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +21: [2023-04-29 11:37:31,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +21: [2023-04-29 11:37:31,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +21: [2023-04-29 11:37:31,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +62: [2023-04-29 11:37:31,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +21: [2023-04-29 11:37:31,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +39: [2023-04-29 11:37:31,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +53: [2023-04-29 11:37:31,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +39: [2023-04-29 11:37:31,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +39: [2023-04-29 11:37:31,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +50: [2023-04-29 11:37:31,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +35: [2023-04-29 11:37:31,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +51: [2023-04-29 11:37:31,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +47: [2023-04-29 11:37:31,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +38: [2023-04-29 11:37:31,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +16: [2023-04-29 11:37:31,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +42: [2023-04-29 11:37:31,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +42: [2023-04-29 11:37:31,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +39: [2023-04-29 11:37:31,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +60: [2023-04-29 11:37:31,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +60: [2023-04-29 11:37:31,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +53: [2023-04-29 11:37:31,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +53: [2023-04-29 11:37:31,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +35: [2023-04-29 11:37:31,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +60: [2023-04-29 11:37:31,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +42: [2023-04-29 11:37:31,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +53: [2023-04-29 11:37:31,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +47: [2023-04-29 11:37:31,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +53: [2023-04-29 11:37:31,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +62: [2023-04-29 11:37:31,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +62: [2023-04-29 11:37:31,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +51: [2023-04-29 11:37:31,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +60: [2023-04-29 11:37:31,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +60: [2023-04-29 11:37:31,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +39: [2023-04-29 11:37:31,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +39: [2023-04-29 11:37:31,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +51: [2023-04-29 11:37:31,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +53: [2023-04-29 11:37:31,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +53: [2023-04-29 11:37:31,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +35: [2023-04-29 11:37:31,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +56: [2023-04-29 11:37:31,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +56: [2023-04-29 11:37:31,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +35: [2023-04-29 11:37:31,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +60: [2023-04-29 11:37:31,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +39: [2023-04-29 11:37:31,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +14: [2023-04-29 11:37:31,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +51: [2023-04-29 11:37:31,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +47: [2023-04-29 11:37:31,111] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +47: [2023-04-29 11:37:31,111] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +53: [2023-04-29 11:37:31,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +37: [2023-04-29 11:37:31,112] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +37: [2023-04-29 11:37:31,112] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +37: [2023-04-29 11:37:31,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +37: [2023-04-29 11:37:31,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +33: [2023-04-29 11:37:31,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +33: [2023-04-29 11:37:31,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +41: [2023-04-29 11:37:31,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +41: [2023-04-29 11:37:31,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +35: [2023-04-29 11:37:31,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +35: [2023-04-29 11:37:31,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +33: [2023-04-29 11:37:31,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +33: [2023-04-29 11:37:31,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +14: [2023-04-29 11:37:31,114] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +55: [2023-04-29 11:37:31,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +51: [2023-04-29 11:37:31,114] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +56: [2023-04-29 11:37:31,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +38: [2023-04-29 11:37:31,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +14: [2023-04-29 11:37:31,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +14: [2023-04-29 11:37:31,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +55: [2023-04-29 11:37:31,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +56: [2023-04-29 11:37:31,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +56: [2023-04-29 11:37:31,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +33: [2023-04-29 11:37:31,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +55: [2023-04-29 11:37:31,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +33: [2023-04-29 11:37:31,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +55: [2023-04-29 11:37:31,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +41: [2023-04-29 11:37:31,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +33: [2023-04-29 11:37:31,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +33: [2023-04-29 11:37:31,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +37: [2023-04-29 11:37:31,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +56: [2023-04-29 11:37:31,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 0: [2023-04-29 11:37:31,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +35: [2023-04-29 11:37:31,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +35: [2023-04-29 11:37:31,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +37: [2023-04-29 11:37:31,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +37: [2023-04-29 11:37:31,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +33: [2023-04-29 11:37:31,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +33: [2023-04-29 11:37:31,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +60: [2023-04-29 11:37:31,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +37: [2023-04-29 11:37:31,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +60: [2023-04-29 11:37:31,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +55: [2023-04-29 11:37:31,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 4: [2023-04-29 11:37:31,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +55: [2023-04-29 11:37:31,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +56: [2023-04-29 11:37:31,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +33: [2023-04-29 11:37:31,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +33: [2023-04-29 11:37:31,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +55: [2023-04-29 11:37:31,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 4: [2023-04-29 11:37:31,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +21: [2023-04-29 11:37:31,123] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +55: [2023-04-29 11:37:31,123] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +35: [2023-04-29 11:37:31,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +56: [2023-04-29 11:37:31,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... + 0: [2023-04-29 11:37:31,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +52: [2023-04-29 11:37:31,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +52: [2023-04-29 11:37:31,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +52: [2023-04-29 11:37:31,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +21: [2023-04-29 11:37:31,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +47: [2023-04-29 11:37:31,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +52: [2023-04-29 11:37:31,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +41: [2023-04-29 11:37:31,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 0: [2023-04-29 11:37:31,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 0: [2023-04-29 11:37:31,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +35: [2023-04-29 11:37:31,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +38: [2023-04-29 11:37:31,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +38: [2023-04-29 11:37:31,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +21: [2023-04-29 11:37:31,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +47: [2023-04-29 11:37:31,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +43: [2023-04-29 11:37:31,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +23: [2023-04-29 11:37:31,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +23: [2023-04-29 11:37:31,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +47: [2023-04-29 11:37:31,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +45: [2023-04-29 11:37:31,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 4: [2023-04-29 11:37:31,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +52: [2023-04-29 11:37:31,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +45: [2023-04-29 11:37:31,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +45: [2023-04-29 11:37:31,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 4: [2023-04-29 11:37:31,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +45: [2023-04-29 11:37:31,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +47: [2023-04-29 11:37:31,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +47: [2023-04-29 11:37:31,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +21: [2023-04-29 11:37:31,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +16: [2023-04-29 11:37:31,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +38: [2023-04-29 11:37:31,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +47: [2023-04-29 11:37:31,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +22: [2023-04-29 11:37:31,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +22: [2023-04-29 11:37:31,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +22: [2023-04-29 11:37:31,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +28: [2023-04-29 11:37:31,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +28: [2023-04-29 11:37:31,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +28: [2023-04-29 11:37:31,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +28: [2023-04-29 11:37:31,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +22: [2023-04-29 11:37:31,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +60: [2023-04-29 11:37:31,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +52: [2023-04-29 11:37:31,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +52: [2023-04-29 11:37:31,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +52: [2023-04-29 11:37:31,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +23: [2023-04-29 11:37:31,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +23: [2023-04-29 11:37:31,133] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +43: [2023-04-29 11:37:31,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +60: [2023-04-29 11:37:31,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +45: [2023-04-29 11:37:31,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +45: [2023-04-29 11:37:31,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +16: [2023-04-29 11:37:31,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +45: [2023-04-29 11:37:31,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +16: [2023-04-29 11:37:31,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +43: [2023-04-29 11:37:31,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +43: [2023-04-29 11:37:31,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +45: [2023-04-29 11:37:31,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +60: [2023-04-29 11:37:31,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +60: [2023-04-29 11:37:31,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +20: [2023-04-29 11:37:31,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +20: [2023-04-29 11:37:31,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +20: [2023-04-29 11:37:31,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +16: [2023-04-29 11:37:31,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 6: [2023-04-29 11:37:31,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +20: [2023-04-29 11:37:31,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +38: [2023-04-29 11:37:31,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +38: [2023-04-29 11:37:31,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +47: [2023-04-29 11:37:31,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +38: [2023-04-29 11:37:31,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +38: [2023-04-29 11:37:31,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +33: [2023-04-29 11:37:31,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +47: [2023-04-29 11:37:31,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +36: [2023-04-29 11:37:31,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +36: [2023-04-29 11:37:31,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +12: [2023-04-29 11:37:31,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +12: [2023-04-29 11:37:31,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +12: [2023-04-29 11:37:31,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +12: [2023-04-29 11:37:31,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +35: [2023-04-29 11:37:31,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 6: [2023-04-29 11:37:31,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +20: [2023-04-29 11:37:31,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +20: [2023-04-29 11:37:31,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +20: [2023-04-29 11:37:31,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +33: [2023-04-29 11:37:31,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. + 1: [2023-04-29 11:37:31,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +49: [2023-04-29 11:37:31,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +54: [2023-04-29 11:37:31,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +54: [2023-04-29 11:37:31,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 0: [2023-04-29 11:37:31,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +20: [2023-04-29 11:37:31,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... + 1: [2023-04-29 11:37:31,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +54: [2023-04-29 11:37:31,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +33: [2023-04-29 11:37:31,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +54: [2023-04-29 11:37:31,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +50: [2023-04-29 11:37:31,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +57: [2023-04-29 11:37:31,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +57: [2023-04-29 11:37:31,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +57: [2023-04-29 11:37:31,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +57: [2023-04-29 11:37:31,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +35: [2023-04-29 11:37:31,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +43: [2023-04-29 11:37:31,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +33: [2023-04-29 11:37:31,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +49: [2023-04-29 11:37:31,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +49: [2023-04-29 11:37:31,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +49: [2023-04-29 11:37:31,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +54: [2023-04-29 11:37:31,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +36: [2023-04-29 11:37:31,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +36: [2023-04-29 11:37:31,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +54: [2023-04-29 11:37:31,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +54: [2023-04-29 11:37:31,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 0: [2023-04-29 11:37:31,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +57: [2023-04-29 11:37:31,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +57: [2023-04-29 11:37:31,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +54: [2023-04-29 11:37:31,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 6: [2023-04-29 11:37:31,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 6: [2023-04-29 11:37:31,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 6: [2023-04-29 11:37:31,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 0: [2023-04-29 11:37:31,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +57: [2023-04-29 11:37:31,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +57: [2023-04-29 11:37:31,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +35: [2023-04-29 11:37:31,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +22: [2023-04-29 11:37:31,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +43: [2023-04-29 11:37:31,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +28: [2023-04-29 11:37:31,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 0: [2023-04-29 11:37:31,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +28: [2023-04-29 11:37:31,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +47: [2023-04-29 11:37:31,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +22: [2023-04-29 11:37:31,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +22: [2023-04-29 11:37:31,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +28: [2023-04-29 11:37:31,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +47: [2023-04-29 11:37:31,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +22: [2023-04-29 11:37:31,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +31: [2023-04-29 11:37:31,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +31: [2023-04-29 11:37:31,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +31: [2023-04-29 11:37:31,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +31: [2023-04-29 11:37:31,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +50: [2023-04-29 11:37:31,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +43: [2023-04-29 11:37:31,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +43: [2023-04-29 11:37:31,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +28: [2023-04-29 11:37:31,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 6: [2023-04-29 11:37:31,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +47: [2023-04-29 11:37:31,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 6: [2023-04-29 11:37:31,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +47: [2023-04-29 11:37:31,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +59: [2023-04-29 11:37:31,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +59: [2023-04-29 11:37:31,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +59: [2023-04-29 11:37:31,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. + 6: [2023-04-29 11:37:31,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +59: [2023-04-29 11:37:31,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +46: [2023-04-29 11:37:31,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +46: [2023-04-29 11:37:31,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +46: [2023-04-29 11:37:31,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +46: [2023-04-29 11:37:31,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +12: [2023-04-29 11:37:31,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +49: [2023-04-29 11:37:31,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +38: [2023-04-29 11:37:31,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +38: [2023-04-29 11:37:31,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +50: [2023-04-29 11:37:31,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +14: [2023-04-29 11:37:31,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +36: [2023-04-29 11:37:31,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +36: [2023-04-29 11:37:31,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +54: [2023-04-29 11:37:31,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +54: [2023-04-29 11:37:31,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +12: [2023-04-29 11:37:31,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +54: [2023-04-29 11:37:31,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +12: [2023-04-29 11:37:31,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +54: [2023-04-29 11:37:31,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +12: [2023-04-29 11:37:31,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +38: [2023-04-29 11:37:31,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +38: [2023-04-29 11:37:31,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +14: [2023-04-29 11:37:31,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +50: [2023-04-29 11:37:31,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +14: [2023-04-29 11:37:31,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +52: [2023-04-29 11:37:31,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +37: [2023-04-29 11:37:31,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +55: [2023-04-29 11:37:31,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +14: [2023-04-29 11:37:31,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +14: [2023-04-29 11:37:31,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +25: [2023-04-29 11:37:31,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +25: [2023-04-29 11:37:31,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +56: [2023-04-29 11:37:31,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +56: [2023-04-29 11:37:31,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +25: [2023-04-29 11:37:31,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +25: [2023-04-29 11:37:31,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +36: [2023-04-29 11:37:31,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +21: [2023-04-29 11:37:31,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 4: [2023-04-29 11:37:31,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +50: [2023-04-29 11:37:31,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +34: [2023-04-29 11:37:31,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +34: [2023-04-29 11:37:31,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +52: [2023-04-29 11:37:31,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +61: [2023-04-29 11:37:31,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +61: [2023-04-29 11:37:31,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +61: [2023-04-29 11:37:31,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +14: [2023-04-29 11:37:31,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +61: [2023-04-29 11:37:31,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +40: [2023-04-29 11:37:31,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +40: [2023-04-29 11:37:31,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +40: [2023-04-29 11:37:31,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +36: [2023-04-29 11:37:31,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +40: [2023-04-29 11:37:31,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +31: [2023-04-29 11:37:31,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +56: [2023-04-29 11:37:31,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +49: [2023-04-29 11:37:31,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +56: [2023-04-29 11:37:31,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +14: [2023-04-29 11:37:31,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +49: [2023-04-29 11:37:31,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +14: [2023-04-29 11:37:31,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +49: [2023-04-29 11:37:31,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +21: [2023-04-29 11:37:31,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +55: [2023-04-29 11:37:31,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +56: [2023-04-29 11:37:31,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +59: [2023-04-29 11:37:31,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +59: [2023-04-29 11:37:31,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +31: [2023-04-29 11:37:31,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 4: [2023-04-29 11:37:31,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 4: [2023-04-29 11:37:31,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +56: [2023-04-29 11:37:31,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +34: [2023-04-29 11:37:31,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +61: [2023-04-29 11:37:31,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +37: [2023-04-29 11:37:31,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +37: [2023-04-29 11:37:31,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +31: [2023-04-29 11:37:31,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +61: [2023-04-29 11:37:31,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +34: [2023-04-29 11:37:31,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +23: [2023-04-29 11:37:31,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +50: [2023-04-29 11:37:31,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +55: [2023-04-29 11:37:31,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +40: [2023-04-29 11:37:31,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +33: [2023-04-29 11:37:31,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +33: [2023-04-29 11:37:31,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +33: [2023-04-29 11:37:31,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 4: [2023-04-29 11:37:31,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 4: [2023-04-29 11:37:31,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +45: [2023-04-29 11:37:31,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +61: [2023-04-29 11:37:31,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +46: [2023-04-29 11:37:31,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +56: [2023-04-29 11:37:31,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +46: [2023-04-29 11:37:31,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +31: [2023-04-29 11:37:31,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +10: [2023-04-29 11:37:31,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +61: [2023-04-29 11:37:31,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +59: [2023-04-29 11:37:31,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +10: [2023-04-29 11:37:31,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +10: [2023-04-29 11:37:31,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. + 4: [2023-04-29 11:37:31,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 4: [2023-04-29 11:37:31,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +40: [2023-04-29 11:37:31,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +40: [2023-04-29 11:37:31,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +59: [2023-04-29 11:37:31,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +56: [2023-04-29 11:37:31,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +23: [2023-04-29 11:37:31,197] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 4: [2023-04-29 11:37:31,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +44: [2023-04-29 11:37:31,197] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +44: [2023-04-29 11:37:31,197] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +40: [2023-04-29 11:37:31,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +46: [2023-04-29 11:37:31,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +46: [2023-04-29 11:37:31,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +10: [2023-04-29 11:37:31,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +21: [2023-04-29 11:37:31,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +44: [2023-04-29 11:37:31,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +37: [2023-04-29 11:37:31,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +23: [2023-04-29 11:37:31,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +44: [2023-04-29 11:37:31,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +33: [2023-04-29 11:37:31,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +45: [2023-04-29 11:37:31,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +23: [2023-04-29 11:37:31,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +23: [2023-04-29 11:37:31,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... + 4: [2023-04-29 11:37:31,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 4: [2023-04-29 11:37:31,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 4: [2023-04-29 11:37:31,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +55: [2023-04-29 11:37:31,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +60: [2023-04-29 11:37:31,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +54: [2023-04-29 11:37:31,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +52: [2023-04-29 11:37:31,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +45: [2023-04-29 11:37:31,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +48: [2023-04-29 11:37:31,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +48: [2023-04-29 11:37:31,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +60: [2023-04-29 11:37:31,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +48: [2023-04-29 11:37:31,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +48: [2023-04-29 11:37:31,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +21: [2023-04-29 11:37:31,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +21: [2023-04-29 11:37:31,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 4: [2023-04-29 11:37:31,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 4: [2023-04-29 11:37:31,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +52: [2023-04-29 11:37:31,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +33: [2023-04-29 11:37:31,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +33: [2023-04-29 11:37:31,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +52: [2023-04-29 11:37:31,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +23: [2023-04-29 11:37:31,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +21: [2023-04-29 11:37:31,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +54: [2023-04-29 11:37:31,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +37: [2023-04-29 11:37:31,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +54: [2023-04-29 11:37:31,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +54: [2023-04-29 11:37:31,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +23: [2023-04-29 11:37:31,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +55: [2023-04-29 11:37:31,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +60: [2023-04-29 11:37:31,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +60: [2023-04-29 11:37:31,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +60: [2023-04-29 11:37:31,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 4: [2023-04-29 11:37:31,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +60: [2023-04-29 11:37:31,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +45: [2023-04-29 11:37:31,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +34: [2023-04-29 11:37:31,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +34: [2023-04-29 11:37:31,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +25: [2023-04-29 11:37:31,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +21: [2023-04-29 11:37:31,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +25: [2023-04-29 11:37:31,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +23: [2023-04-29 11:37:31,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... + 4: [2023-04-29 11:37:31,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +52: [2023-04-29 11:37:31,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +29: [2023-04-29 11:37:31,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +29: [2023-04-29 11:37:31,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +29: [2023-04-29 11:37:31,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +29: [2023-04-29 11:37:31,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +34: [2023-04-29 11:37:31,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +27: [2023-04-29 11:37:31,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +27: [2023-04-29 11:37:31,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +27: [2023-04-29 11:37:31,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +27: [2023-04-29 11:37:31,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +34: [2023-04-29 11:37:31,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +50: [2023-04-29 11:37:31,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +28: [2023-04-29 11:37:31,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +60: [2023-04-29 11:37:31,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +34: [2023-04-29 11:37:31,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +25: [2023-04-29 11:37:31,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +21: [2023-04-29 11:37:31,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +34: [2023-04-29 11:37:31,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +25: [2023-04-29 11:37:31,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +34: [2023-04-29 11:37:31,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +34: [2023-04-29 11:37:31,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +60: [2023-04-29 11:37:31,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... + 4: [2023-04-29 11:37:31,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +27: [2023-04-29 11:37:31,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +47: [2023-04-29 11:37:31,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +27: [2023-04-29 11:37:31,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +33: [2023-04-29 11:37:31,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +28: [2023-04-29 11:37:31,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +27: [2023-04-29 11:37:31,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +27: [2023-04-29 11:37:31,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +28: [2023-04-29 11:37:31,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +33: [2023-04-29 11:37:31,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +33: [2023-04-29 11:37:31,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +55: [2023-04-29 11:37:31,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +57: [2023-04-29 11:37:31,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +57: [2023-04-29 11:37:31,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +28: [2023-04-29 11:37:31,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +34: [2023-04-29 11:37:31,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +50: [2023-04-29 11:37:31,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +22: [2023-04-29 11:37:31,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +45: [2023-04-29 11:37:31,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +43: [2023-04-29 11:37:31,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +43: [2023-04-29 11:37:31,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +43: [2023-04-29 11:37:31,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +47: [2023-04-29 11:37:31,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +43: [2023-04-29 11:37:31,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_35-model_01-model_states.pt. +55: [2023-04-29 11:37:31,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +55: [2023-04-29 11:37:31,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +47: [2023-04-29 11:37:31,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +44: [2023-04-29 11:37:31,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +44: [2023-04-29 11:37:31,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +55: [2023-04-29 11:37:31,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +47: [2023-04-29 11:37:31,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +28: [2023-04-29 11:37:31,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +55: [2023-04-29 11:37:31,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +55: [2023-04-29 11:37:31,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +44: [2023-04-29 11:37:31,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +44: [2023-04-29 11:37:31,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +34: [2023-04-29 11:37:31,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +34: [2023-04-29 11:37:31,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +10: [2023-04-29 11:37:31,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +28: [2023-04-29 11:37:31,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +45: [2023-04-29 11:37:31,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +10: [2023-04-29 11:37:31,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +37: [2023-04-29 11:37:31,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +10: [2023-04-29 11:37:31,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +37: [2023-04-29 11:37:31,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +34: [2023-04-29 11:37:31,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +54: [2023-04-29 11:37:31,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +57: [2023-04-29 11:37:31,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +57: [2023-04-29 11:37:31,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +22: [2023-04-29 11:37:31,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +22: [2023-04-29 11:37:31,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +10: [2023-04-29 11:37:31,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +45: [2023-04-29 11:37:31,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +47: [2023-04-29 11:37:31,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +47: [2023-04-29 11:37:31,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +22: [2023-04-29 11:37:31,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +54: [2023-04-29 11:37:31,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +52: [2023-04-29 11:37:31,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +55: [2023-04-29 11:37:31,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +12: [2023-04-29 11:37:31,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +22: [2023-04-29 11:37:31,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +58: [2023-04-29 11:37:31,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +58: [2023-04-29 11:37:31,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +58: [2023-04-29 11:37:31,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +58: [2023-04-29 11:37:31,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +11: [2023-04-29 11:37:31,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +11: [2023-04-29 11:37:31,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +11: [2023-04-29 11:37:31,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +11: [2023-04-29 11:37:31,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +22: [2023-04-29 11:37:31,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +22: [2023-04-29 11:37:31,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +54: [2023-04-29 11:37:31,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +52: [2023-04-29 11:37:31,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +33: [2023-04-29 11:37:31,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +33: [2023-04-29 11:37:31,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +33: [2023-04-29 11:37:31,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +33: [2023-04-29 11:37:31,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +28: [2023-04-29 11:37:31,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 3: [2023-04-29 11:37:31,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. + 3: [2023-04-29 11:37:31,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. + 3: [2023-04-29 11:37:31,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +48: [2023-04-29 11:37:31,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +48: [2023-04-29 11:37:31,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +47: [2023-04-29 11:37:31,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +12: [2023-04-29 11:37:31,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +48: [2023-04-29 11:37:31,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +48: [2023-04-29 11:37:31,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +38: [2023-04-29 11:37:31,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +22: [2023-04-29 11:37:31,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +46: [2023-04-29 11:37:31,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +46: [2023-04-29 11:37:31,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +46: [2023-04-29 11:37:31,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +46: [2023-04-29 11:37:31,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +38: [2023-04-29 11:37:31,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +28: [2023-04-29 11:37:31,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +37: [2023-04-29 11:37:31,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +29: [2023-04-29 11:37:31,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +29: [2023-04-29 11:37:31,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +29: [2023-04-29 11:37:31,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +45: [2023-04-29 11:37:31,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +33: [2023-04-29 11:37:31,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +47: [2023-04-29 11:37:31,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +33: [2023-04-29 11:37:31,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +12: [2023-04-29 11:37:31,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +12: [2023-04-29 11:37:31,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +46: [2023-04-29 11:37:31,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +46: [2023-04-29 11:37:31,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +29: [2023-04-29 11:37:31,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +33: [2023-04-29 11:37:31,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +12: [2023-04-29 11:37:31,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +38: [2023-04-29 11:37:31,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +38: [2023-04-29 11:37:31,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +46: [2023-04-29 11:37:31,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +46: [2023-04-29 11:37:31,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +38: [2023-04-29 11:37:31,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +54: [2023-04-29 11:37:31,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +12: [2023-04-29 11:37:31,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +12: [2023-04-29 11:37:31,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +12: [2023-04-29 11:37:31,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +56: [2023-04-29 11:37:31,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +26: [2023-04-29 11:37:31,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +26: [2023-04-29 11:37:31,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. + 1: [2023-04-29 11:37:31,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +57: [2023-04-29 11:37:31,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +57: [2023-04-29 11:37:31,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +38: [2023-04-29 11:37:31,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +31: [2023-04-29 11:37:31,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +46: [2023-04-29 11:37:31,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... + 1: [2023-04-29 11:37:31,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +54: [2023-04-29 11:37:31,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +38: [2023-04-29 11:37:31,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +59: [2023-04-29 11:37:31,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +43: [2023-04-29 11:37:31,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +26: [2023-04-29 11:37:31,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +40: [2023-04-29 11:37:31,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +26: [2023-04-29 11:37:31,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +57: [2023-04-29 11:37:31,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +43: [2023-04-29 11:37:31,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +43: [2023-04-29 11:37:31,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +43: [2023-04-29 11:37:31,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt... +55: [2023-04-29 11:37:31,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +55: [2023-04-29 11:37:31,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +55: [2023-04-29 11:37:31,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +55: [2023-04-29 11:37:31,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +46: [2023-04-29 11:37:31,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +57: [2023-04-29 11:37:31,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +19: [2023-04-29 11:37:31,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +19: [2023-04-29 11:37:31,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +31: [2023-04-29 11:37:31,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +61: [2023-04-29 11:37:31,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +59: [2023-04-29 11:37:31,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +38: [2023-04-29 11:37:31,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +61: [2023-04-29 11:37:31,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +19: [2023-04-29 11:37:31,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +50: [2023-04-29 11:37:31,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +50: [2023-04-29 11:37:31,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +59: [2023-04-29 11:37:31,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +50: [2023-04-29 11:37:31,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +19: [2023-04-29 11:37:31,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +50: [2023-04-29 11:37:31,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +58: [2023-04-29 11:37:31,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +59: [2023-04-29 11:37:31,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +31: [2023-04-29 11:37:31,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 3: [2023-04-29 11:37:31,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +21: [2023-04-29 11:37:31,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +21: [2023-04-29 11:37:31,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +21: [2023-04-29 11:37:31,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +58: [2023-04-29 11:37:31,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +46: [2023-04-29 11:37:31,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 4: [2023-04-29 11:37:31,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +59: [2023-04-29 11:37:31,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +58: [2023-04-29 11:37:31,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +21: [2023-04-29 11:37:31,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +58: [2023-04-29 11:37:31,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +11: [2023-04-29 11:37:31,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +11: [2023-04-29 11:37:31,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +11: [2023-04-29 11:37:31,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +61: [2023-04-29 11:37:31,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +59: [2023-04-29 11:37:31,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. + 3: [2023-04-29 11:37:31,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +31: [2023-04-29 11:37:31,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +56: [2023-04-29 11:37:31,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +31: [2023-04-29 11:37:31,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +24: [2023-04-29 11:37:31,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +24: [2023-04-29 11:37:31,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +24: [2023-04-29 11:37:31,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +24: [2023-04-29 11:37:31,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +11: [2023-04-29 11:37:31,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +56: [2023-04-29 11:37:31,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +40: [2023-04-29 11:37:31,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +40: [2023-04-29 11:37:31,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +40: [2023-04-29 11:37:31,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +54: [2023-04-29 11:37:31,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +54: [2023-04-29 11:37:31,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +46: [2023-04-29 11:37:31,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +34: [2023-04-29 11:37:31,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +59: [2023-04-29 11:37:31,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +31: [2023-04-29 11:37:31,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +25: [2023-04-29 11:37:31,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +46: [2023-04-29 11:37:31,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +21: [2023-04-29 11:37:31,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +54: [2023-04-29 11:37:31,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +21: [2023-04-29 11:37:31,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +21: [2023-04-29 11:37:31,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +21: [2023-04-29 11:37:31,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +31: [2023-04-29 11:37:31,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +31: [2023-04-29 11:37:31,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +59: [2023-04-29 11:37:31,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +61: [2023-04-29 11:37:31,272] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +34: [2023-04-29 11:37:31,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +61: [2023-04-29 11:37:31,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +56: [2023-04-29 11:37:31,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +61: [2023-04-29 11:37:31,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +46: [2023-04-29 11:37:31,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +25: [2023-04-29 11:37:31,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +61: [2023-04-29 11:37:31,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +61: [2023-04-29 11:37:31,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +25: [2023-04-29 11:37:31,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +54: [2023-04-29 11:37:31,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... + 9: [2023-04-29 11:37:31,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. + 9: [2023-04-29 11:37:31,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. + 9: [2023-04-29 11:37:31,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +30: [2023-04-29 11:37:31,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +30: [2023-04-29 11:37:31,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 9: [2023-04-29 11:37:31,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. + 4: [2023-04-29 11:37:31,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 4: [2023-04-29 11:37:31,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 4: [2023-04-29 11:37:31,278] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +15: [2023-04-29 11:37:31,278] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +15: [2023-04-29 11:37:31,278] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +15: [2023-04-29 11:37:31,278] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +15: [2023-04-29 11:37:31,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +30: [2023-04-29 11:37:31,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +26: [2023-04-29 11:37:31,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +25: [2023-04-29 11:37:31,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +34: [2023-04-29 11:37:31,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +30: [2023-04-29 11:37:31,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +26: [2023-04-29 11:37:31,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +56: [2023-04-29 11:37:31,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +40: [2023-04-29 11:37:31,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +46: [2023-04-29 11:37:31,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +26: [2023-04-29 11:37:31,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +30: [2023-04-29 11:37:31,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +25: [2023-04-29 11:37:31,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +30: [2023-04-29 11:37:31,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +54: [2023-04-29 11:37:31,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +27: [2023-04-29 11:37:31,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +32: [2023-04-29 11:37:31,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +32: [2023-04-29 11:37:31,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +32: [2023-04-29 11:37:31,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +32: [2023-04-29 11:37:31,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +34: [2023-04-29 11:37:31,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +44: [2023-04-29 11:37:31,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +44: [2023-04-29 11:37:31,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +49: [2023-04-29 11:37:31,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +49: [2023-04-29 11:37:31,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +30: [2023-04-29 11:37:31,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +25: [2023-04-29 11:37:31,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +34: [2023-04-29 11:37:31,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +34: [2023-04-29 11:37:31,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +26: [2023-04-29 11:37:31,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +44: [2023-04-29 11:37:31,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 2: [2023-04-29 11:37:31,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. + 2: [2023-04-29 11:37:31,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. + 2: [2023-04-29 11:37:31,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. + 2: [2023-04-29 11:37:31,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +44: [2023-04-29 11:37:31,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +30: [2023-04-29 11:37:31,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +49: [2023-04-29 11:37:31,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +49: [2023-04-29 11:37:31,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +54: [2023-04-29 11:37:31,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +25: [2023-04-29 11:37:31,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... + 4: [2023-04-29 11:37:31,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +19: [2023-04-29 11:37:31,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +50: [2023-04-29 11:37:31,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +19: [2023-04-29 11:37:31,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +19: [2023-04-29 11:37:31,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +27: [2023-04-29 11:37:31,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +16: [2023-04-29 11:37:31,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +16: [2023-04-29 11:37:31,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +44: [2023-04-29 11:37:31,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +16: [2023-04-29 11:37:31,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +50: [2023-04-29 11:37:31,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +46: [2023-04-29 11:37:31,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +16: [2023-04-29 11:37:31,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +25: [2023-04-29 11:37:31,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +44: [2023-04-29 11:37:31,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +44: [2023-04-29 11:37:31,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +61: [2023-04-29 11:37:31,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +10: [2023-04-29 11:37:31,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +10: [2023-04-29 11:37:31,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +44: [2023-04-29 11:37:31,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +44: [2023-04-29 11:37:31,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +44: [2023-04-29 11:37:31,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +27: [2023-04-29 11:37:31,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +27: [2023-04-29 11:37:31,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +24: [2023-04-29 11:37:31,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +54: [2023-04-29 11:37:31,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +50: [2023-04-29 11:37:31,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +54: [2023-04-29 11:37:31,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +24: [2023-04-29 11:37:31,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +61: [2023-04-29 11:37:31,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +19: [2023-04-29 11:37:31,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +24: [2023-04-29 11:37:31,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +44: [2023-04-29 11:37:31,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +10: [2023-04-29 11:37:31,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +50: [2023-04-29 11:37:31,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +24: [2023-04-29 11:37:31,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +10: [2023-04-29 11:37:31,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +44: [2023-04-29 11:37:31,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +10: [2023-04-29 11:37:31,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... + 3: [2023-04-29 11:37:31,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 3: [2023-04-29 11:37:31,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 3: [2023-04-29 11:37:31,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +44: [2023-04-29 11:37:31,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +44: [2023-04-29 11:37:31,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... + 3: [2023-04-29 11:37:31,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +62: [2023-04-29 11:37:31,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +56: [2023-04-29 11:37:31,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +62: [2023-04-29 11:37:31,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +62: [2023-04-29 11:37:31,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +56: [2023-04-29 11:37:31,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +40: [2023-04-29 11:37:31,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +62: [2023-04-29 11:37:31,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +40: [2023-04-29 11:37:31,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +54: [2023-04-29 11:37:31,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +40: [2023-04-29 11:37:31,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +54: [2023-04-29 11:37:31,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +61: [2023-04-29 11:37:31,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +44: [2023-04-29 11:37:31,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +34: [2023-04-29 11:37:31,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +10: [2023-04-29 11:37:31,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... + 3: [2023-04-29 11:37:31,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +44: [2023-04-29 11:37:31,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... + 3: [2023-04-29 11:37:31,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +37: [2023-04-29 11:37:31,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +37: [2023-04-29 11:37:31,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. + 3: [2023-04-29 11:37:31,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +37: [2023-04-29 11:37:31,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +37: [2023-04-29 11:37:31,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. + 7: [2023-04-29 11:37:31,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. + 7: [2023-04-29 11:37:31,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +56: [2023-04-29 11:37:31,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 9: [2023-04-29 11:37:31,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +10: [2023-04-29 11:37:31,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +34: [2023-04-29 11:37:31,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +34: [2023-04-29 11:37:31,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 9: [2023-04-29 11:37:31,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 7: [2023-04-29 11:37:31,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. + 7: [2023-04-29 11:37:31,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +54: [2023-04-29 11:37:31,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... + 9: [2023-04-29 11:37:31,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 9: [2023-04-29 11:37:31,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +61: [2023-04-29 11:37:31,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +62: [2023-04-29 11:37:31,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +62: [2023-04-29 11:37:31,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 4: [2023-04-29 11:37:31,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +29: [2023-04-29 11:37:31,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +27: [2023-04-29 11:37:31,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +61: [2023-04-29 11:37:31,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 4: [2023-04-29 11:37:31,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +49: [2023-04-29 11:37:31,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 4: [2023-04-29 11:37:31,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +15: [2023-04-29 11:37:31,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +15: [2023-04-29 11:37:31,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 2: [2023-04-29 11:37:31,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +34: [2023-04-29 11:37:31,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +46: [2023-04-29 11:37:31,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +46: [2023-04-29 11:37:31,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +29: [2023-04-29 11:37:31,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +29: [2023-04-29 11:37:31,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +34: [2023-04-29 11:37:31,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +62: [2023-04-29 11:37:31,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +32: [2023-04-29 11:37:31,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +15: [2023-04-29 11:37:31,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +15: [2023-04-29 11:37:31,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +61: [2023-04-29 11:37:31,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +34: [2023-04-29 11:37:31,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +61: [2023-04-29 11:37:31,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +61: [2023-04-29 11:37:31,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +34: [2023-04-29 11:37:31,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 2: [2023-04-29 11:37:31,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 2: [2023-04-29 11:37:31,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +10: [2023-04-29 11:37:31,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... + 2: [2023-04-29 11:37:31,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +62: [2023-04-29 11:37:31,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +32: [2023-04-29 11:37:31,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +32: [2023-04-29 11:37:31,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +49: [2023-04-29 11:37:31,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +29: [2023-04-29 11:37:31,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +49: [2023-04-29 11:37:31,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +29: [2023-04-29 11:37:31,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +49: [2023-04-29 11:37:31,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +29: [2023-04-29 11:37:31,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +62: [2023-04-29 11:37:31,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +62: [2023-04-29 11:37:31,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +29: [2023-04-29 11:37:31,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +32: [2023-04-29 11:37:31,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +16: [2023-04-29 11:37:31,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +16: [2023-04-29 11:37:31,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +41: [2023-04-29 11:37:31,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +41: [2023-04-29 11:37:31,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +27: [2023-04-29 11:37:31,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +41: [2023-04-29 11:37:31,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +41: [2023-04-29 11:37:31,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +27: [2023-04-29 11:37:31,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +27: [2023-04-29 11:37:31,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +55: [2023-04-29 11:37:31,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +55: [2023-04-29 11:37:31,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +16: [2023-04-29 11:37:31,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +29: [2023-04-29 11:37:31,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +34: [2023-04-29 11:37:31,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +43: [2023-04-29 11:37:31,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +62: [2023-04-29 11:37:31,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +16: [2023-04-29 11:37:31,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +55: [2023-04-29 11:37:31,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +55: [2023-04-29 11:37:31,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +46: [2023-04-29 11:37:31,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +46: [2023-04-29 11:37:31,326] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +55: [2023-04-29 11:37:31,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +55: [2023-04-29 11:37:31,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +20: [2023-04-29 11:37:31,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +20: [2023-04-29 11:37:31,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +20: [2023-04-29 11:37:31,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +20: [2023-04-29 11:37:31,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 7: [2023-04-29 11:37:31,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +62: [2023-04-29 11:37:31,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +37: [2023-04-29 11:37:31,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +43: [2023-04-29 11:37:31,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +43: [2023-04-29 11:37:31,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +43: [2023-04-29 11:37:31,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +55: [2023-04-29 11:37:31,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +43: [2023-04-29 11:37:31,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_00-model_states.pt. +55: [2023-04-29 11:37:31,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +11: [2023-04-29 11:37:31,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +20: [2023-04-29 11:37:31,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +20: [2023-04-29 11:37:31,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +11: [2023-04-29 11:37:31,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 7: [2023-04-29 11:37:31,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 7: [2023-04-29 11:37:31,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +20: [2023-04-29 11:37:31,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +20: [2023-04-29 11:37:31,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +62: [2023-04-29 11:37:31,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +21: [2023-04-29 11:37:31,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +43: [2023-04-29 11:37:31,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... + 7: [2023-04-29 11:37:31,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +46: [2023-04-29 11:37:31,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +62: [2023-04-29 11:37:31,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +43: [2023-04-29 11:37:31,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +43: [2023-04-29 11:37:31,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt... +62: [2023-04-29 11:37:31,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +34: [2023-04-29 11:37:31,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +11: [2023-04-29 11:37:31,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +11: [2023-04-29 11:37:31,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +62: [2023-04-29 11:37:31,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +37: [2023-04-29 11:37:31,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +11: [2023-04-29 11:37:31,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +11: [2023-04-29 11:37:31,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +34: [2023-04-29 11:37:31,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +46: [2023-04-29 11:37:31,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +56: [2023-04-29 11:37:31,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +56: [2023-04-29 11:37:31,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +56: [2023-04-29 11:37:31,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +56: [2023-04-29 11:37:31,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. + 3: [2023-04-29 11:37:31,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +37: [2023-04-29 11:37:31,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +21: [2023-04-29 11:37:31,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +37: [2023-04-29 11:37:31,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +11: [2023-04-29 11:37:31,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +11: [2023-04-29 11:37:31,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +11: [2023-04-29 11:37:31,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +40: [2023-04-29 11:37:31,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +40: [2023-04-29 11:37:31,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +40: [2023-04-29 11:37:31,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +40: [2023-04-29 11:37:31,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +11: [2023-04-29 11:37:31,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +41: [2023-04-29 11:37:31,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +21: [2023-04-29 11:37:31,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +21: [2023-04-29 11:37:31,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +30: [2023-04-29 11:37:31,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +30: [2023-04-29 11:37:31,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +44: [2023-04-29 11:37:31,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +11: [2023-04-29 11:37:31,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +41: [2023-04-29 11:37:31,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +11: [2023-04-29 11:37:31,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +41: [2023-04-29 11:37:31,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +26: [2023-04-29 11:37:31,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +11: [2023-04-29 11:37:31,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +19: [2023-04-29 11:37:31,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +11: [2023-04-29 11:37:31,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +11: [2023-04-29 11:37:31,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +11: [2023-04-29 11:37:31,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +30: [2023-04-29 11:37:31,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +19: [2023-04-29 11:37:31,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +41: [2023-04-29 11:37:31,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +30: [2023-04-29 11:37:31,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +58: [2023-04-29 11:37:31,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +58: [2023-04-29 11:37:31,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +26: [2023-04-29 11:37:31,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +58: [2023-04-29 11:37:31,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +58: [2023-04-29 11:37:31,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +58: [2023-04-29 11:37:31,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +58: [2023-04-29 11:37:31,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +58: [2023-04-29 11:37:31,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +26: [2023-04-29 11:37:31,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +58: [2023-04-29 11:37:31,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 5: [2023-04-29 11:37:31,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. + 5: [2023-04-29 11:37:31,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. + 5: [2023-04-29 11:37:31,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. + 5: [2023-04-29 11:37:31,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_11-model_01-model_states.pt. +36: [2023-04-29 11:37:31,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +36: [2023-04-29 11:37:31,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +36: [2023-04-29 11:37:31,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +19: [2023-04-29 11:37:31,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +36: [2023-04-29 11:37:31,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +45: [2023-04-29 11:37:31,354] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +45: [2023-04-29 11:37:31,354] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +30: [2023-04-29 11:37:31,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +30: [2023-04-29 11:37:31,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +30: [2023-04-29 11:37:31,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +19: [2023-04-29 11:37:31,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +45: [2023-04-29 11:37:31,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +30: [2023-04-29 11:37:31,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +45: [2023-04-29 11:37:31,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +26: [2023-04-29 11:37:31,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +26: [2023-04-29 11:37:31,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +26: [2023-04-29 11:37:31,357] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +46: [2023-04-29 11:37:31,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +26: [2023-04-29 11:37:31,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +46: [2023-04-29 11:37:31,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +29: [2023-04-29 11:37:31,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +29: [2023-04-29 11:37:31,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +29: [2023-04-29 11:37:31,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +58: [2023-04-29 11:37:31,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +58: [2023-04-29 11:37:31,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +29: [2023-04-29 11:37:31,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +50: [2023-04-29 11:37:31,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +58: [2023-04-29 11:37:31,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +58: [2023-04-29 11:37:31,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +24: [2023-04-29 11:37:31,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +51: [2023-04-29 11:37:31,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +51: [2023-04-29 11:37:31,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +51: [2023-04-29 11:37:31,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +51: [2023-04-29 11:37:31,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +58: [2023-04-29 11:37:31,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +44: [2023-04-29 11:37:31,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +58: [2023-04-29 11:37:31,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +58: [2023-04-29 11:37:31,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +39: [2023-04-29 11:37:31,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +58: [2023-04-29 11:37:31,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +39: [2023-04-29 11:37:31,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +39: [2023-04-29 11:37:31,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +39: [2023-04-29 11:37:31,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +44: [2023-04-29 11:37:31,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +50: [2023-04-29 11:37:31,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +50: [2023-04-29 11:37:31,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +49: [2023-04-29 11:37:31,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +19: [2023-04-29 11:37:31,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +26: [2023-04-29 11:37:31,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +21: [2023-04-29 11:37:31,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +24: [2023-04-29 11:37:31,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +29: [2023-04-29 11:37:31,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +44: [2023-04-29 11:37:31,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +50: [2023-04-29 11:37:31,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +29: [2023-04-29 11:37:31,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +24: [2023-04-29 11:37:31,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +29: [2023-04-29 11:37:31,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +13: [2023-04-29 11:37:31,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +13: [2023-04-29 11:37:31,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +13: [2023-04-29 11:37:31,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +29: [2023-04-29 11:37:31,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +39: [2023-04-29 11:37:31,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +13: [2023-04-29 11:37:31,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +49: [2023-04-29 11:37:31,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +61: [2023-04-29 11:37:31,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +39: [2023-04-29 11:37:31,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +39: [2023-04-29 11:37:31,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +56: [2023-04-29 11:37:31,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +39: [2023-04-29 11:37:31,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +56: [2023-04-29 11:37:31,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +50: [2023-04-29 11:37:31,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +50: [2023-04-29 11:37:31,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +19: [2023-04-29 11:37:31,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +19: [2023-04-29 11:37:31,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +24: [2023-04-29 11:37:31,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +56: [2023-04-29 11:37:31,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +56: [2023-04-29 11:37:31,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 9: [2023-04-29 11:37:31,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +40: [2023-04-29 11:37:31,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +40: [2023-04-29 11:37:31,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +63: [2023-04-29 11:37:31,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +63: [2023-04-29 11:37:31,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +63: [2023-04-29 11:37:31,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +63: [2023-04-29 11:37:31,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. + 3: [2023-04-29 11:37:31,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +57: [2023-04-29 11:37:31,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +57: [2023-04-29 11:37:31,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +61: [2023-04-29 11:37:31,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +57: [2023-04-29 11:37:31,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +61: [2023-04-29 11:37:31,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +40: [2023-04-29 11:37:31,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +57: [2023-04-29 11:37:31,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +24: [2023-04-29 11:37:31,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 3: [2023-04-29 11:37:31,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 3: [2023-04-29 11:37:31,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 9: [2023-04-29 11:37:31,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +21: [2023-04-29 11:37:31,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 9: [2023-04-29 11:37:31,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +50: [2023-04-29 11:37:31,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 2: [2023-04-29 11:37:31,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +21: [2023-04-29 11:37:31,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +40: [2023-04-29 11:37:31,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +24: [2023-04-29 11:37:31,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +19: [2023-04-29 11:37:31,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +15: [2023-04-29 11:37:31,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +15: [2023-04-29 11:37:31,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +21: [2023-04-29 11:37:31,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 9: [2023-04-29 11:37:31,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 9: [2023-04-29 11:37:31,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +61: [2023-04-29 11:37:31,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +61: [2023-04-29 11:37:31,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +44: [2023-04-29 11:37:31,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +61: [2023-04-29 11:37:31,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 2: [2023-04-29 11:37:31,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +30: [2023-04-29 11:37:31,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +30: [2023-04-29 11:37:31,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 9: [2023-04-29 11:37:31,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +24: [2023-04-29 11:37:31,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... + 5: [2023-04-29 11:37:31,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 5: [2023-04-29 11:37:31,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 5: [2023-04-29 11:37:31,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +24: [2023-04-29 11:37:31,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +15: [2023-04-29 11:37:31,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +16: [2023-04-29 11:37:31,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +16: [2023-04-29 11:37:31,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +15: [2023-04-29 11:37:31,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +62: [2023-04-29 11:37:31,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +62: [2023-04-29 11:37:31,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +49: [2023-04-29 11:37:31,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +15: [2023-04-29 11:37:31,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +30: [2023-04-29 11:37:31,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... + 2: [2023-04-29 11:37:31,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +48: [2023-04-29 11:37:31,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +36: [2023-04-29 11:37:31,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +48: [2023-04-29 11:37:31,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +48: [2023-04-29 11:37:31,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 9: [2023-04-29 11:37:31,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +30: [2023-04-29 11:37:31,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +36: [2023-04-29 11:37:31,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +48: [2023-04-29 11:37:31,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +48: [2023-04-29 11:37:31,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +48: [2023-04-29 11:37:31,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +48: [2023-04-29 11:37:31,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +48: [2023-04-29 11:37:31,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +36: [2023-04-29 11:37:31,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 9: [2023-04-29 11:37:31,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +50: [2023-04-29 11:37:31,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +45: [2023-04-29 11:37:31,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 5: [2023-04-29 11:37:31,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt... +45: [2023-04-29 11:37:31,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 2: [2023-04-29 11:37:31,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 2: [2023-04-29 11:37:31,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +20: [2023-04-29 11:37:31,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +15: [2023-04-29 11:37:31,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +49: [2023-04-29 11:37:31,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +61: [2023-04-29 11:37:31,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +61: [2023-04-29 11:37:31,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +49: [2023-04-29 11:37:31,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +15: [2023-04-29 11:37:31,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +45: [2023-04-29 11:37:31,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +16: [2023-04-29 11:37:31,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +51: [2023-04-29 11:37:31,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +51: [2023-04-29 11:37:31,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +16: [2023-04-29 11:37:31,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +45: [2023-04-29 11:37:31,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +48: [2023-04-29 11:37:31,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +36: [2023-04-29 11:37:31,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +16: [2023-04-29 11:37:31,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 2: [2023-04-29 11:37:31,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +48: [2023-04-29 11:37:31,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +30: [2023-04-29 11:37:31,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +48: [2023-04-29 11:37:31,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +15: [2023-04-29 11:37:31,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +13: [2023-04-29 11:37:31,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +30: [2023-04-29 11:37:31,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +44: [2023-04-29 11:37:31,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 2: [2023-04-29 11:37:31,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +49: [2023-04-29 11:37:31,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... + 2: [2023-04-29 11:37:31,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +22: [2023-04-29 11:37:31,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +22: [2023-04-29 11:37:31,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +22: [2023-04-29 11:37:31,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 7: [2023-04-29 11:37:31,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +44: [2023-04-29 11:37:31,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +49: [2023-04-29 11:37:31,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +22: [2023-04-29 11:37:31,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +30: [2023-04-29 11:37:31,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +48: [2023-04-29 11:37:31,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +37: [2023-04-29 11:37:31,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +48: [2023-04-29 11:37:31,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +48: [2023-04-29 11:37:31,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +48: [2023-04-29 11:37:31,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +30: [2023-04-29 11:37:31,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +48: [2023-04-29 11:37:31,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +52: [2023-04-29 11:37:31,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +52: [2023-04-29 11:37:31,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +51: [2023-04-29 11:37:31,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +51: [2023-04-29 11:37:31,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +16: [2023-04-29 11:37:31,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +44: [2023-04-29 11:37:31,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +42: [2023-04-29 11:37:31,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +42: [2023-04-29 11:37:31,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. + 3: [2023-04-29 11:37:31,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +17: [2023-04-29 11:37:31,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +17: [2023-04-29 11:37:31,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +17: [2023-04-29 11:37:31,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +17: [2023-04-29 11:37:31,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +52: [2023-04-29 11:37:31,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +52: [2023-04-29 11:37:31,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +42: [2023-04-29 11:37:31,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +42: [2023-04-29 11:37:31,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +16: [2023-04-29 11:37:31,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 7: [2023-04-29 11:37:31,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... + 8: [2023-04-29 11:37:31,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 8: [2023-04-29 11:37:31,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +20: [2023-04-29 11:37:31,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +49: [2023-04-29 11:37:31,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +22: [2023-04-29 11:37:31,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 7: [2023-04-29 11:37:31,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +37: [2023-04-29 11:37:31,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... + 8: [2023-04-29 11:37:31,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 8: [2023-04-29 11:37:31,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +22: [2023-04-29 11:37:31,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +13: [2023-04-29 11:37:31,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +22: [2023-04-29 11:37:31,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +57: [2023-04-29 11:37:31,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +13: [2023-04-29 11:37:31,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +22: [2023-04-29 11:37:31,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +17: [2023-04-29 11:37:31,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +17: [2023-04-29 11:37:31,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +17: [2023-04-29 11:37:31,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +17: [2023-04-29 11:37:31,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 7: [2023-04-29 11:37:31,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +13: [2023-04-29 11:37:31,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 7: [2023-04-29 11:37:31,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +63: [2023-04-29 11:37:31,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +16: [2023-04-29 11:37:31,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +20: [2023-04-29 11:37:31,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +20: [2023-04-29 11:37:31,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +63: [2023-04-29 11:37:31,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 8: [2023-04-29 11:37:31,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 8: [2023-04-29 11:37:31,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +57: [2023-04-29 11:37:31,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 8: [2023-04-29 11:37:31,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +37: [2023-04-29 11:37:31,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +11: [2023-04-29 11:37:31,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 8: [2023-04-29 11:37:31,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +63: [2023-04-29 11:37:31,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +57: [2023-04-29 11:37:31,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +57: [2023-04-29 11:37:31,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +63: [2023-04-29 11:37:31,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +41: [2023-04-29 11:37:31,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 7: [2023-04-29 11:37:31,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... + 0: [2023-04-29 11:37:31,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 0: [2023-04-29 11:37:31,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +62: [2023-04-29 11:37:31,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +37: [2023-04-29 11:37:31,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +62: [2023-04-29 11:37:31,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 0: [2023-04-29 11:37:31,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +20: [2023-04-29 11:37:31,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +11: [2023-04-29 11:37:31,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 7: [2023-04-29 11:37:31,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 0: [2023-04-29 11:37:31,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +41: [2023-04-29 11:37:31,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... + 0: [2023-04-29 11:37:31,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +11: [2023-04-29 11:37:31,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 0: [2023-04-29 11:37:31,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 0: [2023-04-29 11:37:31,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 0: [2023-04-29 11:37:31,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 7: [2023-04-29 11:37:31,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +41: [2023-04-29 11:37:31,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +62: [2023-04-29 11:37:31,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +37: [2023-04-29 11:37:31,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +37: [2023-04-29 11:37:31,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +41: [2023-04-29 11:37:31,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +11: [2023-04-29 11:37:31,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +41: [2023-04-29 11:37:31,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +42: [2023-04-29 11:37:31,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +62: [2023-04-29 11:37:31,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +20: [2023-04-29 11:37:31,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +58: [2023-04-29 11:37:31,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +58: [2023-04-29 11:37:31,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +37: [2023-04-29 11:37:31,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +37: [2023-04-29 11:37:31,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +39: [2023-04-29 11:37:31,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +52: [2023-04-29 11:37:31,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +41: [2023-04-29 11:37:31,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +52: [2023-04-29 11:37:31,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +29: [2023-04-29 11:37:31,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +42: [2023-04-29 11:37:31,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +52: [2023-04-29 11:37:31,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +42: [2023-04-29 11:37:31,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +41: [2023-04-29 11:37:31,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +53: [2023-04-29 11:37:31,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +53: [2023-04-29 11:37:31,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +53: [2023-04-29 11:37:31,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +53: [2023-04-29 11:37:31,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +39: [2023-04-29 11:37:31,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +58: [2023-04-29 11:37:31,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +58: [2023-04-29 11:37:31,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +52: [2023-04-29 11:37:31,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +20: [2023-04-29 11:37:31,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +42: [2023-04-29 11:37:31,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +56: [2023-04-29 11:37:31,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +56: [2023-04-29 11:37:31,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +40: [2023-04-29 11:37:31,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +11: [2023-04-29 11:37:31,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +53: [2023-04-29 11:37:31,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +20: [2023-04-29 11:37:31,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +62: [2023-04-29 11:37:31,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +41: [2023-04-29 11:37:31,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +11: [2023-04-29 11:37:31,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +40: [2023-04-29 11:37:31,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +40: [2023-04-29 11:37:31,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +29: [2023-04-29 11:37:31,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +29: [2023-04-29 11:37:31,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +29: [2023-04-29 11:37:31,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +53: [2023-04-29 11:37:31,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +40: [2023-04-29 11:37:31,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... + 0: [2023-04-29 11:37:31,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 0: [2023-04-29 11:37:31,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 0: [2023-04-29 11:37:31,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +53: [2023-04-29 11:37:31,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +53: [2023-04-29 11:37:31,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 6: [2023-04-29 11:37:31,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 6: [2023-04-29 11:37:31,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +62: [2023-04-29 11:37:31,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +56: [2023-04-29 11:37:31,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +56: [2023-04-29 11:37:31,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +56: [2023-04-29 11:37:31,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +36: [2023-04-29 11:37:31,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 0: [2023-04-29 11:37:31,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +40: [2023-04-29 11:37:31,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... + 6: [2023-04-29 11:37:31,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +47: [2023-04-29 11:37:31,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +47: [2023-04-29 11:37:31,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +39: [2023-04-29 11:37:31,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +39: [2023-04-29 11:37:31,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +47: [2023-04-29 11:37:31,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +40: [2023-04-29 11:37:31,442] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +62: [2023-04-29 11:37:31,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +56: [2023-04-29 11:37:31,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 5: [2023-04-29 11:37:31,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 6: [2023-04-29 11:37:31,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +11: [2023-04-29 11:37:31,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +47: [2023-04-29 11:37:31,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +62: [2023-04-29 11:37:31,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +30: [2023-04-29 11:37:31,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +62: [2023-04-29 11:37:31,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +36: [2023-04-29 11:37:31,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +56: [2023-04-29 11:37:31,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +40: [2023-04-29 11:37:31,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +45: [2023-04-29 11:37:31,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +36: [2023-04-29 11:37:31,447] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +27: [2023-04-29 11:37:31,448] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +27: [2023-04-29 11:37:31,448] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +27: [2023-04-29 11:37:31,448] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +56: [2023-04-29 11:37:31,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +27: [2023-04-29 11:37:31,448] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 5: [2023-04-29 11:37:31,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +48: [2023-04-29 11:37:31,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +35: [2023-04-29 11:37:31,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +35: [2023-04-29 11:37:31,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +62: [2023-04-29 11:37:31,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +60: [2023-04-29 11:37:31,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +60: [2023-04-29 11:37:31,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +30: [2023-04-29 11:37:31,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +36: [2023-04-29 11:37:31,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +35: [2023-04-29 11:37:31,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +35: [2023-04-29 11:37:31,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. + 5: [2023-04-29 11:37:31,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 5: [2023-04-29 11:37:31,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. + 5: [2023-04-29 11:37:31,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +40: [2023-04-29 11:37:31,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +45: [2023-04-29 11:37:31,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +53: [2023-04-29 11:37:31,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +53: [2023-04-29 11:37:31,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +62: [2023-04-29 11:37:31,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +36: [2023-04-29 11:37:31,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +53: [2023-04-29 11:37:31,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +60: [2023-04-29 11:37:31,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +60: [2023-04-29 11:37:31,453] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +11: [2023-04-29 11:37:31,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +29: [2023-04-29 11:37:31,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +62: [2023-04-29 11:37:31,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +30: [2023-04-29 11:37:31,453] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +30: [2023-04-29 11:37:31,453] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +62: [2023-04-29 11:37:31,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +39: [2023-04-29 11:37:31,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +36: [2023-04-29 11:37:31,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +45: [2023-04-29 11:37:31,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +53: [2023-04-29 11:37:31,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +48: [2023-04-29 11:37:31,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +58: [2023-04-29 11:37:31,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +58: [2023-04-29 11:37:31,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +22: [2023-04-29 11:37:31,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 5: [2023-04-29 11:37:31,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +39: [2023-04-29 11:37:31,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 5: [2023-04-29 11:37:31,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +30: [2023-04-29 11:37:31,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_00-model_states.pt. +30: [2023-04-29 11:37:31,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... + 5: [2023-04-29 11:37:31,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +36: [2023-04-29 11:37:31,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +17: [2023-04-29 11:37:31,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +45: [2023-04-29 11:37:31,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +45: [2023-04-29 11:37:31,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +48: [2023-04-29 11:37:31,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +30: [2023-04-29 11:37:31,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +45: [2023-04-29 11:37:31,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +48: [2023-04-29 11:37:31,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +18: [2023-04-29 11:37:31,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +18: [2023-04-29 11:37:31,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +57: [2023-04-29 11:37:31,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +58: [2023-04-29 11:37:31,462] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +18: [2023-04-29 11:37:31,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +32: [2023-04-29 11:37:31,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +32: [2023-04-29 11:37:31,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +32: [2023-04-29 11:37:31,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +32: [2023-04-29 11:37:31,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +32: [2023-04-29 11:37:31,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +32: [2023-04-29 11:37:31,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +32: [2023-04-29 11:37:31,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +18: [2023-04-29 11:37:31,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +32: [2023-04-29 11:37:31,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +30: [2023-04-29 11:37:31,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt... +45: [2023-04-29 11:37:31,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... + 8: [2023-04-29 11:37:31,464] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +29: [2023-04-29 11:37:31,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +45: [2023-04-29 11:37:31,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +29: [2023-04-29 11:37:31,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +29: [2023-04-29 11:37:31,466] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +58: [2023-04-29 11:37:31,466] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 0: [2023-04-29 11:37:31,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +57: [2023-04-29 11:37:31,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +36: [2023-04-29 11:37:31,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +18: [2023-04-29 11:37:31,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +18: [2023-04-29 11:37:31,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +32: [2023-04-29 11:37:31,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +47: [2023-04-29 11:37:31,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +32: [2023-04-29 11:37:31,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 8: [2023-04-29 11:37:31,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +22: [2023-04-29 11:37:31,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +22: [2023-04-29 11:37:31,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +22: [2023-04-29 11:37:31,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +32: [2023-04-29 11:37:31,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +18: [2023-04-29 11:37:31,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +32: [2023-04-29 11:37:31,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +17: [2023-04-29 11:37:31,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +17: [2023-04-29 11:37:31,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +17: [2023-04-29 11:37:31,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +32: [2023-04-29 11:37:31,470] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... + 6: [2023-04-29 11:37:31,470] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 6: [2023-04-29 11:37:31,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +32: [2023-04-29 11:37:31,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +32: [2023-04-29 11:37:31,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 0: [2023-04-29 11:37:31,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +63: [2023-04-29 11:37:31,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +63: [2023-04-29 11:37:31,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +63: [2023-04-29 11:37:31,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 0: [2023-04-29 11:37:31,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +47: [2023-04-29 11:37:31,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +39: [2023-04-29 11:37:31,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +18: [2023-04-29 11:37:31,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +39: [2023-04-29 11:37:31,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 6: [2023-04-29 11:37:31,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 6: [2023-04-29 11:37:31,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +32: [2023-04-29 11:37:31,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +48: [2023-04-29 11:37:31,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 8: [2023-04-29 11:37:31,473] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 0: [2023-04-29 11:37:31,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +57: [2023-04-29 11:37:31,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +57: [2023-04-29 11:37:31,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +47: [2023-04-29 11:37:31,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +47: [2023-04-29 11:37:31,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +63: [2023-04-29 11:37:31,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +63: [2023-04-29 11:37:31,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +63: [2023-04-29 11:37:31,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +63: [2023-04-29 11:37:31,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... + 8: [2023-04-29 11:37:31,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +62: [2023-04-29 11:37:31,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +57: [2023-04-29 11:37:31,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +35: [2023-04-29 11:37:31,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +35: [2023-04-29 11:37:31,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +27: [2023-04-29 11:37:31,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +27: [2023-04-29 11:37:31,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +27: [2023-04-29 11:37:31,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +38: [2023-04-29 11:37:31,479] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +38: [2023-04-29 11:37:31,479] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +27: [2023-04-29 11:37:31,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +60: [2023-04-29 11:37:31,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +63: [2023-04-29 11:37:31,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +60: [2023-04-29 11:37:31,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +35: [2023-04-29 11:37:31,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +57: [2023-04-29 11:37:31,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +53: [2023-04-29 11:37:31,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +57: [2023-04-29 11:37:31,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +38: [2023-04-29 11:37:31,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +38: [2023-04-29 11:37:31,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +35: [2023-04-29 11:37:31,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +17: [2023-04-29 11:37:31,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +57: [2023-04-29 11:37:31,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +60: [2023-04-29 11:37:31,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +53: [2023-04-29 11:37:31,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +17: [2023-04-29 11:37:31,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +48: [2023-04-29 11:37:31,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +48: [2023-04-29 11:37:31,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +53: [2023-04-29 11:37:31,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +22: [2023-04-29 11:37:31,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +60: [2023-04-29 11:37:31,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +18: [2023-04-29 11:37:31,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +18: [2023-04-29 11:37:31,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +17: [2023-04-29 11:37:31,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +17: [2023-04-29 11:37:31,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 0: [2023-04-29 11:37:31,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +17: [2023-04-29 11:37:31,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 8: [2023-04-29 11:37:31,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +52: [2023-04-29 11:37:31,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 0: [2023-04-29 11:37:31,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +53: [2023-04-29 11:37:31,493] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 8: [2023-04-29 11:37:31,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +48: [2023-04-29 11:37:31,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +18: [2023-04-29 11:37:31,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +18: [2023-04-29 11:37:31,495] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +24: [2023-04-29 11:37:31,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +24: [2023-04-29 11:37:31,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +22: [2023-04-29 11:37:31,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +52: [2023-04-29 11:37:31,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +47: [2023-04-29 11:37:31,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +47: [2023-04-29 11:37:31,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +47: [2023-04-29 11:37:31,499] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +47: [2023-04-29 11:37:31,499] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 0: [2023-04-29 11:37:31,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 0: [2023-04-29 11:37:31,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +24: [2023-04-29 11:37:31,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +24: [2023-04-29 11:37:31,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +22: [2023-04-29 11:37:31,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +22: [2023-04-29 11:37:31,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +17: [2023-04-29 11:37:31,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +52: [2023-04-29 11:37:31,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +53: [2023-04-29 11:37:31,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +24: [2023-04-29 11:37:31,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +24: [2023-04-29 11:37:31,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +52: [2023-04-29 11:37:31,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +36: [2023-04-29 11:37:31,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +36: [2023-04-29 11:37:31,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +47: [2023-04-29 11:37:31,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +41: [2023-04-29 11:37:31,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +41: [2023-04-29 11:37:31,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +41: [2023-04-29 11:37:31,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +41: [2023-04-29 11:37:31,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +47: [2023-04-29 11:37:31,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +31: [2023-04-29 11:37:31,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +31: [2023-04-29 11:37:31,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +31: [2023-04-29 11:37:31,505] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +36: [2023-04-29 11:37:31,505] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +47: [2023-04-29 11:37:31,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +31: [2023-04-29 11:37:31,505] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +17: [2023-04-29 11:37:31,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +36: [2023-04-29 11:37:31,505] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +24: [2023-04-29 11:37:31,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +24: [2023-04-29 11:37:31,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +47: [2023-04-29 11:37:31,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +52: [2023-04-29 11:37:31,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... + 8: [2023-04-29 11:37:31,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 8: [2023-04-29 11:37:31,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +41: [2023-04-29 11:37:31,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +20: [2023-04-29 11:37:31,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +20: [2023-04-29 11:37:31,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +20: [2023-04-29 11:37:31,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 2: [2023-04-29 11:37:31,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 2: [2023-04-29 11:37:31,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +20: [2023-04-29 11:37:31,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +52: [2023-04-29 11:37:31,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +36: [2023-04-29 11:37:31,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +36: [2023-04-29 11:37:31,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +31: [2023-04-29 11:37:31,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +31: [2023-04-29 11:37:31,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +38: [2023-04-29 11:37:31,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +17: [2023-04-29 11:37:31,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 8: [2023-04-29 11:37:31,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 8: [2023-04-29 11:37:31,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +38: [2023-04-29 11:37:31,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +31: [2023-04-29 11:37:31,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +52: [2023-04-29 11:37:31,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +31: [2023-04-29 11:37:31,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +36: [2023-04-29 11:37:31,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +17: [2023-04-29 11:37:31,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +13: [2023-04-29 11:37:31,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +13: [2023-04-29 11:37:31,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 8: [2023-04-29 11:37:31,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +13: [2023-04-29 11:37:31,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +41: [2023-04-29 11:37:31,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +41: [2023-04-29 11:37:31,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +41: [2023-04-29 11:37:31,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 8: [2023-04-29 11:37:31,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +13: [2023-04-29 11:37:31,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +13: [2023-04-29 11:37:31,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +13: [2023-04-29 11:37:31,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +13: [2023-04-29 11:37:31,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +13: [2023-04-29 11:37:31,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +18: [2023-04-29 11:37:31,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +18: [2023-04-29 11:37:31,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 2: [2023-04-29 11:37:31,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 2: [2023-04-29 11:37:31,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +36: [2023-04-29 11:37:31,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +38: [2023-04-29 11:37:31,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +12: [2023-04-29 11:37:31,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +12: [2023-04-29 11:37:31,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +12: [2023-04-29 11:37:31,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +12: [2023-04-29 11:37:31,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +38: [2023-04-29 11:37:31,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +23: [2023-04-29 11:37:31,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +23: [2023-04-29 11:37:31,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +23: [2023-04-29 11:37:31,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 2: [2023-04-29 11:37:31,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +23: [2023-04-29 11:37:31,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 2: [2023-04-29 11:37:31,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +42: [2023-04-29 11:37:31,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +42: [2023-04-29 11:37:31,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +26: [2023-04-29 11:37:31,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +26: [2023-04-29 11:37:31,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +26: [2023-04-29 11:37:31,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +26: [2023-04-29 11:37:31,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +13: [2023-04-29 11:37:31,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +52: [2023-04-29 11:37:31,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +13: [2023-04-29 11:37:31,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +13: [2023-04-29 11:37:31,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +10: [2023-04-29 11:37:31,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +42: [2023-04-29 11:37:31,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +10: [2023-04-29 11:37:31,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +42: [2023-04-29 11:37:31,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +10: [2023-04-29 11:37:31,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +42: [2023-04-29 11:37:31,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +42: [2023-04-29 11:37:31,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +42: [2023-04-29 11:37:31,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +10: [2023-04-29 11:37:31,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +42: [2023-04-29 11:37:31,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +19: [2023-04-29 11:37:31,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +19: [2023-04-29 11:37:31,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +19: [2023-04-29 11:37:31,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +17: [2023-04-29 11:37:31,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +12: [2023-04-29 11:37:31,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +19: [2023-04-29 11:37:31,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 2: [2023-04-29 11:37:31,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +23: [2023-04-29 11:37:31,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +17: [2023-04-29 11:37:31,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 2: [2023-04-29 11:37:31,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +23: [2023-04-29 11:37:31,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +17: [2023-04-29 11:37:31,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 0: [2023-04-29 11:37:31,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +12: [2023-04-29 11:37:31,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +13: [2023-04-29 11:37:31,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +23: [2023-04-29 11:37:31,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +23: [2023-04-29 11:37:31,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +12: [2023-04-29 11:37:31,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +53: [2023-04-29 11:37:31,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +53: [2023-04-29 11:37:31,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +53: [2023-04-29 11:37:31,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +13: [2023-04-29 11:37:31,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +34: [2023-04-29 11:37:31,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +34: [2023-04-29 11:37:31,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +13: [2023-04-29 11:37:31,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +13: [2023-04-29 11:37:31,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +34: [2023-04-29 11:37:31,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +34: [2023-04-29 11:37:31,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +42: [2023-04-29 11:37:31,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +42: [2023-04-29 11:37:31,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +13: [2023-04-29 11:37:31,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +12: [2023-04-29 11:37:31,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +26: [2023-04-29 11:37:31,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +26: [2023-04-29 11:37:31,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +26: [2023-04-29 11:37:31,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +26: [2023-04-29 11:37:31,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +42: [2023-04-29 11:37:31,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +19: [2023-04-29 11:37:31,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +19: [2023-04-29 11:37:31,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 0: [2023-04-29 11:37:31,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +10: [2023-04-29 11:37:31,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +19: [2023-04-29 11:37:31,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +19: [2023-04-29 11:37:31,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +10: [2023-04-29 11:37:31,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +42: [2023-04-29 11:37:31,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +10: [2023-04-29 11:37:31,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +10: [2023-04-29 11:37:31,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +18: [2023-04-29 11:37:31,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +18: [2023-04-29 11:37:31,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +42: [2023-04-29 11:37:31,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +53: [2023-04-29 11:37:31,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +28: [2023-04-29 11:37:31,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +28: [2023-04-29 11:37:31,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +42: [2023-04-29 11:37:31,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +28: [2023-04-29 11:37:31,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +28: [2023-04-29 11:37:31,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +42: [2023-04-29 11:37:31,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +42: [2023-04-29 11:37:31,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +50: [2023-04-29 11:37:31,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +50: [2023-04-29 11:37:31,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +50: [2023-04-29 11:37:31,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 0: [2023-04-29 11:37:31,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +50: [2023-04-29 11:37:31,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 0: [2023-04-29 11:37:31,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +32: [2023-04-29 11:37:31,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +32: [2023-04-29 11:37:31,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +46: [2023-04-29 11:37:31,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +46: [2023-04-29 11:37:31,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +28: [2023-04-29 11:37:31,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +46: [2023-04-29 11:37:31,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +28: [2023-04-29 11:37:31,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +46: [2023-04-29 11:37:31,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +18: [2023-04-29 11:37:31,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 4: [2023-04-29 11:37:31,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 4: [2023-04-29 11:37:31,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 4: [2023-04-29 11:37:31,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +50: [2023-04-29 11:37:31,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 4: [2023-04-29 11:37:31,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +28: [2023-04-29 11:37:31,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +28: [2023-04-29 11:37:31,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +47: [2023-04-29 11:37:31,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +20: [2023-04-29 11:37:31,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +50: [2023-04-29 11:37:31,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 8: [2023-04-29 11:37:31,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +50: [2023-04-29 11:37:31,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +50: [2023-04-29 11:37:31,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +32: [2023-04-29 11:37:31,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +32: [2023-04-29 11:37:31,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +47: [2023-04-29 11:37:31,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +47: [2023-04-29 11:37:31,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +20: [2023-04-29 11:37:31,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +20: [2023-04-29 11:37:31,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +44: [2023-04-29 11:37:31,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +44: [2023-04-29 11:37:31,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +20: [2023-04-29 11:37:31,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +44: [2023-04-29 11:37:31,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +44: [2023-04-29 11:37:31,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +55: [2023-04-29 11:37:31,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +55: [2023-04-29 11:37:31,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +55: [2023-04-29 11:37:31,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +27: [2023-04-29 11:37:31,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 8: [2023-04-29 11:37:31,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +55: [2023-04-29 11:37:31,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. + 8: [2023-04-29 11:37:31,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 8: [2023-04-29 11:37:31,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 0: [2023-04-29 11:37:31,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +47: [2023-04-29 11:37:31,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +59: [2023-04-29 11:37:31,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +59: [2023-04-29 11:37:31,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +27: [2023-04-29 11:37:31,551] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +27: [2023-04-29 11:37:31,551] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +27: [2023-04-29 11:37:31,551] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +27: [2023-04-29 11:37:31,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 0: [2023-04-29 11:37:31,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +34: [2023-04-29 11:37:31,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +34: [2023-04-29 11:37:31,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +27: [2023-04-29 11:37:31,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +59: [2023-04-29 11:37:31,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +59: [2023-04-29 11:37:31,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +39: [2023-04-29 11:37:31,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +39: [2023-04-29 11:37:31,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. + 0: [2023-04-29 11:37:31,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +27: [2023-04-29 11:37:31,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +27: [2023-04-29 11:37:31,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +53: [2023-04-29 11:37:31,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +53: [2023-04-29 11:37:31,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +39: [2023-04-29 11:37:31,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +53: [2023-04-29 11:37:31,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +39: [2023-04-29 11:37:31,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +18: [2023-04-29 11:37:31,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +18: [2023-04-29 11:37:31,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +27: [2023-04-29 11:37:31,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +27: [2023-04-29 11:37:31,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +27: [2023-04-29 11:37:31,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +27: [2023-04-29 11:37:31,558] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +27: [2023-04-29 11:37:31,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 0: [2023-04-29 11:37:31,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 0: [2023-04-29 11:37:31,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 0: [2023-04-29 11:37:31,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +27: [2023-04-29 11:37:31,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +34: [2023-04-29 11:37:31,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +34: [2023-04-29 11:37:31,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 4: [2023-04-29 11:37:31,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +27: [2023-04-29 11:37:31,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... + 4: [2023-04-29 11:37:31,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +46: [2023-04-29 11:37:31,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +46: [2023-04-29 11:37:31,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +47: [2023-04-29 11:37:31,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +46: [2023-04-29 11:37:31,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +61: [2023-04-29 11:37:31,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +61: [2023-04-29 11:37:31,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +61: [2023-04-29 11:37:31,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +61: [2023-04-29 11:37:31,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +53: [2023-04-29 11:37:31,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +32: [2023-04-29 11:37:31,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +32: [2023-04-29 11:37:31,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +24: [2023-04-29 11:37:31,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +24: [2023-04-29 11:37:31,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +27: [2023-04-29 11:37:31,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +46: [2023-04-29 11:37:31,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +18: [2023-04-29 11:37:31,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 0: [2023-04-29 11:37:31,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... + 0: [2023-04-29 11:37:31,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +47: [2023-04-29 11:37:31,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +53: [2023-04-29 11:37:31,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +53: [2023-04-29 11:37:31,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +54: [2023-04-29 11:37:31,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +54: [2023-04-29 11:37:31,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 4: [2023-04-29 11:37:31,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +18: [2023-04-29 11:37:31,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +36: [2023-04-29 11:37:31,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +24: [2023-04-29 11:37:31,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +53: [2023-04-29 11:37:31,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... + 1: [2023-04-29 11:37:31,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +38: [2023-04-29 11:37:31,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +38: [2023-04-29 11:37:31,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +43: [2023-04-29 11:37:31,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +43: [2023-04-29 11:37:31,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +43: [2023-04-29 11:37:31,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +21: [2023-04-29 11:37:31,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +21: [2023-04-29 11:37:31,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +21: [2023-04-29 11:37:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +43: [2023-04-29 11:37:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_36-model_01-model_states.pt. +21: [2023-04-29 11:37:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 1: [2023-04-29 11:37:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 4: [2023-04-29 11:37:31,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +33: [2023-04-29 11:37:31,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +33: [2023-04-29 11:37:31,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +33: [2023-04-29 11:37:31,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +21: [2023-04-29 11:37:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +54: [2023-04-29 11:37:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +33: [2023-04-29 11:37:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +21: [2023-04-29 11:37:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +47: [2023-04-29 11:37:31,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +54: [2023-04-29 11:37:31,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +53: [2023-04-29 11:37:31,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +24: [2023-04-29 11:37:31,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +53: [2023-04-29 11:37:31,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +53: [2023-04-29 11:37:31,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +44: [2023-04-29 11:37:31,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +44: [2023-04-29 11:37:31,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +44: [2023-04-29 11:37:31,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +38: [2023-04-29 11:37:31,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +38: [2023-04-29 11:37:31,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +47: [2023-04-29 11:37:31,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +21: [2023-04-29 11:37:31,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +21: [2023-04-29 11:37:31,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +12: [2023-04-29 11:37:31,574] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +55: [2023-04-29 11:37:31,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +55: [2023-04-29 11:37:31,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +32: [2023-04-29 11:37:31,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +44: [2023-04-29 11:37:31,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +54: [2023-04-29 11:37:31,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +55: [2023-04-29 11:37:31,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +47: [2023-04-29 11:37:31,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +47: [2023-04-29 11:37:31,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +54: [2023-04-29 11:37:31,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +55: [2023-04-29 11:37:31,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +54: [2023-04-29 11:37:31,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +53: [2023-04-29 11:37:31,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +38: [2023-04-29 11:37:31,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +31: [2023-04-29 11:37:31,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +31: [2023-04-29 11:37:31,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +54: [2023-04-29 11:37:31,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +38: [2023-04-29 11:37:31,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +32: [2023-04-29 11:37:31,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +38: [2023-04-29 11:37:31,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +21: [2023-04-29 11:37:31,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +36: [2023-04-29 11:37:31,577] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +60: [2023-04-29 11:37:31,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +60: [2023-04-29 11:37:31,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +31: [2023-04-29 11:37:31,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +17: [2023-04-29 11:37:31,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +41: [2023-04-29 11:37:31,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +17: [2023-04-29 11:37:31,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +59: [2023-04-29 11:37:31,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +31: [2023-04-29 11:37:31,579] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +36: [2023-04-29 11:37:31,579] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +21: [2023-04-29 11:37:31,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +47: [2023-04-29 11:37:31,579] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +39: [2023-04-29 11:37:31,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +60: [2023-04-29 11:37:31,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +60: [2023-04-29 11:37:31,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +60: [2023-04-29 11:37:31,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +60: [2023-04-29 11:37:31,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +38: [2023-04-29 11:37:31,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +60: [2023-04-29 11:37:31,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +60: [2023-04-29 11:37:31,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +23: [2023-04-29 11:37:31,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +31: [2023-04-29 11:37:31,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +21: [2023-04-29 11:37:31,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +21: [2023-04-29 11:37:31,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +59: [2023-04-29 11:37:31,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +59: [2023-04-29 11:37:31,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +14: [2023-04-29 11:37:31,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +14: [2023-04-29 11:37:31,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +14: [2023-04-29 11:37:31,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +14: [2023-04-29 11:37:31,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +13: [2023-04-29 11:37:31,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +13: [2023-04-29 11:37:31,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +17: [2023-04-29 11:37:31,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +17: [2023-04-29 11:37:31,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +38: [2023-04-29 11:37:31,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +59: [2023-04-29 11:37:31,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +31: [2023-04-29 11:37:31,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +31: [2023-04-29 11:37:31,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +31: [2023-04-29 11:37:31,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +60: [2023-04-29 11:37:31,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +60: [2023-04-29 11:37:31,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +23: [2023-04-29 11:37:31,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +60: [2023-04-29 11:37:31,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +41: [2023-04-29 11:37:31,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +60: [2023-04-29 11:37:31,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +39: [2023-04-29 11:37:31,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +18: [2023-04-29 11:37:31,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 2: [2023-04-29 11:37:31,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 2: [2023-04-29 11:37:31,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +52: [2023-04-29 11:37:31,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +52: [2023-04-29 11:37:31,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +39: [2023-04-29 11:37:31,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +54: [2023-04-29 11:37:31,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +54: [2023-04-29 11:37:31,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +52: [2023-04-29 11:37:31,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +60: [2023-04-29 11:37:31,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +52: [2023-04-29 11:37:31,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +54: [2023-04-29 11:37:31,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +39: [2023-04-29 11:37:31,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +54: [2023-04-29 11:37:31,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +24: [2023-04-29 11:37:31,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +41: [2023-04-29 11:37:31,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +38: [2023-04-29 11:37:31,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +12: [2023-04-29 11:37:31,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +36: [2023-04-29 11:37:31,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +19: [2023-04-29 11:37:31,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +19: [2023-04-29 11:37:31,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +18: [2023-04-29 11:37:31,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +18: [2023-04-29 11:37:31,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 2: [2023-04-29 11:37:31,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +60: [2023-04-29 11:37:31,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +60: [2023-04-29 11:37:31,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +49: [2023-04-29 11:37:31,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +49: [2023-04-29 11:37:31,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +13: [2023-04-29 11:37:31,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +60: [2023-04-29 11:37:31,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +23: [2023-04-29 11:37:31,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +23: [2023-04-29 11:37:31,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +26: [2023-04-29 11:37:31,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +49: [2023-04-29 11:37:31,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +24: [2023-04-29 11:37:31,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +42: [2023-04-29 11:37:31,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +42: [2023-04-29 11:37:31,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +49: [2023-04-29 11:37:31,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +61: [2023-04-29 11:37:31,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +42: [2023-04-29 11:37:31,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +52: [2023-04-29 11:37:31,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +61: [2023-04-29 11:37:31,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +61: [2023-04-29 11:37:31,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +52: [2023-04-29 11:37:31,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +26: [2023-04-29 11:37:31,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +17: [2023-04-29 11:37:31,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +61: [2023-04-29 11:37:31,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +35: [2023-04-29 11:37:31,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +35: [2023-04-29 11:37:31,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +52: [2023-04-29 11:37:31,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +38: [2023-04-29 11:37:31,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +10: [2023-04-29 11:37:31,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +10: [2023-04-29 11:37:31,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +10: [2023-04-29 11:37:31,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +10: [2023-04-29 11:37:31,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +12: [2023-04-29 11:37:31,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +17: [2023-04-29 11:37:31,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +12: [2023-04-29 11:37:31,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +13: [2023-04-29 11:37:31,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 2: [2023-04-29 11:37:31,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +52: [2023-04-29 11:37:31,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +35: [2023-04-29 11:37:31,594] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +38: [2023-04-29 11:37:31,594] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +35: [2023-04-29 11:37:31,594] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +35: [2023-04-29 11:37:31,594] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +24: [2023-04-29 11:37:31,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +35: [2023-04-29 11:37:31,594] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +35: [2023-04-29 11:37:31,594] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +19: [2023-04-29 11:37:31,594] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +19: [2023-04-29 11:37:31,594] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +35: [2023-04-29 11:37:31,594] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +38: [2023-04-29 11:37:31,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +20: [2023-04-29 11:37:31,594] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,594] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 1: [2023-04-29 11:37:31,594] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 1: [2023-04-29 11:37:31,594] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 6: [2023-04-29 11:37:31,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 6: [2023-04-29 11:37:31,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 6: [2023-04-29 11:37:31,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 6: [2023-04-29 11:37:31,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 6: [2023-04-29 11:37:31,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 6: [2023-04-29 11:37:31,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 6: [2023-04-29 11:37:31,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 6: [2023-04-29 11:37:31,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +18: [2023-04-29 11:37:31,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +18: [2023-04-29 11:37:31,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +47: [2023-04-29 11:37:31,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 5: [2023-04-29 11:37:31,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 5: [2023-04-29 11:37:31,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 5: [2023-04-29 11:37:31,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 5: [2023-04-29 11:37:31,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +25: [2023-04-29 11:37:31,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +25: [2023-04-29 11:37:31,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +25: [2023-04-29 11:37:31,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +49: [2023-04-29 11:37:31,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +25: [2023-04-29 11:37:31,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +49: [2023-04-29 11:37:31,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +49: [2023-04-29 11:37:31,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +42: [2023-04-29 11:37:31,597] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +28: [2023-04-29 11:37:31,597] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +36: [2023-04-29 11:37:31,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +38: [2023-04-29 11:37:31,597] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +18: [2023-04-29 11:37:31,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +21: [2023-04-29 11:37:31,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +49: [2023-04-29 11:37:31,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +24: [2023-04-29 11:37:31,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +21: [2023-04-29 11:37:31,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +17: [2023-04-29 11:37:31,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +26: [2023-04-29 11:37:31,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +35: [2023-04-29 11:37:31,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +35: [2023-04-29 11:37:31,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +33: [2023-04-29 11:37:31,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +20: [2023-04-29 11:37:31,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +28: [2023-04-29 11:37:31,600] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 6: [2023-04-29 11:37:31,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 6: [2023-04-29 11:37:31,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 6: [2023-04-29 11:37:31,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +17: [2023-04-29 11:37:31,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +41: [2023-04-29 11:37:31,601] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +35: [2023-04-29 11:37:31,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... + 6: [2023-04-29 11:37:31,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +43: [2023-04-29 11:37:31,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +25: [2023-04-29 11:37:31,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +35: [2023-04-29 11:37:31,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +43: [2023-04-29 11:37:31,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +43: [2023-04-29 11:37:31,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... + 6: [2023-04-29 11:37:31,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +43: [2023-04-29 11:37:31,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt... +35: [2023-04-29 11:37:31,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +26: [2023-04-29 11:37:31,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +35: [2023-04-29 11:37:31,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +35: [2023-04-29 11:37:31,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +33: [2023-04-29 11:37:31,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +28: [2023-04-29 11:37:31,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 6: [2023-04-29 11:37:31,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +12: [2023-04-29 11:37:31,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 5: [2023-04-29 11:37:31,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 5: [2023-04-29 11:37:31,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 5: [2023-04-29 11:37:31,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 5: [2023-04-29 11:37:31,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +33: [2023-04-29 11:37:31,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +38: [2023-04-29 11:37:31,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... + 6: [2023-04-29 11:37:31,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +33: [2023-04-29 11:37:31,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 6: [2023-04-29 11:37:31,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +25: [2023-04-29 11:37:31,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +25: [2023-04-29 11:37:31,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +47: [2023-04-29 11:37:31,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +25: [2023-04-29 11:37:31,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +18: [2023-04-29 11:37:31,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +36: [2023-04-29 11:37:31,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +41: [2023-04-29 11:37:31,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +35: [2023-04-29 11:37:31,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +28: [2023-04-29 11:37:31,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +23: [2023-04-29 11:37:31,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +14: [2023-04-29 11:37:31,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +38: [2023-04-29 11:37:31,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +21: [2023-04-29 11:37:31,607] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +13: [2023-04-29 11:37:31,607] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +36: [2023-04-29 11:37:31,607] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +47: [2023-04-29 11:37:31,607] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +50: [2023-04-29 11:37:31,608] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +63: [2023-04-29 11:37:31,608] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +63: [2023-04-29 11:37:31,608] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +63: [2023-04-29 11:37:31,608] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +13: [2023-04-29 11:37:31,609] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +21: [2023-04-29 11:37:31,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +14: [2023-04-29 11:37:31,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +63: [2023-04-29 11:37:31,610] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 8: [2023-04-29 11:37:31,611] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +14: [2023-04-29 11:37:31,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +14: [2023-04-29 11:37:31,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +23: [2023-04-29 11:37:31,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +31: [2023-04-29 11:37:31,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +55: [2023-04-29 11:37:31,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +55: [2023-04-29 11:37:31,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +47: [2023-04-29 11:37:31,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 8: [2023-04-29 11:37:31,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 2: [2023-04-29 11:37:31,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +31: [2023-04-29 11:37:31,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +31: [2023-04-29 11:37:31,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +31: [2023-04-29 11:37:31,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +63: [2023-04-29 11:37:31,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 3: [2023-04-29 11:37:31,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +63: [2023-04-29 11:37:31,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 3: [2023-04-29 11:37:31,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 2: [2023-04-29 11:37:31,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +19: [2023-04-29 11:37:31,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 2: [2023-04-29 11:37:31,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +50: [2023-04-29 11:37:31,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +31: [2023-04-29 11:37:31,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +63: [2023-04-29 11:37:31,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +20: [2023-04-29 11:37:31,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +63: [2023-04-29 11:37:31,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +51: [2023-04-29 11:37:31,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +20: [2023-04-29 11:37:31,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +27: [2023-04-29 11:37:31,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +51: [2023-04-29 11:37:31,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +51: [2023-04-29 11:37:31,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +55: [2023-04-29 11:37:31,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +55: [2023-04-29 11:37:31,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +55: [2023-04-29 11:37:31,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +31: [2023-04-29 11:37:31,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +51: [2023-04-29 11:37:31,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +51: [2023-04-29 11:37:31,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +51: [2023-04-29 11:37:31,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +51: [2023-04-29 11:37:31,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +23: [2023-04-29 11:37:31,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +31: [2023-04-29 11:37:31,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +51: [2023-04-29 11:37:31,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +42: [2023-04-29 11:37:31,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +50: [2023-04-29 11:37:31,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +50: [2023-04-29 11:37:31,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +23: [2023-04-29 11:37:31,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +31: [2023-04-29 11:37:31,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +26: [2023-04-29 11:37:31,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +54: [2023-04-29 11:37:31,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +54: [2023-04-29 11:37:31,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +13: [2023-04-29 11:37:31,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +36: [2023-04-29 11:37:31,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +19: [2023-04-29 11:37:31,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +20: [2023-04-29 11:37:31,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +15: [2023-04-29 11:37:31,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +15: [2023-04-29 11:37:31,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +10: [2023-04-29 11:37:31,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +55: [2023-04-29 11:37:31,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +12: [2023-04-29 11:37:31,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +11: [2023-04-29 11:37:31,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +11: [2023-04-29 11:37:31,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +10: [2023-04-29 11:37:31,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +11: [2023-04-29 11:37:31,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +19: [2023-04-29 11:37:31,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +41: [2023-04-29 11:37:31,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +11: [2023-04-29 11:37:31,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 3: [2023-04-29 11:37:31,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +10: [2023-04-29 11:37:31,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +54: [2023-04-29 11:37:31,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +26: [2023-04-29 11:37:31,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +13: [2023-04-29 11:37:31,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +42: [2023-04-29 11:37:31,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 7: [2023-04-29 11:37:31,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 7: [2023-04-29 11:37:31,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +20: [2023-04-29 11:37:31,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +15: [2023-04-29 11:37:31,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +10: [2023-04-29 11:37:31,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 7: [2023-04-29 11:37:31,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +20: [2023-04-29 11:37:31,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... + 1: [2023-04-29 11:37:31,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 7: [2023-04-29 11:37:31,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +15: [2023-04-29 11:37:31,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 3: [2023-04-29 11:37:31,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +19: [2023-04-29 11:37:31,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 8: [2023-04-29 11:37:31,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +28: [2023-04-29 11:37:31,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +12: [2023-04-29 11:37:31,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 2: [2023-04-29 11:37:31,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +12: [2023-04-29 11:37:31,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 9: [2023-04-29 11:37:31,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 9: [2023-04-29 11:37:31,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +51: [2023-04-29 11:37:31,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +51: [2023-04-29 11:37:31,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +27: [2023-04-29 11:37:31,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +55: [2023-04-29 11:37:31,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +47: [2023-04-29 11:37:31,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +18: [2023-04-29 11:37:31,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 4: [2023-04-29 11:37:31,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +27: [2023-04-29 11:37:31,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +27: [2023-04-29 11:37:31,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +42: [2023-04-29 11:37:31,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +55: [2023-04-29 11:37:31,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +54: [2023-04-29 11:37:31,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +28: [2023-04-29 11:37:31,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 8: [2023-04-29 11:37:31,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... + 8: [2023-04-29 11:37:31,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +11: [2023-04-29 11:37:31,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +11: [2023-04-29 11:37:31,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +11: [2023-04-29 11:37:31,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +41: [2023-04-29 11:37:31,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +51: [2023-04-29 11:37:31,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +11: [2023-04-29 11:37:31,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +20: [2023-04-29 11:37:31,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +51: [2023-04-29 11:37:31,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +18: [2023-04-29 11:37:31,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 9: [2023-04-29 11:37:31,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +51: [2023-04-29 11:37:31,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +15: [2023-04-29 11:37:31,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +15: [2023-04-29 11:37:31,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 7: [2023-04-29 11:37:31,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +16: [2023-04-29 11:37:31,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +16: [2023-04-29 11:37:31,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +16: [2023-04-29 11:37:31,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 9: [2023-04-29 11:37:31,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +16: [2023-04-29 11:37:31,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +50: [2023-04-29 11:37:31,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 4: [2023-04-29 11:37:31,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +26: [2023-04-29 11:37:31,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +15: [2023-04-29 11:37:31,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +51: [2023-04-29 11:37:31,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... + 8: [2023-04-29 11:37:31,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +38: [2023-04-29 11:37:31,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 4: [2023-04-29 11:37:31,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +15: [2023-04-29 11:37:31,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 7: [2023-04-29 11:37:31,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +51: [2023-04-29 11:37:31,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +51: [2023-04-29 11:37:31,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +28: [2023-04-29 11:37:31,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 7: [2023-04-29 11:37:31,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 9: [2023-04-29 11:37:31,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 9: [2023-04-29 11:37:31,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +37: [2023-04-29 11:37:31,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +37: [2023-04-29 11:37:31,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +37: [2023-04-29 11:37:31,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +57: [2023-04-29 11:37:31,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +57: [2023-04-29 11:37:31,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +41: [2023-04-29 11:37:31,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +37: [2023-04-29 11:37:31,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 8: [2023-04-29 11:37:31,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +42: [2023-04-29 11:37:31,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +56: [2023-04-29 11:37:31,633] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +56: [2023-04-29 11:37:31,633] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +56: [2023-04-29 11:37:31,633] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 7: [2023-04-29 11:37:31,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +56: [2023-04-29 11:37:31,633] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +18: [2023-04-29 11:37:31,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... + 4: [2023-04-29 11:37:31,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +26: [2023-04-29 11:37:31,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 9: [2023-04-29 11:37:31,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +57: [2023-04-29 11:37:31,634] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +57: [2023-04-29 11:37:31,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +59: [2023-04-29 11:37:31,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +59: [2023-04-29 11:37:31,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +59: [2023-04-29 11:37:31,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +59: [2023-04-29 11:37:31,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +28: [2023-04-29 11:37:31,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +18: [2023-04-29 11:37:31,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... + 9: [2023-04-29 11:37:31,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +16: [2023-04-29 11:37:31,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +37: [2023-04-29 11:37:31,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +14: [2023-04-29 11:37:31,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +14: [2023-04-29 11:37:31,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +57: [2023-04-29 11:37:31,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 8: [2023-04-29 11:37:31,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +57: [2023-04-29 11:37:31,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +16: [2023-04-29 11:37:31,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +16: [2023-04-29 11:37:31,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +56: [2023-04-29 11:37:31,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 4: [2023-04-29 11:37:31,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +43: [2023-04-29 11:37:31,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +43: [2023-04-29 11:37:31,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +21: [2023-04-29 11:37:31,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +37: [2023-04-29 11:37:31,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +43: [2023-04-29 11:37:31,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +56: [2023-04-29 11:37:31,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +16: [2023-04-29 11:37:31,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +37: [2023-04-29 11:37:31,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +43: [2023-04-29 11:37:31,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +56: [2023-04-29 11:37:31,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +57: [2023-04-29 11:37:31,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +56: [2023-04-29 11:37:31,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +57: [2023-04-29 11:37:31,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +37: [2023-04-29 11:37:31,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +49: [2023-04-29 11:37:31,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +49: [2023-04-29 11:37:31,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +49: [2023-04-29 11:37:31,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +49: [2023-04-29 11:37:31,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +14: [2023-04-29 11:37:31,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +14: [2023-04-29 11:37:31,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +59: [2023-04-29 11:37:31,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +59: [2023-04-29 11:37:31,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +59: [2023-04-29 11:37:31,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +60: [2023-04-29 11:37:31,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +59: [2023-04-29 11:37:31,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +14: [2023-04-29 11:37:31,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 4: [2023-04-29 11:37:31,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +27: [2023-04-29 11:37:31,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +43: [2023-04-29 11:37:31,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +14: [2023-04-29 11:37:31,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 4: [2023-04-29 11:37:31,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +59: [2023-04-29 11:37:31,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +55: [2023-04-29 11:37:31,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +43: [2023-04-29 11:37:31,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +43: [2023-04-29 11:37:31,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +43: [2023-04-29 11:37:31,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +55: [2023-04-29 11:37:31,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +14: [2023-04-29 11:37:31,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +52: [2023-04-29 11:37:31,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 4: [2023-04-29 11:37:31,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +14: [2023-04-29 11:37:31,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +39: [2023-04-29 11:37:31,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +39: [2023-04-29 11:37:31,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +22: [2023-04-29 11:37:31,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +22: [2023-04-29 11:37:31,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +22: [2023-04-29 11:37:31,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +54: [2023-04-29 11:37:31,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +22: [2023-04-29 11:37:31,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +59: [2023-04-29 11:37:31,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +55: [2023-04-29 11:37:31,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +38: [2023-04-29 11:37:31,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +38: [2023-04-29 11:37:31,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +38: [2023-04-29 11:37:31,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +38: [2023-04-29 11:37:31,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +55: [2023-04-29 11:37:31,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +59: [2023-04-29 11:37:31,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +60: [2023-04-29 11:37:31,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +60: [2023-04-29 11:37:31,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +56: [2023-04-29 11:37:31,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +56: [2023-04-29 11:37:31,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +39: [2023-04-29 11:37:31,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +59: [2023-04-29 11:37:31,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +50: [2023-04-29 11:37:31,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +55: [2023-04-29 11:37:31,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +39: [2023-04-29 11:37:31,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +54: [2023-04-29 11:37:31,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +61: [2023-04-29 11:37:31,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +27: [2023-04-29 11:37:31,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +56: [2023-04-29 11:37:31,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +56: [2023-04-29 11:37:31,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +39: [2023-04-29 11:37:31,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +58: [2023-04-29 11:37:31,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +58: [2023-04-29 11:37:31,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +58: [2023-04-29 11:37:31,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +58: [2023-04-29 11:37:31,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +55: [2023-04-29 11:37:31,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +27: [2023-04-29 11:37:31,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +27: [2023-04-29 11:37:31,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +50: [2023-04-29 11:37:31,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +50: [2023-04-29 11:37:31,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +59: [2023-04-29 11:37:31,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +61: [2023-04-29 11:37:31,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +59: [2023-04-29 11:37:31,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +61: [2023-04-29 11:37:31,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +60: [2023-04-29 11:37:31,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +55: [2023-04-29 11:37:31,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +61: [2023-04-29 11:37:31,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +59: [2023-04-29 11:37:31,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +52: [2023-04-29 11:37:31,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +40: [2023-04-29 11:37:31,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +35: [2023-04-29 11:37:31,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +40: [2023-04-29 11:37:31,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +40: [2023-04-29 11:37:31,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +40: [2023-04-29 11:37:31,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +39: [2023-04-29 11:37:31,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +52: [2023-04-29 11:37:31,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +41: [2023-04-29 11:37:31,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +41: [2023-04-29 11:37:31,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +21: [2023-04-29 11:37:31,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +21: [2023-04-29 11:37:31,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +54: [2023-04-29 11:37:31,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +54: [2023-04-29 11:37:31,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 6: [2023-04-29 11:37:31,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +21: [2023-04-29 11:37:31,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +59: [2023-04-29 11:37:31,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +25: [2023-04-29 11:37:31,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +29: [2023-04-29 11:37:31,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +29: [2023-04-29 11:37:31,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +29: [2023-04-29 11:37:31,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +29: [2023-04-29 11:37:31,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +12: [2023-04-29 11:37:31,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +12: [2023-04-29 11:37:31,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +12: [2023-04-29 11:37:31,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +12: [2023-04-29 11:37:31,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +55: [2023-04-29 11:37:31,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +40: [2023-04-29 11:37:31,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +50: [2023-04-29 11:37:31,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +50: [2023-04-29 11:37:31,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. + 6: [2023-04-29 11:37:31,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 6: [2023-04-29 11:37:31,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +35: [2023-04-29 11:37:31,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +41: [2023-04-29 11:37:31,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +41: [2023-04-29 11:37:31,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +52: [2023-04-29 11:37:31,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +21: [2023-04-29 11:37:31,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 6: [2023-04-29 11:37:31,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +62: [2023-04-29 11:37:31,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +49: [2023-04-29 11:37:31,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +62: [2023-04-29 11:37:31,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +62: [2023-04-29 11:37:31,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +62: [2023-04-29 11:37:31,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +21: [2023-04-29 11:37:31,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +40: [2023-04-29 11:37:31,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +60: [2023-04-29 11:37:31,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +29: [2023-04-29 11:37:31,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +40: [2023-04-29 11:37:31,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +29: [2023-04-29 11:37:31,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +14: [2023-04-29 11:37:31,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +29: [2023-04-29 11:37:31,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +61: [2023-04-29 11:37:31,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +61: [2023-04-29 11:37:31,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +61: [2023-04-29 11:37:31,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +61: [2023-04-29 11:37:31,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +40: [2023-04-29 11:37:31,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +29: [2023-04-29 11:37:31,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +49: [2023-04-29 11:37:31,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +50: [2023-04-29 11:37:31,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +49: [2023-04-29 11:37:31,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +50: [2023-04-29 11:37:31,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +21: [2023-04-29 11:37:31,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +43: [2023-04-29 11:37:31,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. + 5: [2023-04-29 11:37:31,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 5: [2023-04-29 11:37:31,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 5: [2023-04-29 11:37:31,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 5: [2023-04-29 11:37:31,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +39: [2023-04-29 11:37:31,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +40: [2023-04-29 11:37:31,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +40: [2023-04-29 11:37:31,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +25: [2023-04-29 11:37:31,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +25: [2023-04-29 11:37:31,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +25: [2023-04-29 11:37:31,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +14: [2023-04-29 11:37:31,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +22: [2023-04-29 11:37:31,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +40: [2023-04-29 11:37:31,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +40: [2023-04-29 11:37:31,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +43: [2023-04-29 11:37:31,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +21: [2023-04-29 11:37:31,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +21: [2023-04-29 11:37:31,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +52: [2023-04-29 11:37:31,677] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +54: [2023-04-29 11:37:31,678] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +43: [2023-04-29 11:37:31,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +46: [2023-04-29 11:37:31,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +63: [2023-04-29 11:37:31,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +46: [2023-04-29 11:37:31,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +35: [2023-04-29 11:37:31,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +49: [2023-04-29 11:37:31,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +49: [2023-04-29 11:37:31,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +55: [2023-04-29 11:37:31,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +11: [2023-04-29 11:37:31,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +31: [2023-04-29 11:37:31,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +22: [2023-04-29 11:37:31,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +46: [2023-04-29 11:37:31,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +46: [2023-04-29 11:37:31,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +35: [2023-04-29 11:37:31,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +46: [2023-04-29 11:37:31,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +46: [2023-04-29 11:37:31,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +46: [2023-04-29 11:37:31,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +46: [2023-04-29 11:37:31,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +38: [2023-04-29 11:37:31,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +22: [2023-04-29 11:37:31,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +43: [2023-04-29 11:37:31,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +34: [2023-04-29 11:37:31,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +34: [2023-04-29 11:37:31,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +60: [2023-04-29 11:37:31,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +60: [2023-04-29 11:37:31,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +54: [2023-04-29 11:37:31,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +22: [2023-04-29 11:37:31,683] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +43: [2023-04-29 11:37:31,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_00-model_states.pt. +39: [2023-04-29 11:37:31,683] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +38: [2023-04-29 11:37:31,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +43: [2023-04-29 11:37:31,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... +38: [2023-04-29 11:37:31,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +43: [2023-04-29 11:37:31,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... + 4: [2023-04-29 11:37:31,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 4: [2023-04-29 11:37:31,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 4: [2023-04-29 11:37:31,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +31: [2023-04-29 11:37:31,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... + 4: [2023-04-29 11:37:31,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +46: [2023-04-29 11:37:31,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +46: [2023-04-29 11:37:31,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +46: [2023-04-29 11:37:31,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +46: [2023-04-29 11:37:31,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +46: [2023-04-29 11:37:31,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +56: [2023-04-29 11:37:31,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +56: [2023-04-29 11:37:31,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +46: [2023-04-29 11:37:31,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +34: [2023-04-29 11:37:31,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +34: [2023-04-29 11:37:31,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +34: [2023-04-29 11:37:31,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +34: [2023-04-29 11:37:31,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +34: [2023-04-29 11:37:31,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +52: [2023-04-29 11:37:31,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +34: [2023-04-29 11:37:31,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +57: [2023-04-29 11:37:31,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +57: [2023-04-29 11:37:31,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +57: [2023-04-29 11:37:31,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +56: [2023-04-29 11:37:31,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +57: [2023-04-29 11:37:31,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +56: [2023-04-29 11:37:31,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +34: [2023-04-29 11:37:31,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +11: [2023-04-29 11:37:31,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +60: [2023-04-29 11:37:31,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +14: [2023-04-29 11:37:31,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +14: [2023-04-29 11:37:31,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +34: [2023-04-29 11:37:31,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +46: [2023-04-29 11:37:31,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +46: [2023-04-29 11:37:31,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +41: [2023-04-29 11:37:31,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +31: [2023-04-29 11:37:31,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +31: [2023-04-29 11:37:31,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +14: [2023-04-29 11:37:31,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +58: [2023-04-29 11:37:31,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +45: [2023-04-29 11:37:31,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +45: [2023-04-29 11:37:31,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +45: [2023-04-29 11:37:31,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +63: [2023-04-29 11:37:31,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +45: [2023-04-29 11:37:31,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +52: [2023-04-29 11:37:31,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +12: [2023-04-29 11:37:31,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +58: [2023-04-29 11:37:31,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +58: [2023-04-29 11:37:31,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +43: [2023-04-29 11:37:31,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt... + 1: [2023-04-29 11:37:31,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... + 4: [2023-04-29 11:37:31,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +25: [2023-04-29 11:37:31,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +49: [2023-04-29 11:37:31,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +49: [2023-04-29 11:37:31,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +49: [2023-04-29 11:37:31,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 4: [2023-04-29 11:37:31,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +11: [2023-04-29 11:37:31,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 4: [2023-04-29 11:37:31,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +31: [2023-04-29 11:37:31,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +34: [2023-04-29 11:37:31,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +41: [2023-04-29 11:37:31,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 4: [2023-04-29 11:37:31,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +34: [2023-04-29 11:37:31,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +35: [2023-04-29 11:37:31,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 7: [2023-04-29 11:37:31,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +63: [2023-04-29 11:37:31,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +58: [2023-04-29 11:37:31,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +54: [2023-04-29 11:37:31,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +50: [2023-04-29 11:37:31,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +50: [2023-04-29 11:37:31,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +51: [2023-04-29 11:37:31,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +35: [2023-04-29 11:37:31,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +14: [2023-04-29 11:37:31,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +14: [2023-04-29 11:37:31,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... + 6: [2023-04-29 11:37:31,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +54: [2023-04-29 11:37:31,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +12: [2023-04-29 11:37:31,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +14: [2023-04-29 11:37:31,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +12: [2023-04-29 11:37:31,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +31: [2023-04-29 11:37:31,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +12: [2023-04-29 11:37:31,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +31: [2023-04-29 11:37:31,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +34: [2023-04-29 11:37:31,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +52: [2023-04-29 11:37:31,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +21: [2023-04-29 11:37:31,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 6: [2023-04-29 11:37:31,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 6: [2023-04-29 11:37:31,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +63: [2023-04-29 11:37:31,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +34: [2023-04-29 11:37:31,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +54: [2023-04-29 11:37:31,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +21: [2023-04-29 11:37:31,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 6: [2023-04-29 11:37:31,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +55: [2023-04-29 11:37:31,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +34: [2023-04-29 11:37:31,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +34: [2023-04-29 11:37:31,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +15: [2023-04-29 11:37:31,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +15: [2023-04-29 11:37:31,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +11: [2023-04-29 11:37:31,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +31: [2023-04-29 11:37:31,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +54: [2023-04-29 11:37:31,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +49: [2023-04-29 11:37:31,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 9: [2023-04-29 11:37:31,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +37: [2023-04-29 11:37:31,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 9: [2023-04-29 11:37:31,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +15: [2023-04-29 11:37:31,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 7: [2023-04-29 11:37:31,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 7: [2023-04-29 11:37:31,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +41: [2023-04-29 11:37:31,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +54: [2023-04-29 11:37:31,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +41: [2023-04-29 11:37:31,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +55: [2023-04-29 11:37:31,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +51: [2023-04-29 11:37:31,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 9: [2023-04-29 11:37:31,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +51: [2023-04-29 11:37:31,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +25: [2023-04-29 11:37:31,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +15: [2023-04-29 11:37:31,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 7: [2023-04-29 11:37:31,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +55: [2023-04-29 11:37:31,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +14: [2023-04-29 11:37:31,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +63: [2023-04-29 11:37:31,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +62: [2023-04-29 11:37:31,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +40: [2023-04-29 11:37:31,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +40: [2023-04-29 11:37:31,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +62: [2023-04-29 11:37:31,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +43: [2023-04-29 11:37:31,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 5: [2023-04-29 11:37:31,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +55: [2023-04-29 11:37:31,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +54: [2023-04-29 11:37:31,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +25: [2023-04-29 11:37:31,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +21: [2023-04-29 11:37:31,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +57: [2023-04-29 11:37:31,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +50: [2023-04-29 11:37:31,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +16: [2023-04-29 11:37:31,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +16: [2023-04-29 11:37:31,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +16: [2023-04-29 11:37:31,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +62: [2023-04-29 11:37:31,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +62: [2023-04-29 11:37:31,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 5: [2023-04-29 11:37:31,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 5: [2023-04-29 11:37:31,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 5: [2023-04-29 11:37:31,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +25: [2023-04-29 11:37:31,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +57: [2023-04-29 11:37:31,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 9: [2023-04-29 11:37:31,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +11: [2023-04-29 11:37:31,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +59: [2023-04-29 11:37:31,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +59: [2023-04-29 11:37:31,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 3: [2023-04-29 11:37:31,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 3: [2023-04-29 11:37:31,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 3: [2023-04-29 11:37:31,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 3: [2023-04-29 11:37:31,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +50: [2023-04-29 11:37:31,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +44: [2023-04-29 11:37:31,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +44: [2023-04-29 11:37:31,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +44: [2023-04-29 11:37:31,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +44: [2023-04-29 11:37:31,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +44: [2023-04-29 11:37:31,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +44: [2023-04-29 11:37:31,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +44: [2023-04-29 11:37:31,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +44: [2023-04-29 11:37:31,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +21: [2023-04-29 11:37:31,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +40: [2023-04-29 11:37:31,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +54: [2023-04-29 11:37:31,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +40: [2023-04-29 11:37:31,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +56: [2023-04-29 11:37:31,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +56: [2023-04-29 11:37:31,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +56: [2023-04-29 11:37:31,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +59: [2023-04-29 11:37:31,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +59: [2023-04-29 11:37:31,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +11: [2023-04-29 11:37:31,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +16: [2023-04-29 11:37:31,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 3: [2023-04-29 11:37:31,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +35: [2023-04-29 11:37:31,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +21: [2023-04-29 11:37:31,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +21: [2023-04-29 11:37:31,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +45: [2023-04-29 11:37:31,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +44: [2023-04-29 11:37:31,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +45: [2023-04-29 11:37:31,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 7: [2023-04-29 11:37:31,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +44: [2023-04-29 11:37:31,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +63: [2023-04-29 11:37:31,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +57: [2023-04-29 11:37:31,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +14: [2023-04-29 11:37:31,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +44: [2023-04-29 11:37:31,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +43: [2023-04-29 11:37:31,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +44: [2023-04-29 11:37:31,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +44: [2023-04-29 11:37:31,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +56: [2023-04-29 11:37:31,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +44: [2023-04-29 11:37:31,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +37: [2023-04-29 11:37:31,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +37: [2023-04-29 11:37:31,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +44: [2023-04-29 11:37:31,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +57: [2023-04-29 11:37:31,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +44: [2023-04-29 11:37:31,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +57: [2023-04-29 11:37:31,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +54: [2023-04-29 11:37:31,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +35: [2023-04-29 11:37:31,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +11: [2023-04-29 11:37:31,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +63: [2023-04-29 11:37:31,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +21: [2023-04-29 11:37:31,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +63: [2023-04-29 11:37:31,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +63: [2023-04-29 11:37:31,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +45: [2023-04-29 11:37:31,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +45: [2023-04-29 11:37:31,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +57: [2023-04-29 11:37:31,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +54: [2023-04-29 11:37:31,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 3: [2023-04-29 11:37:31,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +63: [2023-04-29 11:37:31,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +43: [2023-04-29 11:37:31,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +14: [2023-04-29 11:37:31,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +14: [2023-04-29 11:37:31,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +51: [2023-04-29 11:37:31,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +57: [2023-04-29 11:37:31,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +33: [2023-04-29 11:37:31,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +33: [2023-04-29 11:37:31,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +33: [2023-04-29 11:37:31,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +33: [2023-04-29 11:37:31,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +63: [2023-04-29 11:37:31,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +33: [2023-04-29 11:37:31,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +33: [2023-04-29 11:37:31,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +33: [2023-04-29 11:37:31,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +33: [2023-04-29 11:37:31,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +36: [2023-04-29 11:37:31,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +36: [2023-04-29 11:37:31,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +36: [2023-04-29 11:37:31,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +36: [2023-04-29 11:37:31,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +20: [2023-04-29 11:37:31,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +20: [2023-04-29 11:37:31,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +43: [2023-04-29 11:37:31,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 9: [2023-04-29 11:37:31,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +30: [2023-04-29 11:37:31,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +45: [2023-04-29 11:37:31,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +54: [2023-04-29 11:37:31,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +45: [2023-04-29 11:37:31,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +30: [2023-04-29 11:37:31,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +51: [2023-04-29 11:37:31,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +45: [2023-04-29 11:37:31,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +45: [2023-04-29 11:37:31,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +43: [2023-04-29 11:37:31,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +30: [2023-04-29 11:37:31,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +63: [2023-04-29 11:37:31,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +30: [2023-04-29 11:37:31,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 9: [2023-04-29 11:37:31,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +37: [2023-04-29 11:37:31,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +11: [2023-04-29 11:37:31,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 9: [2023-04-29 11:37:31,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +49: [2023-04-29 11:37:31,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +20: [2023-04-29 11:37:31,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +20: [2023-04-29 11:37:31,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 3: [2023-04-29 11:37:31,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +15: [2023-04-29 11:37:31,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +15: [2023-04-29 11:37:31,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +49: [2023-04-29 11:37:31,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +49: [2023-04-29 11:37:31,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +15: [2023-04-29 11:37:31,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +57: [2023-04-29 11:37:31,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +33: [2023-04-29 11:37:31,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +33: [2023-04-29 11:37:31,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +33: [2023-04-29 11:37:31,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +33: [2023-04-29 11:37:31,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +14: [2023-04-29 11:37:31,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 7: [2023-04-29 11:37:31,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +29: [2023-04-29 11:37:31,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +37: [2023-04-29 11:37:31,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +15: [2023-04-29 11:37:31,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +30: [2023-04-29 11:37:31,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +33: [2023-04-29 11:37:31,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +45: [2023-04-29 11:37:31,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +45: [2023-04-29 11:37:31,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +30: [2023-04-29 11:37:31,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +20: [2023-04-29 11:37:31,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +33: [2023-04-29 11:37:31,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +20: [2023-04-29 11:37:31,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +45: [2023-04-29 11:37:31,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +33: [2023-04-29 11:37:31,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +20: [2023-04-29 11:37:31,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +33: [2023-04-29 11:37:31,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +55: [2023-04-29 11:37:31,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +20: [2023-04-29 11:37:31,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +45: [2023-04-29 11:37:31,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +30: [2023-04-29 11:37:31,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 7: [2023-04-29 11:37:31,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +30: [2023-04-29 11:37:31,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +57: [2023-04-29 11:37:31,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +49: [2023-04-29 11:37:31,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +57: [2023-04-29 11:37:31,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +40: [2023-04-29 11:37:31,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 7: [2023-04-29 11:37:31,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +22: [2023-04-29 11:37:31,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +55: [2023-04-29 11:37:31,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +51: [2023-04-29 11:37:31,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +49: [2023-04-29 11:37:31,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +51: [2023-04-29 11:37:31,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +16: [2023-04-29 11:37:31,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +59: [2023-04-29 11:37:31,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +59: [2023-04-29 11:37:31,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +16: [2023-04-29 11:37:31,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +37: [2023-04-29 11:37:31,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +56: [2023-04-29 11:37:31,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 9: [2023-04-29 11:37:31,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +16: [2023-04-29 11:37:31,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +55: [2023-04-29 11:37:31,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +29: [2023-04-29 11:37:31,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +29: [2023-04-29 11:37:31,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +29: [2023-04-29 11:37:31,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +56: [2023-04-29 11:37:31,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +22: [2023-04-29 11:37:31,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +56: [2023-04-29 11:37:31,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +22: [2023-04-29 11:37:31,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +56: [2023-04-29 11:37:31,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +59: [2023-04-29 11:37:31,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +59: [2023-04-29 11:37:31,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +57: [2023-04-29 11:37:31,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +37: [2023-04-29 11:37:31,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +37: [2023-04-29 11:37:31,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +37: [2023-04-29 11:37:31,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +43: [2023-04-29 11:37:31,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +46: [2023-04-29 11:37:31,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +22: [2023-04-29 11:37:31,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +63: [2023-04-29 11:37:31,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +16: [2023-04-29 11:37:31,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +22: [2023-04-29 11:37:31,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +49: [2023-04-29 11:37:31,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +63: [2023-04-29 11:37:31,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +37: [2023-04-29 11:37:31,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +14: [2023-04-29 11:37:31,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +50: [2023-04-29 11:37:31,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +12: [2023-04-29 11:37:31,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 4: [2023-04-29 11:37:31,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +37: [2023-04-29 11:37:31,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +29: [2023-04-29 11:37:31,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +43: [2023-04-29 11:37:31,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +14: [2023-04-29 11:37:31,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +63: [2023-04-29 11:37:31,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +63: [2023-04-29 11:37:31,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +22: [2023-04-29 11:37:31,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +22: [2023-04-29 11:37:31,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +14: [2023-04-29 11:37:31,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +36: [2023-04-29 11:37:31,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +36: [2023-04-29 11:37:31,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +49: [2023-04-29 11:37:31,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +46: [2023-04-29 11:37:31,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +51: [2023-04-29 11:37:31,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +43: [2023-04-29 11:37:31,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +12: [2023-04-29 11:37:31,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +34: [2023-04-29 11:37:31,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +34: [2023-04-29 11:37:31,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +40: [2023-04-29 11:37:31,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +56: [2023-04-29 11:37:31,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +56: [2023-04-29 11:37:31,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +41: [2023-04-29 11:37:31,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +41: [2023-04-29 11:37:31,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +36: [2023-04-29 11:37:31,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +22: [2023-04-29 11:37:31,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +36: [2023-04-29 11:37:31,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +46: [2023-04-29 11:37:31,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +46: [2023-04-29 11:37:31,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +23: [2023-04-29 11:37:31,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +23: [2023-04-29 11:37:31,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +23: [2023-04-29 11:37:31,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +23: [2023-04-29 11:37:31,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +50: [2023-04-29 11:37:31,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +57: [2023-04-29 11:37:31,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +12: [2023-04-29 11:37:31,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +56: [2023-04-29 11:37:31,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +56: [2023-04-29 11:37:31,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +56: [2023-04-29 11:37:31,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +56: [2023-04-29 11:37:31,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +12: [2023-04-29 11:37:31,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +37: [2023-04-29 11:37:31,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 4: [2023-04-29 11:37:31,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 4: [2023-04-29 11:37:31,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 4: [2023-04-29 11:37:31,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +50: [2023-04-29 11:37:31,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +48: [2023-04-29 11:37:31,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +48: [2023-04-29 11:37:31,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +48: [2023-04-29 11:37:31,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +41: [2023-04-29 11:37:31,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +41: [2023-04-29 11:37:31,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +48: [2023-04-29 11:37:31,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +41: [2023-04-29 11:37:31,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +50: [2023-04-29 11:37:31,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +40: [2023-04-29 11:37:31,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +40: [2023-04-29 11:37:31,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +12: [2023-04-29 11:37:31,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +12: [2023-04-29 11:37:31,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +34: [2023-04-29 11:37:31,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +49: [2023-04-29 11:37:31,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +34: [2023-04-29 11:37:31,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +56: [2023-04-29 11:37:31,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +56: [2023-04-29 11:37:31,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +26: [2023-04-29 11:37:31,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +26: [2023-04-29 11:37:31,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +26: [2023-04-29 11:37:31,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +41: [2023-04-29 11:37:31,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +26: [2023-04-29 11:37:31,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +12: [2023-04-29 11:37:31,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +49: [2023-04-29 11:37:31,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +40: [2023-04-29 11:37:31,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +40: [2023-04-29 11:37:31,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +46: [2023-04-29 11:37:31,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +37: [2023-04-29 11:37:31,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +12: [2023-04-29 11:37:31,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... + 8: [2023-04-29 11:37:31,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 8: [2023-04-29 11:37:31,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 8: [2023-04-29 11:37:31,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 8: [2023-04-29 11:37:31,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +40: [2023-04-29 11:37:31,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +28: [2023-04-29 11:37:31,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +28: [2023-04-29 11:37:31,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +28: [2023-04-29 11:37:31,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 9: [2023-04-29 11:37:31,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 9: [2023-04-29 11:37:31,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 2: [2023-04-29 11:37:31,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 2: [2023-04-29 11:37:31,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 9: [2023-04-29 11:37:31,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +49: [2023-04-29 11:37:31,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... + 2: [2023-04-29 11:37:31,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 2: [2023-04-29 11:37:31,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +28: [2023-04-29 11:37:31,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 9: [2023-04-29 11:37:31,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +15: [2023-04-29 11:37:31,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +15: [2023-04-29 11:37:31,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +15: [2023-04-29 11:37:31,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +15: [2023-04-29 11:37:31,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +49: [2023-04-29 11:37:31,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +29: [2023-04-29 11:37:31,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +29: [2023-04-29 11:37:31,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +62: [2023-04-29 11:37:31,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +62: [2023-04-29 11:37:31,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +40: [2023-04-29 11:37:31,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +41: [2023-04-29 11:37:31,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 4: [2023-04-29 11:37:31,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 8: [2023-04-29 11:37:31,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +44: [2023-04-29 11:37:31,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 8: [2023-04-29 11:37:31,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 8: [2023-04-29 11:37:31,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +40: [2023-04-29 11:37:31,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... + 8: [2023-04-29 11:37:31,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +32: [2023-04-29 11:37:31,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +32: [2023-04-29 11:37:31,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +32: [2023-04-29 11:37:31,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +29: [2023-04-29 11:37:31,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +32: [2023-04-29 11:37:31,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +34: [2023-04-29 11:37:31,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +50: [2023-04-29 11:37:31,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +34: [2023-04-29 11:37:31,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +17: [2023-04-29 11:37:31,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +17: [2023-04-29 11:37:31,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +17: [2023-04-29 11:37:31,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +17: [2023-04-29 11:37:31,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +45: [2023-04-29 11:37:31,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +44: [2023-04-29 11:37:31,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +37: [2023-04-29 11:37:31,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +62: [2023-04-29 11:37:31,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +44: [2023-04-29 11:37:31,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +44: [2023-04-29 11:37:31,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +62: [2023-04-29 11:37:31,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +37: [2023-04-29 11:37:31,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +37: [2023-04-29 11:37:31,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +46: [2023-04-29 11:37:31,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +62: [2023-04-29 11:37:31,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +62: [2023-04-29 11:37:31,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +41: [2023-04-29 11:37:31,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +50: [2023-04-29 11:37:31,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +46: [2023-04-29 11:37:31,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +46: [2023-04-29 11:37:31,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +45: [2023-04-29 11:37:31,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +45: [2023-04-29 11:37:31,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +17: [2023-04-29 11:37:31,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +17: [2023-04-29 11:37:31,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +61: [2023-04-29 11:37:31,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +61: [2023-04-29 11:37:31,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +61: [2023-04-29 11:37:31,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +50: [2023-04-29 11:37:31,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +61: [2023-04-29 11:37:31,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +17: [2023-04-29 11:37:31,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +17: [2023-04-29 11:37:31,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +23: [2023-04-29 11:37:31,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +23: [2023-04-29 11:37:31,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +23: [2023-04-29 11:37:31,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +62: [2023-04-29 11:37:31,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +33: [2023-04-29 11:37:31,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +62: [2023-04-29 11:37:31,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... + 4: [2023-04-29 11:37:31,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +57: [2023-04-29 11:37:31,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +50: [2023-04-29 11:37:31,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +23: [2023-04-29 11:37:31,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +45: [2023-04-29 11:37:31,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +48: [2023-04-29 11:37:31,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 4: [2023-04-29 11:37:31,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 4: [2023-04-29 11:37:31,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +61: [2023-04-29 11:37:31,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +61: [2023-04-29 11:37:31,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +61: [2023-04-29 11:37:31,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +61: [2023-04-29 11:37:31,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +48: [2023-04-29 11:37:31,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +33: [2023-04-29 11:37:31,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +33: [2023-04-29 11:37:31,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +42: [2023-04-29 11:37:31,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +42: [2023-04-29 11:37:31,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +42: [2023-04-29 11:37:31,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. + 2: [2023-04-29 11:37:31,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +30: [2023-04-29 11:37:31,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +42: [2023-04-29 11:37:31,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. + 3: [2023-04-29 11:37:31,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +20: [2023-04-29 11:37:31,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +19: [2023-04-29 11:37:31,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +19: [2023-04-29 11:37:31,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +45: [2023-04-29 11:37:31,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +45: [2023-04-29 11:37:31,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +57: [2023-04-29 11:37:31,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +48: [2023-04-29 11:37:31,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +48: [2023-04-29 11:37:31,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +20: [2023-04-29 11:37:31,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +20: [2023-04-29 11:37:31,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +20: [2023-04-29 11:37:31,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +26: [2023-04-29 11:37:31,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +45: [2023-04-29 11:37:31,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +30: [2023-04-29 11:37:31,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +57: [2023-04-29 11:37:31,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +57: [2023-04-29 11:37:31,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +45: [2023-04-29 11:37:31,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +40: [2023-04-29 11:37:31,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +34: [2023-04-29 11:37:31,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +19: [2023-04-29 11:37:31,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +34: [2023-04-29 11:37:31,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +19: [2023-04-29 11:37:31,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +28: [2023-04-29 11:37:31,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +33: [2023-04-29 11:37:31,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 3: [2023-04-29 11:37:31,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... + 2: [2023-04-29 11:37:31,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 2: [2023-04-29 11:37:31,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +25: [2023-04-29 11:37:31,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +25: [2023-04-29 11:37:31,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 2: [2023-04-29 11:37:31,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +40: [2023-04-29 11:37:31,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +40: [2023-04-29 11:37:31,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +32: [2023-04-29 11:37:31,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +26: [2023-04-29 11:37:31,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 9: [2023-04-29 11:37:31,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +26: [2023-04-29 11:37:31,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +26: [2023-04-29 11:37:31,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +15: [2023-04-29 11:37:31,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 9: [2023-04-29 11:37:31,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +28: [2023-04-29 11:37:31,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +45: [2023-04-29 11:37:31,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +15: [2023-04-29 11:37:31,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +28: [2023-04-29 11:37:31,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +57: [2023-04-29 11:37:31,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +28: [2023-04-29 11:37:31,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +25: [2023-04-29 11:37:31,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +57: [2023-04-29 11:37:31,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +25: [2023-04-29 11:37:31,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +44: [2023-04-29 11:37:31,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 9: [2023-04-29 11:37:31,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +24: [2023-04-29 11:37:31,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +24: [2023-04-29 11:37:31,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +32: [2023-04-29 11:37:31,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +32: [2023-04-29 11:37:31,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +57: [2023-04-29 11:37:31,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 9: [2023-04-29 11:37:31,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +45: [2023-04-29 11:37:31,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +30: [2023-04-29 11:37:31,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +32: [2023-04-29 11:37:31,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +40: [2023-04-29 11:37:31,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +22: [2023-04-29 11:37:31,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +15: [2023-04-29 11:37:31,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +15: [2023-04-29 11:37:31,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +22: [2023-04-29 11:37:31,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +22: [2023-04-29 11:37:31,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +11: [2023-04-29 11:37:31,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +11: [2023-04-29 11:37:31,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +22: [2023-04-29 11:37:31,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +44: [2023-04-29 11:37:31,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 7: [2023-04-29 11:37:31,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 7: [2023-04-29 11:37:31,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +44: [2023-04-29 11:37:31,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +44: [2023-04-29 11:37:31,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 3: [2023-04-29 11:37:31,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +24: [2023-04-29 11:37:31,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +40: [2023-04-29 11:37:31,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +24: [2023-04-29 11:37:31,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +30: [2023-04-29 11:37:31,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +45: [2023-04-29 11:37:31,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +11: [2023-04-29 11:37:31,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +11: [2023-04-29 11:37:31,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +57: [2023-04-29 11:37:31,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +63: [2023-04-29 11:37:31,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 7: [2023-04-29 11:37:31,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +10: [2023-04-29 11:37:31,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 7: [2023-04-29 11:37:31,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +10: [2023-04-29 11:37:31,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +10: [2023-04-29 11:37:31,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +10: [2023-04-29 11:37:31,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +22: [2023-04-29 11:37:31,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +22: [2023-04-29 11:37:31,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +22: [2023-04-29 11:37:31,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +36: [2023-04-29 11:37:31,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +22: [2023-04-29 11:37:31,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +33: [2023-04-29 11:37:31,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +45: [2023-04-29 11:37:31,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +40: [2023-04-29 11:37:31,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... + 3: [2023-04-29 11:37:31,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... + 3: [2023-04-29 11:37:31,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +63: [2023-04-29 11:37:31,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +63: [2023-04-29 11:37:31,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +63: [2023-04-29 11:37:31,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +42: [2023-04-29 11:37:31,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +40: [2023-04-29 11:37:31,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +20: [2023-04-29 11:37:31,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +30: [2023-04-29 11:37:31,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +36: [2023-04-29 11:37:31,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +36: [2023-04-29 11:37:31,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +63: [2023-04-29 11:37:31,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +63: [2023-04-29 11:37:31,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +33: [2023-04-29 11:37:31,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +33: [2023-04-29 11:37:31,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +20: [2023-04-29 11:37:31,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +36: [2023-04-29 11:37:31,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +30: [2023-04-29 11:37:31,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +18: [2023-04-29 11:37:31,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +18: [2023-04-29 11:37:31,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +18: [2023-04-29 11:37:31,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +63: [2023-04-29 11:37:31,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +18: [2023-04-29 11:37:31,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +37: [2023-04-29 11:37:31,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +42: [2023-04-29 11:37:31,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +36: [2023-04-29 11:37:31,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +19: [2023-04-29 11:37:31,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +36: [2023-04-29 11:37:31,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +30: [2023-04-29 11:37:31,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +30: [2023-04-29 11:37:31,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +19: [2023-04-29 11:37:31,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +42: [2023-04-29 11:37:31,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +45: [2023-04-29 11:37:31,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +30: [2023-04-29 11:37:31,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +63: [2023-04-29 11:37:31,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +30: [2023-04-29 11:37:31,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +45: [2023-04-29 11:37:31,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +20: [2023-04-29 11:37:31,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +20: [2023-04-29 11:37:31,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +19: [2023-04-29 11:37:31,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +47: [2023-04-29 11:37:31,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +47: [2023-04-29 11:37:31,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +36: [2023-04-29 11:37:31,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +33: [2023-04-29 11:37:31,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +25: [2023-04-29 11:37:31,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +25: [2023-04-29 11:37:31,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +42: [2023-04-29 11:37:31,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +19: [2023-04-29 11:37:31,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +18: [2023-04-29 11:37:31,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +47: [2023-04-29 11:37:31,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +45: [2023-04-29 11:37:31,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 8: [2023-04-29 11:37:31,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +47: [2023-04-29 11:37:31,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +37: [2023-04-29 11:37:31,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +24: [2023-04-29 11:37:31,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +18: [2023-04-29 11:37:31,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +25: [2023-04-29 11:37:31,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +24: [2023-04-29 11:37:31,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +18: [2023-04-29 11:37:31,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +18: [2023-04-29 11:37:31,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +36: [2023-04-29 11:37:31,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +25: [2023-04-29 11:37:31,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 7: [2023-04-29 11:37:31,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +30: [2023-04-29 11:37:31,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 7: [2023-04-29 11:37:31,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 7: [2023-04-29 11:37:31,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 8: [2023-04-29 11:37:31,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +24: [2023-04-29 11:37:31,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +11: [2023-04-29 11:37:31,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 8: [2023-04-29 11:37:31,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +30: [2023-04-29 11:37:31,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +11: [2023-04-29 11:37:31,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +11: [2023-04-29 11:37:31,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +11: [2023-04-29 11:37:31,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +10: [2023-04-29 11:37:31,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +24: [2023-04-29 11:37:31,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +10: [2023-04-29 11:37:31,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +10: [2023-04-29 11:37:31,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 7: [2023-04-29 11:37:31,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +45: [2023-04-29 11:37:31,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 8: [2023-04-29 11:37:31,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +10: [2023-04-29 11:37:31,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +23: [2023-04-29 11:37:31,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +17: [2023-04-29 11:37:31,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +61: [2023-04-29 11:37:31,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +26: [2023-04-29 11:37:31,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +37: [2023-04-29 11:37:31,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +30: [2023-04-29 11:37:31,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +23: [2023-04-29 11:37:31,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... + 2: [2023-04-29 11:37:31,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +38: [2023-04-29 11:37:31,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +38: [2023-04-29 11:37:31,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +26: [2023-04-29 11:37:31,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +23: [2023-04-29 11:37:31,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +23: [2023-04-29 11:37:31,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +47: [2023-04-29 11:37:31,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +17: [2023-04-29 11:37:31,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +17: [2023-04-29 11:37:31,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +17: [2023-04-29 11:37:31,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +47: [2023-04-29 11:37:31,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +30: [2023-04-29 11:37:31,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +37: [2023-04-29 11:37:31,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +47: [2023-04-29 11:37:31,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +47: [2023-04-29 11:37:31,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +61: [2023-04-29 11:37:31,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 8: [2023-04-29 11:37:31,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 2: [2023-04-29 11:37:31,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +30: [2023-04-29 11:37:31,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +30: [2023-04-29 11:37:31,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 9: [2023-04-29 11:37:31,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +38: [2023-04-29 11:37:31,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +26: [2023-04-29 11:37:31,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +26: [2023-04-29 11:37:31,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +38: [2023-04-29 11:37:31,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +37: [2023-04-29 11:37:31,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +37: [2023-04-29 11:37:31,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +61: [2023-04-29 11:37:31,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +23: [2023-04-29 11:37:31,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +23: [2023-04-29 11:37:31,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +23: [2023-04-29 11:37:31,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... + 8: [2023-04-29 11:37:31,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 2: [2023-04-29 11:37:31,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +16: [2023-04-29 11:37:31,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +16: [2023-04-29 11:37:31,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +28: [2023-04-29 11:37:31,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +61: [2023-04-29 11:37:31,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +16: [2023-04-29 11:37:31,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +16: [2023-04-29 11:37:31,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 2: [2023-04-29 11:37:31,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 2: [2023-04-29 11:37:31,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +26: [2023-04-29 11:37:31,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +26: [2023-04-29 11:37:31,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... + 9: [2023-04-29 11:37:31,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... + 8: [2023-04-29 11:37:31,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 9: [2023-04-29 11:37:31,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 2: [2023-04-29 11:37:31,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +15: [2023-04-29 11:37:31,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +37: [2023-04-29 11:37:31,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +37: [2023-04-29 11:37:31,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +23: [2023-04-29 11:37:31,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +28: [2023-04-29 11:37:31,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +15: [2023-04-29 11:37:31,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +26: [2023-04-29 11:37:31,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 2: [2023-04-29 11:37:31,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... + 2: [2023-04-29 11:37:31,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +17: [2023-04-29 11:37:31,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +15: [2023-04-29 11:37:31,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 9: [2023-04-29 11:37:31,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 9: [2023-04-29 11:37:31,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +28: [2023-04-29 11:37:31,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 8: [2023-04-29 11:37:31,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 9: [2023-04-29 11:37:31,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +15: [2023-04-29 11:37:31,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +28: [2023-04-29 11:37:31,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +28: [2023-04-29 11:37:31,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +26: [2023-04-29 11:37:31,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +15: [2023-04-29 11:37:31,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +22: [2023-04-29 11:37:31,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +61: [2023-04-29 11:37:31,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +15: [2023-04-29 11:37:31,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... + 9: [2023-04-29 11:37:31,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... + 9: [2023-04-29 11:37:31,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +28: [2023-04-29 11:37:31,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +25: [2023-04-29 11:37:31,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +15: [2023-04-29 11:37:31,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +28: [2023-04-29 11:37:31,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +22: [2023-04-29 11:37:31,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +28: [2023-04-29 11:37:31,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +60: [2023-04-29 11:37:31,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +60: [2023-04-29 11:37:31,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +60: [2023-04-29 11:37:31,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +60: [2023-04-29 11:37:31,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +38: [2023-04-29 11:37:31,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +38: [2023-04-29 11:37:31,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +29: [2023-04-29 11:37:31,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +29: [2023-04-29 11:37:31,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +29: [2023-04-29 11:37:31,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +29: [2023-04-29 11:37:31,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +35: [2023-04-29 11:37:31,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +35: [2023-04-29 11:37:31,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +61: [2023-04-29 11:37:31,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +17: [2023-04-29 11:37:31,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +35: [2023-04-29 11:37:31,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +15: [2023-04-29 11:37:31,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +35: [2023-04-29 11:37:31,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +53: [2023-04-29 11:37:31,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +53: [2023-04-29 11:37:31,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +61: [2023-04-29 11:37:31,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +25: [2023-04-29 11:37:31,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +53: [2023-04-29 11:37:31,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +53: [2023-04-29 11:37:31,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +53: [2023-04-29 11:37:31,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +53: [2023-04-29 11:37:31,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +61: [2023-04-29 11:37:31,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +61: [2023-04-29 11:37:31,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +61: [2023-04-29 11:37:31,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +17: [2023-04-29 11:37:31,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +61: [2023-04-29 11:37:31,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +16: [2023-04-29 11:37:31,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +16: [2023-04-29 11:37:31,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +22: [2023-04-29 11:37:31,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +17: [2023-04-29 11:37:31,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +38: [2023-04-29 11:37:31,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +38: [2023-04-29 11:37:31,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +53: [2023-04-29 11:37:31,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +13: [2023-04-29 11:37:31,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +13: [2023-04-29 11:37:31,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +13: [2023-04-29 11:37:31,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +13: [2023-04-29 11:37:31,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +18: [2023-04-29 11:37:31,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +53: [2023-04-29 11:37:31,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +53: [2023-04-29 11:37:31,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +19: [2023-04-29 11:37:31,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +19: [2023-04-29 11:37:31,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +53: [2023-04-29 11:37:31,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +22: [2023-04-29 11:37:31,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +53: [2023-04-29 11:37:31,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. + 7: [2023-04-29 11:37:31,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +61: [2023-04-29 11:37:31,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +53: [2023-04-29 11:37:31,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +18: [2023-04-29 11:37:31,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +19: [2023-04-29 11:37:31,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +25: [2023-04-29 11:37:31,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +16: [2023-04-29 11:37:31,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 0: [2023-04-29 11:37:31,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 0: [2023-04-29 11:37:31,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +25: [2023-04-29 11:37:31,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 7: [2023-04-29 11:37:31,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... + 0: [2023-04-29 11:37:31,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 0: [2023-04-29 11:37:31,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 7: [2023-04-29 11:37:31,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 7: [2023-04-29 11:37:31,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +55: [2023-04-29 11:37:31,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +55: [2023-04-29 11:37:31,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +55: [2023-04-29 11:37:31,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +55: [2023-04-29 11:37:31,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +16: [2023-04-29 11:37:31,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +25: [2023-04-29 11:37:31,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +24: [2023-04-29 11:37:31,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +19: [2023-04-29 11:37:31,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +19: [2023-04-29 11:37:31,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +19: [2023-04-29 11:37:31,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +25: [2023-04-29 11:37:31,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +19: [2023-04-29 11:37:31,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +51: [2023-04-29 11:37:31,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +51: [2023-04-29 11:37:31,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +51: [2023-04-29 11:37:31,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +24: [2023-04-29 11:37:31,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +24: [2023-04-29 11:37:31,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +10: [2023-04-29 11:37:31,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +51: [2023-04-29 11:37:31,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +22: [2023-04-29 11:37:31,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 0: [2023-04-29 11:37:31,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +52: [2023-04-29 11:37:31,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +52: [2023-04-29 11:37:31,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +52: [2023-04-29 11:37:31,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +52: [2023-04-29 11:37:31,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. + 0: [2023-04-29 11:37:31,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 0: [2023-04-29 11:37:31,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +25: [2023-04-29 11:37:31,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... + 0: [2023-04-29 11:37:31,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 7: [2023-04-29 11:37:31,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... + 7: [2023-04-29 11:37:31,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +11: [2023-04-29 11:37:31,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 5: [2023-04-29 11:37:31,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. + 5: [2023-04-29 11:37:31,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +25: [2023-04-29 11:37:31,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... + 7: [2023-04-29 11:37:31,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +10: [2023-04-29 11:37:31,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +18: [2023-04-29 11:37:31,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +18: [2023-04-29 11:37:31,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +11: [2023-04-29 11:37:31,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +29: [2023-04-29 11:37:31,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +24: [2023-04-29 11:37:31,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +24: [2023-04-29 11:37:31,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +10: [2023-04-29 11:37:31,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +60: [2023-04-29 11:37:31,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +24: [2023-04-29 11:37:31,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +22: [2023-04-29 11:37:31,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 5: [2023-04-29 11:37:31,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +19: [2023-04-29 11:37:31,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... + 5: [2023-04-29 11:37:31,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_12-model_01-model_states.pt. +21: [2023-04-29 11:37:31,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +21: [2023-04-29 11:37:31,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +21: [2023-04-29 11:37:31,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +21: [2023-04-29 11:37:31,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 7: [2023-04-29 11:37:31,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +60: [2023-04-29 11:37:31,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +24: [2023-04-29 11:37:31,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +10: [2023-04-29 11:37:31,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +11: [2023-04-29 11:37:31,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +11: [2023-04-29 11:37:31,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +29: [2023-04-29 11:37:31,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +35: [2023-04-29 11:37:31,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +11: [2023-04-29 11:37:31,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +29: [2023-04-29 11:37:31,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +61: [2023-04-29 11:37:31,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +11: [2023-04-29 11:37:31,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +60: [2023-04-29 11:37:31,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +29: [2023-04-29 11:37:31,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +60: [2023-04-29 11:37:31,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +18: [2023-04-29 11:37:31,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +30: [2023-04-29 11:37:31,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +61: [2023-04-29 11:37:31,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +13: [2023-04-29 11:37:31,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +35: [2023-04-29 11:37:31,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +21: [2023-04-29 11:37:31,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +10: [2023-04-29 11:37:31,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +35: [2023-04-29 11:37:31,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +35: [2023-04-29 11:37:31,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +53: [2023-04-29 11:37:31,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +24: [2023-04-29 11:37:31,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +11: [2023-04-29 11:37:31,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +53: [2023-04-29 11:37:31,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +21: [2023-04-29 11:37:31,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +24: [2023-04-29 11:37:31,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +24: [2023-04-29 11:37:31,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +21: [2023-04-29 11:37:31,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +22: [2023-04-29 11:37:31,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +24: [2023-04-29 11:37:31,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +10: [2023-04-29 11:37:31,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +24: [2023-04-29 11:37:31,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +21: [2023-04-29 11:37:31,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +61: [2023-04-29 11:37:31,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +11: [2023-04-29 11:37:31,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +13: [2023-04-29 11:37:31,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +27: [2023-04-29 11:37:31,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +27: [2023-04-29 11:37:31,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +61: [2023-04-29 11:37:31,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +27: [2023-04-29 11:37:31,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +27: [2023-04-29 11:37:31,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +30: [2023-04-29 11:37:31,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +24: [2023-04-29 11:37:31,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +18: [2023-04-29 11:37:31,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +30: [2023-04-29 11:37:31,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +10: [2023-04-29 11:37:31,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +24: [2023-04-29 11:37:31,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +24: [2023-04-29 11:37:31,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +24: [2023-04-29 11:37:31,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +53: [2023-04-29 11:37:31,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +13: [2023-04-29 11:37:31,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +22: [2023-04-29 11:37:31,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +13: [2023-04-29 11:37:31,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +10: [2023-04-29 11:37:31,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +27: [2023-04-29 11:37:31,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +27: [2023-04-29 11:37:31,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +27: [2023-04-29 11:37:31,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +27: [2023-04-29 11:37:31,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +30: [2023-04-29 11:37:31,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +53: [2023-04-29 11:37:31,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +30: [2023-04-29 11:37:31,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +30: [2023-04-29 11:37:31,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +51: [2023-04-29 11:37:31,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +51: [2023-04-29 11:37:31,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +55: [2023-04-29 11:37:31,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +55: [2023-04-29 11:37:31,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +52: [2023-04-29 11:37:31,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +17: [2023-04-29 11:37:31,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +55: [2023-04-29 11:37:31,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +17: [2023-04-29 11:37:31,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +17: [2023-04-29 11:37:31,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +17: [2023-04-29 11:37:31,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +52: [2023-04-29 11:37:31,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +55: [2023-04-29 11:37:31,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +51: [2023-04-29 11:37:31,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 5: [2023-04-29 11:37:31,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +30: [2023-04-29 11:37:31,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... + 5: [2023-04-29 11:37:31,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +30: [2023-04-29 11:37:31,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +18: [2023-04-29 11:37:31,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +52: [2023-04-29 11:37:31,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 5: [2023-04-29 11:37:31,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... + 5: [2023-04-29 11:37:31,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt... +51: [2023-04-29 11:37:31,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +62: [2023-04-29 11:37:31,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +62: [2023-04-29 11:37:31,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +62: [2023-04-29 11:37:31,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +62: [2023-04-29 11:37:31,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +19: [2023-04-29 11:37:31,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +19: [2023-04-29 11:37:31,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +18: [2023-04-29 11:37:31,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +52: [2023-04-29 11:37:31,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +19: [2023-04-29 11:37:31,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +19: [2023-04-29 11:37:31,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +62: [2023-04-29 11:37:31,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +62: [2023-04-29 11:37:31,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +62: [2023-04-29 11:37:31,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +11: [2023-04-29 11:37:31,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +11: [2023-04-29 11:37:31,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +19: [2023-04-29 11:37:31,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +19: [2023-04-29 11:37:31,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +11: [2023-04-29 11:37:31,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +11: [2023-04-29 11:37:31,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +62: [2023-04-29 11:37:31,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +19: [2023-04-29 11:37:31,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +19: [2023-04-29 11:37:31,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +48: [2023-04-29 11:37:31,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +48: [2023-04-29 11:37:31,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +48: [2023-04-29 11:37:31,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +48: [2023-04-29 11:37:31,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +48: [2023-04-29 11:37:31,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +48: [2023-04-29 11:37:31,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +48: [2023-04-29 11:37:31,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +48: [2023-04-29 11:37:31,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +16: [2023-04-29 11:37:31,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +16: [2023-04-29 11:37:31,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +11: [2023-04-29 11:37:31,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +11: [2023-04-29 11:37:31,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +11: [2023-04-29 11:37:31,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +11: [2023-04-29 11:37:31,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +48: [2023-04-29 11:37:31,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +48: [2023-04-29 11:37:31,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +48: [2023-04-29 11:37:31,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +41: [2023-04-29 11:37:31,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +41: [2023-04-29 11:37:31,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +16: [2023-04-29 11:37:31,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +16: [2023-04-29 11:37:31,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +59: [2023-04-29 11:37:31,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +59: [2023-04-29 11:37:31,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +34: [2023-04-29 11:37:31,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +34: [2023-04-29 11:37:31,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. + 1: [2023-04-29 11:37:31,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +17: [2023-04-29 11:37:31,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +41: [2023-04-29 11:37:31,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +41: [2023-04-29 11:37:31,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +59: [2023-04-29 11:37:31,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +59: [2023-04-29 11:37:31,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +48: [2023-04-29 11:37:31,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +48: [2023-04-29 11:37:31,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +48: [2023-04-29 11:37:31,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... + 0: [2023-04-29 11:37:31,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. + 0: [2023-04-29 11:37:31,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +48: [2023-04-29 11:37:31,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 0: [2023-04-29 11:37:31,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. + 0: [2023-04-29 11:37:31,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +48: [2023-04-29 11:37:31,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +34: [2023-04-29 11:37:31,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +34: [2023-04-29 11:37:31,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +53: [2023-04-29 11:37:31,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 1: [2023-04-29 11:37:31,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +17: [2023-04-29 11:37:31,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +17: [2023-04-29 11:37:31,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 1: [2023-04-29 11:37:31,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +17: [2023-04-29 11:37:31,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +16: [2023-04-29 11:37:31,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +39: [2023-04-29 11:37:31,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +39: [2023-04-29 11:37:31,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +39: [2023-04-29 11:37:31,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +58: [2023-04-29 11:37:31,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +58: [2023-04-29 11:37:31,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +58: [2023-04-29 11:37:31,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +58: [2023-04-29 11:37:31,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +58: [2023-04-29 11:37:31,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +58: [2023-04-29 11:37:31,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +58: [2023-04-29 11:37:31,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +39: [2023-04-29 11:37:31,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +58: [2023-04-29 11:37:31,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 3: [2023-04-29 11:37:31,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 3: [2023-04-29 11:37:31,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 3: [2023-04-29 11:37:31,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 3: [2023-04-29 11:37:31,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +16: [2023-04-29 11:37:31,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +39: [2023-04-29 11:37:31,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +39: [2023-04-29 11:37:31,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +24: [2023-04-29 11:37:31,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +39: [2023-04-29 11:37:31,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +39: [2023-04-29 11:37:31,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +26: [2023-04-29 11:37:31,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +26: [2023-04-29 11:37:31,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +57: [2023-04-29 11:37:31,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +57: [2023-04-29 11:37:31,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +57: [2023-04-29 11:37:31,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +58: [2023-04-29 11:37:31,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +57: [2023-04-29 11:37:31,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +58: [2023-04-29 11:37:31,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +16: [2023-04-29 11:37:31,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +26: [2023-04-29 11:37:31,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +58: [2023-04-29 11:37:31,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +26: [2023-04-29 11:37:31,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +58: [2023-04-29 11:37:31,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +58: [2023-04-29 11:37:31,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +58: [2023-04-29 11:37:31,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 3: [2023-04-29 11:37:31,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +58: [2023-04-29 11:37:31,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +58: [2023-04-29 11:37:31,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +53: [2023-04-29 11:37:31,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +53: [2023-04-29 11:37:31,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +53: [2023-04-29 11:37:31,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 3: [2023-04-29 11:37:31,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +21: [2023-04-29 11:37:31,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 3: [2023-04-29 11:37:31,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +29: [2023-04-29 11:37:31,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +26: [2023-04-29 11:37:31,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +23: [2023-04-29 11:37:31,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +23: [2023-04-29 11:37:31,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +16: [2023-04-29 11:37:31,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +26: [2023-04-29 11:37:31,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +61: [2023-04-29 11:37:31,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +39: [2023-04-29 11:37:31,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +39: [2023-04-29 11:37:31,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +26: [2023-04-29 11:37:31,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +39: [2023-04-29 11:37:31,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +23: [2023-04-29 11:37:31,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +26: [2023-04-29 11:37:31,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +23: [2023-04-29 11:37:31,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +34: [2023-04-29 11:37:31,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +29: [2023-04-29 11:37:31,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +34: [2023-04-29 11:37:31,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 0: [2023-04-29 11:37:31,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 0: [2023-04-29 11:37:31,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +39: [2023-04-29 11:37:31,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +59: [2023-04-29 11:37:31,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +59: [2023-04-29 11:37:31,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +29: [2023-04-29 11:37:31,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +61: [2023-04-29 11:37:31,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +41: [2023-04-29 11:37:31,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +41: [2023-04-29 11:37:31,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +29: [2023-04-29 11:37:31,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +61: [2023-04-29 11:37:31,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +59: [2023-04-29 11:37:31,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +53: [2023-04-29 11:37:31,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +27: [2023-04-29 11:37:31,992] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +24: [2023-04-29 11:37:31,992] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +59: [2023-04-29 11:37:31,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... + 0: [2023-04-29 11:37:31,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +23: [2023-04-29 11:37:31,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +23: [2023-04-29 11:37:31,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +23: [2023-04-29 11:37:31,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +41: [2023-04-29 11:37:31,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +41: [2023-04-29 11:37:31,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +23: [2023-04-29 11:37:31,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +43: [2023-04-29 11:37:31,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +43: [2023-04-29 11:37:31,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +43: [2023-04-29 11:37:31,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +43: [2023-04-29 11:37:31,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_37-model_01-model_states.pt. +28: [2023-04-29 11:37:31,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +28: [2023-04-29 11:37:31,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +29: [2023-04-29 11:37:31,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +61: [2023-04-29 11:37:31,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +27: [2023-04-29 11:37:31,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +29: [2023-04-29 11:37:31,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 0: [2023-04-29 11:37:31,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +24: [2023-04-29 11:37:31,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +28: [2023-04-29 11:37:31,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +34: [2023-04-29 11:37:31,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +28: [2023-04-29 11:37:31,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +29: [2023-04-29 11:37:31,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +29: [2023-04-29 11:37:31,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 0: [2023-04-29 11:37:31,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 0: [2023-04-29 11:37:31,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +29: [2023-04-29 11:37:31,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +24: [2023-04-29 11:37:31,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +29: [2023-04-29 11:37:31,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +56: [2023-04-29 11:37:31,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +56: [2023-04-29 11:37:31,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +56: [2023-04-29 11:37:31,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +29: [2023-04-29 11:37:31,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +56: [2023-04-29 11:37:31,998] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +27: [2023-04-29 11:37:31,998] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +27: [2023-04-29 11:37:31,998] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +61: [2023-04-29 11:37:31,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... + 0: [2023-04-29 11:37:31,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +62: [2023-04-29 11:37:31,998] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +62: [2023-04-29 11:37:31,998] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +62: [2023-04-29 11:37:31,998] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +62: [2023-04-29 11:37:31,998] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +28: [2023-04-29 11:37:31,999] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +61: [2023-04-29 11:37:31,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +34: [2023-04-29 11:37:31,999] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +21: [2023-04-29 11:37:32,000] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +21: [2023-04-29 11:37:32,000] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +28: [2023-04-29 11:37:32,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 0: [2023-04-29 11:37:32,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +61: [2023-04-29 11:37:32,001] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +53: [2023-04-29 11:37:32,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +29: [2023-04-29 11:37:32,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +29: [2023-04-29 11:37:32,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +29: [2023-04-29 11:37:32,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +29: [2023-04-29 11:37:32,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +29: [2023-04-29 11:37:32,004] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +21: [2023-04-29 11:37:32,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +28: [2023-04-29 11:37:32,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +28: [2023-04-29 11:37:32,004] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +45: [2023-04-29 11:37:32,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +45: [2023-04-29 11:37:32,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +61: [2023-04-29 11:37:32,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +53: [2023-04-29 11:37:32,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +53: [2023-04-29 11:37:32,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +55: [2023-04-29 11:37:32,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +55: [2023-04-29 11:37:32,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +52: [2023-04-29 11:37:32,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +10: [2023-04-29 11:37:32,006] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +10: [2023-04-29 11:37:32,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +10: [2023-04-29 11:37:32,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +10: [2023-04-29 11:37:32,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +45: [2023-04-29 11:37:32,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +52: [2023-04-29 11:37:32,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +21: [2023-04-29 11:37:32,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +39: [2023-04-29 11:37:32,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +52: [2023-04-29 11:37:32,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +24: [2023-04-29 11:37:32,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +57: [2023-04-29 11:37:32,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +39: [2023-04-29 11:37:32,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +55: [2023-04-29 11:37:32,010] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +39: [2023-04-29 11:37:32,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +45: [2023-04-29 11:37:32,011] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +55: [2023-04-29 11:37:32,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +55: [2023-04-29 11:37:32,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +53: [2023-04-29 11:37:32,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +53: [2023-04-29 11:37:32,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +53: [2023-04-29 11:37:32,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +52: [2023-04-29 11:37:32,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +52: [2023-04-29 11:37:32,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +55: [2023-04-29 11:37:32,012] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,013] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,013] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +10: [2023-04-29 11:37:32,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +10: [2023-04-29 11:37:32,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +10: [2023-04-29 11:37:32,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +39: [2023-04-29 11:37:32,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +57: [2023-04-29 11:37:32,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 5: [2023-04-29 11:37:32,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_00-model_states.pt. +10: [2023-04-29 11:37:32,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +52: [2023-04-29 11:37:32,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +57: [2023-04-29 11:37:32,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +57: [2023-04-29 11:37:32,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +55: [2023-04-29 11:37:32,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... + 5: [2023-04-29 11:37:32,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +53: [2023-04-29 11:37:32,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +55: [2023-04-29 11:37:32,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +11: [2023-04-29 11:37:32,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +27: [2023-04-29 11:37:32,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +53: [2023-04-29 11:37:32,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +19: [2023-04-29 11:37:32,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +19: [2023-04-29 11:37:32,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +53: [2023-04-29 11:37:32,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +48: [2023-04-29 11:37:32,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,019] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... + 5: [2023-04-29 11:37:32,019] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +24: [2023-04-29 11:37:32,019] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +40: [2023-04-29 11:37:32,020] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +40: [2023-04-29 11:37:32,020] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +40: [2023-04-29 11:37:32,020] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. + 5: [2023-04-29 11:37:32,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt... +43: [2023-04-29 11:37:32,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +19: [2023-04-29 11:37:32,022] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +19: [2023-04-29 11:37:32,022] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 0: [2023-04-29 11:37:32,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +52: [2023-04-29 11:37:32,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +56: [2023-04-29 11:37:32,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 0: [2023-04-29 11:37:32,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +56: [2023-04-29 11:37:32,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +43: [2023-04-29 11:37:32,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +43: [2023-04-29 11:37:32,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +43: [2023-04-29 11:37:32,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt... +47: [2023-04-29 11:37:32,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +40: [2023-04-29 11:37:32,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +56: [2023-04-29 11:37:32,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +48: [2023-04-29 11:37:32,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +47: [2023-04-29 11:37:32,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +24: [2023-04-29 11:37:32,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +47: [2023-04-29 11:37:32,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +47: [2023-04-29 11:37:32,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +47: [2023-04-29 11:37:32,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +47: [2023-04-29 11:37:32,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +47: [2023-04-29 11:37:32,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +47: [2023-04-29 11:37:32,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +24: [2023-04-29 11:37:32,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +11: [2023-04-29 11:37:32,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +56: [2023-04-29 11:37:32,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +11: [2023-04-29 11:37:32,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +11: [2023-04-29 11:37:32,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 6: [2023-04-29 11:37:32,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. + 6: [2023-04-29 11:37:32,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +27: [2023-04-29 11:37:32,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +62: [2023-04-29 11:37:32,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 6: [2023-04-29 11:37:32,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. + 0: [2023-04-29 11:37:32,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 0: [2023-04-29 11:37:32,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +42: [2023-04-29 11:37:32,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +42: [2023-04-29 11:37:32,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 6: [2023-04-29 11:37:32,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +53: [2023-04-29 11:37:32,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +62: [2023-04-29 11:37:32,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +20: [2023-04-29 11:37:32,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +20: [2023-04-29 11:37:32,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +27: [2023-04-29 11:37:32,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +17: [2023-04-29 11:37:32,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +42: [2023-04-29 11:37:32,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +42: [2023-04-29 11:37:32,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +42: [2023-04-29 11:37:32,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +42: [2023-04-29 11:37:32,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +42: [2023-04-29 11:37:32,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +47: [2023-04-29 11:37:32,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +47: [2023-04-29 11:37:32,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +47: [2023-04-29 11:37:32,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +47: [2023-04-29 11:37:32,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +47: [2023-04-29 11:37:32,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +52: [2023-04-29 11:37:32,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +47: [2023-04-29 11:37:32,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +42: [2023-04-29 11:37:32,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +21: [2023-04-29 11:37:32,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +49: [2023-04-29 11:37:32,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +49: [2023-04-29 11:37:32,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +49: [2023-04-29 11:37:32,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +49: [2023-04-29 11:37:32,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +21: [2023-04-29 11:37:32,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +47: [2023-04-29 11:37:32,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +48: [2023-04-29 11:37:32,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +27: [2023-04-29 11:37:32,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +47: [2023-04-29 11:37:32,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +20: [2023-04-29 11:37:32,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +20: [2023-04-29 11:37:32,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +53: [2023-04-29 11:37:32,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +42: [2023-04-29 11:37:32,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +48: [2023-04-29 11:37:32,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +42: [2023-04-29 11:37:32,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +63: [2023-04-29 11:37:32,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +42: [2023-04-29 11:37:32,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +63: [2023-04-29 11:37:32,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +63: [2023-04-29 11:37:32,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +63: [2023-04-29 11:37:32,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +45: [2023-04-29 11:37:32,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +45: [2023-04-29 11:37:32,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +45: [2023-04-29 11:37:32,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +17: [2023-04-29 11:37:32,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +21: [2023-04-29 11:37:32,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +42: [2023-04-29 11:37:32,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +49: [2023-04-29 11:37:32,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +62: [2023-04-29 11:37:32,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +45: [2023-04-29 11:37:32,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +49: [2023-04-29 11:37:32,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +49: [2023-04-29 11:37:32,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +49: [2023-04-29 11:37:32,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +42: [2023-04-29 11:37:32,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +42: [2023-04-29 11:37:32,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +62: [2023-04-29 11:37:32,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +62: [2023-04-29 11:37:32,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +11: [2023-04-29 11:37:32,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +42: [2023-04-29 11:37:32,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +62: [2023-04-29 11:37:32,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +42: [2023-04-29 11:37:32,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +17: [2023-04-29 11:37:32,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +58: [2023-04-29 11:37:32,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +17: [2023-04-29 11:37:32,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 3: [2023-04-29 11:37:32,044] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +19: [2023-04-29 11:37:32,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +36: [2023-04-29 11:37:32,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +36: [2023-04-29 11:37:32,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +36: [2023-04-29 11:37:32,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +36: [2023-04-29 11:37:32,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +36: [2023-04-29 11:37:32,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +38: [2023-04-29 11:37:32,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +38: [2023-04-29 11:37:32,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +36: [2023-04-29 11:37:32,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +48: [2023-04-29 11:37:32,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +26: [2023-04-29 11:37:32,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +19: [2023-04-29 11:37:32,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 5: [2023-04-29 11:37:32,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +19: [2023-04-29 11:37:32,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +38: [2023-04-29 11:37:32,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +35: [2023-04-29 11:37:32,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +35: [2023-04-29 11:37:32,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +38: [2023-04-29 11:37:32,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +38: [2023-04-29 11:37:32,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +38: [2023-04-29 11:37:32,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +38: [2023-04-29 11:37:32,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +38: [2023-04-29 11:37:32,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 3: [2023-04-29 11:37:32,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 3: [2023-04-29 11:37:32,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +54: [2023-04-29 11:37:32,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +54: [2023-04-29 11:37:32,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +40: [2023-04-29 11:37:32,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +17: [2023-04-29 11:37:32,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +40: [2023-04-29 11:37:32,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +54: [2023-04-29 11:37:32,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +54: [2023-04-29 11:37:32,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +17: [2023-04-29 11:37:32,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... + 3: [2023-04-29 11:37:32,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +50: [2023-04-29 11:37:32,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +50: [2023-04-29 11:37:32,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +50: [2023-04-29 11:37:32,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +40: [2023-04-29 11:37:32,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +58: [2023-04-29 11:37:32,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +58: [2023-04-29 11:37:32,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +37: [2023-04-29 11:37:32,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +37: [2023-04-29 11:37:32,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +55: [2023-04-29 11:37:32,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +55: [2023-04-29 11:37:32,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +37: [2023-04-29 11:37:32,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +55: [2023-04-29 11:37:32,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +36: [2023-04-29 11:37:32,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +37: [2023-04-29 11:37:32,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +50: [2023-04-29 11:37:32,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +36: [2023-04-29 11:37:32,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +55: [2023-04-29 11:37:32,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +36: [2023-04-29 11:37:32,052] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +26: [2023-04-29 11:37:32,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +35: [2023-04-29 11:37:32,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +35: [2023-04-29 11:37:32,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +35: [2023-04-29 11:37:32,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +35: [2023-04-29 11:37:32,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +35: [2023-04-29 11:37:32,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +36: [2023-04-29 11:37:32,052] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +35: [2023-04-29 11:37:32,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +17: [2023-04-29 11:37:32,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +26: [2023-04-29 11:37:32,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +48: [2023-04-29 11:37:32,052] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +38: [2023-04-29 11:37:32,052] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +23: [2023-04-29 11:37:32,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +19: [2023-04-29 11:37:32,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +38: [2023-04-29 11:37:32,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +50: [2023-04-29 11:37:32,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +54: [2023-04-29 11:37:32,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +38: [2023-04-29 11:37:32,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +54: [2023-04-29 11:37:32,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +52: [2023-04-29 11:37:32,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +52: [2023-04-29 11:37:32,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +59: [2023-04-29 11:37:32,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 5: [2023-04-29 11:37:32,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 5: [2023-04-29 11:37:32,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +54: [2023-04-29 11:37:32,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +52: [2023-04-29 11:37:32,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +62: [2023-04-29 11:37:32,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +41: [2023-04-29 11:37:32,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +52: [2023-04-29 11:37:32,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +38: [2023-04-29 11:37:32,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... + 5: [2023-04-29 11:37:32,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +62: [2023-04-29 11:37:32,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +54: [2023-04-29 11:37:32,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +62: [2023-04-29 11:37:32,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +35: [2023-04-29 11:37:32,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +13: [2023-04-29 11:37:32,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +13: [2023-04-29 11:37:32,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +13: [2023-04-29 11:37:32,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +37: [2023-04-29 11:37:32,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +13: [2023-04-29 11:37:32,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +13: [2023-04-29 11:37:32,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +13: [2023-04-29 11:37:32,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +13: [2023-04-29 11:37:32,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +58: [2023-04-29 11:37:32,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +38: [2023-04-29 11:37:32,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +40: [2023-04-29 11:37:32,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +13: [2023-04-29 11:37:32,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +55: [2023-04-29 11:37:32,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +55: [2023-04-29 11:37:32,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +37: [2023-04-29 11:37:32,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +11: [2023-04-29 11:37:32,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +38: [2023-04-29 11:37:32,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +37: [2023-04-29 11:37:32,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +55: [2023-04-29 11:37:32,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +37: [2023-04-29 11:37:32,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +11: [2023-04-29 11:37:32,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +38: [2023-04-29 11:37:32,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +55: [2023-04-29 11:37:32,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +59: [2023-04-29 11:37:32,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +59: [2023-04-29 11:37:32,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +59: [2023-04-29 11:37:32,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +52: [2023-04-29 11:37:32,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +38: [2023-04-29 11:37:32,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +35: [2023-04-29 11:37:32,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +35: [2023-04-29 11:37:32,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +17: [2023-04-29 11:37:32,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +35: [2023-04-29 11:37:32,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +50: [2023-04-29 11:37:32,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +23: [2023-04-29 11:37:32,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +20: [2023-04-29 11:37:32,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +20: [2023-04-29 11:37:32,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +50: [2023-04-29 11:37:32,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +35: [2023-04-29 11:37:32,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +32: [2023-04-29 11:37:32,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +32: [2023-04-29 11:37:32,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +52: [2023-04-29 11:37:32,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +48: [2023-04-29 11:37:32,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +36: [2023-04-29 11:37:32,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +52: [2023-04-29 11:37:32,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +41: [2023-04-29 11:37:32,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +50: [2023-04-29 11:37:32,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +13: [2023-04-29 11:37:32,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +13: [2023-04-29 11:37:32,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +11: [2023-04-29 11:37:32,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +59: [2023-04-29 11:37:32,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +28: [2023-04-29 11:37:32,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +28: [2023-04-29 11:37:32,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +23: [2023-04-29 11:37:32,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +23: [2023-04-29 11:37:32,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +13: [2023-04-29 11:37:32,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +52: [2023-04-29 11:37:32,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +36: [2023-04-29 11:37:32,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 9: [2023-04-29 11:37:32,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +35: [2023-04-29 11:37:32,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +41: [2023-04-29 11:37:32,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +35: [2023-04-29 11:37:32,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +63: [2023-04-29 11:37:32,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +41: [2023-04-29 11:37:32,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +63: [2023-04-29 11:37:32,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +41: [2023-04-29 11:37:32,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +41: [2023-04-29 11:37:32,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +32: [2023-04-29 11:37:32,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +35: [2023-04-29 11:37:32,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +32: [2023-04-29 11:37:32,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +41: [2023-04-29 11:37:32,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +32: [2023-04-29 11:37:32,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +41: [2023-04-29 11:37:32,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +32: [2023-04-29 11:37:32,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +32: [2023-04-29 11:37:32,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +59: [2023-04-29 11:37:32,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +20: [2023-04-29 11:37:32,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +32: [2023-04-29 11:37:32,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +59: [2023-04-29 11:37:32,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +13: [2023-04-29 11:37:32,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +20: [2023-04-29 11:37:32,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +59: [2023-04-29 11:37:32,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +13: [2023-04-29 11:37:32,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +13: [2023-04-29 11:37:32,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... + 0: [2023-04-29 11:37:32,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +32: [2023-04-29 11:37:32,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +13: [2023-04-29 11:37:32,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +13: [2023-04-29 11:37:32,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +48: [2023-04-29 11:37:32,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +40: [2023-04-29 11:37:32,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +41: [2023-04-29 11:37:32,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +26: [2023-04-29 11:37:32,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +29: [2023-04-29 11:37:32,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +29: [2023-04-29 11:37:32,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +63: [2023-04-29 11:37:32,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +63: [2023-04-29 11:37:32,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +39: [2023-04-29 11:37:32,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +32: [2023-04-29 11:37:32,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +32: [2023-04-29 11:37:32,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +32: [2023-04-29 11:37:32,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +40: [2023-04-29 11:37:32,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +40: [2023-04-29 11:37:32,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +40: [2023-04-29 11:37:32,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 9: [2023-04-29 11:37:32,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +41: [2023-04-29 11:37:32,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +40: [2023-04-29 11:37:32,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +41: [2023-04-29 11:37:32,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +41: [2023-04-29 11:37:32,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +41: [2023-04-29 11:37:32,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 0: [2023-04-29 11:37:32,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +28: [2023-04-29 11:37:32,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +41: [2023-04-29 11:37:32,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +39: [2023-04-29 11:37:32,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +39: [2023-04-29 11:37:32,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +28: [2023-04-29 11:37:32,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 3: [2023-04-29 11:37:32,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +41: [2023-04-29 11:37:32,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +58: [2023-04-29 11:37:32,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +41: [2023-04-29 11:37:32,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +36: [2023-04-29 11:37:32,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +62: [2023-04-29 11:37:32,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 3: [2023-04-29 11:37:32,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +10: [2023-04-29 11:37:32,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +32: [2023-04-29 11:37:32,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +32: [2023-04-29 11:37:32,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +32: [2023-04-29 11:37:32,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +25: [2023-04-29 11:37:32,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +25: [2023-04-29 11:37:32,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +25: [2023-04-29 11:37:32,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +32: [2023-04-29 11:37:32,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +25: [2023-04-29 11:37:32,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +29: [2023-04-29 11:37:32,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 4: [2023-04-29 11:37:32,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. + 4: [2023-04-29 11:37:32,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. + 0: [2023-04-29 11:37:32,075] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,075] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. + 4: [2023-04-29 11:37:32,076] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +39: [2023-04-29 11:37:32,076] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. + 3: [2023-04-29 11:37:32,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +36: [2023-04-29 11:37:32,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +40: [2023-04-29 11:37:32,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +40: [2023-04-29 11:37:32,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +29: [2023-04-29 11:37:32,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +40: [2023-04-29 11:37:32,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +23: [2023-04-29 11:37:32,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +26: [2023-04-29 11:37:32,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +36: [2023-04-29 11:37:32,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +58: [2023-04-29 11:37:32,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +39: [2023-04-29 11:37:32,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 3: [2023-04-29 11:37:32,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +25: [2023-04-29 11:37:32,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +25: [2023-04-29 11:37:32,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +58: [2023-04-29 11:37:32,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +57: [2023-04-29 11:37:32,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +26: [2023-04-29 11:37:32,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +57: [2023-04-29 11:37:32,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +10: [2023-04-29 11:37:32,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +10: [2023-04-29 11:37:32,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +10: [2023-04-29 11:37:32,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +36: [2023-04-29 11:37:32,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... + 0: [2023-04-29 11:37:32,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +26: [2023-04-29 11:37:32,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +25: [2023-04-29 11:37:32,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +39: [2023-04-29 11:37:32,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +25: [2023-04-29 11:37:32,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 0: [2023-04-29 11:37:32,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +43: [2023-04-29 11:37:32,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +43: [2023-04-29 11:37:32,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 0: [2023-04-29 11:37:32,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +23: [2023-04-29 11:37:32,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +57: [2023-04-29 11:37:32,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +57: [2023-04-29 11:37:32,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +43: [2023-04-29 11:37:32,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +43: [2023-04-29 11:37:32,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +39: [2023-04-29 11:37:32,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +43: [2023-04-29 11:37:32,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +58: [2023-04-29 11:37:32,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +28: [2023-04-29 11:37:32,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +28: [2023-04-29 11:37:32,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +57: [2023-04-29 11:37:32,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 0: [2023-04-29 11:37:32,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +23: [2023-04-29 11:37:32,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +23: [2023-04-29 11:37:32,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +43: [2023-04-29 11:37:32,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +43: [2023-04-29 11:37:32,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +43: [2023-04-29 11:37:32,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 0: [2023-04-29 11:37:32,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +29: [2023-04-29 11:37:32,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +62: [2023-04-29 11:37:32,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +39: [2023-04-29 11:37:32,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +43: [2023-04-29 11:37:32,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +57: [2023-04-29 11:37:32,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +26: [2023-04-29 11:37:32,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +29: [2023-04-29 11:37:32,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +43: [2023-04-29 11:37:32,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +57: [2023-04-29 11:37:32,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +39: [2023-04-29 11:37:32,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +44: [2023-04-29 11:37:32,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +44: [2023-04-29 11:37:32,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +46: [2023-04-29 11:37:32,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +46: [2023-04-29 11:37:32,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +47: [2023-04-29 11:37:32,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +39: [2023-04-29 11:37:32,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +39: [2023-04-29 11:37:32,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +44: [2023-04-29 11:37:32,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +49: [2023-04-29 11:37:32,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +39: [2023-04-29 11:37:32,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +44: [2023-04-29 11:37:32,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +39: [2023-04-29 11:37:32,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +57: [2023-04-29 11:37:32,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +28: [2023-04-29 11:37:32,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +46: [2023-04-29 11:37:32,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +47: [2023-04-29 11:37:32,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +43: [2023-04-29 11:37:32,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +43: [2023-04-29 11:37:32,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +46: [2023-04-29 11:37:32,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +42: [2023-04-29 11:37:32,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +42: [2023-04-29 11:37:32,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +42: [2023-04-29 11:37:32,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +43: [2023-04-29 11:37:32,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_00-model_states.pt. +47: [2023-04-29 11:37:32,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +22: [2023-04-29 11:37:32,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +22: [2023-04-29 11:37:32,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +22: [2023-04-29 11:37:32,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +45: [2023-04-29 11:37:32,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +44: [2023-04-29 11:37:32,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +44: [2023-04-29 11:37:32,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +22: [2023-04-29 11:37:32,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +39: [2023-04-29 11:37:32,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +28: [2023-04-29 11:37:32,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +44: [2023-04-29 11:37:32,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +47: [2023-04-29 11:37:32,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +44: [2023-04-29 11:37:32,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +10: [2023-04-29 11:37:32,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +46: [2023-04-29 11:37:32,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +46: [2023-04-29 11:37:32,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +42: [2023-04-29 11:37:32,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +46: [2023-04-29 11:37:32,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +46: [2023-04-29 11:37:32,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 8: [2023-04-29 11:37:32,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. + 8: [2023-04-29 11:37:32,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. + 8: [2023-04-29 11:37:32,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +63: [2023-04-29 11:37:32,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +63: [2023-04-29 11:37:32,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +39: [2023-04-29 11:37:32,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +45: [2023-04-29 11:37:32,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +43: [2023-04-29 11:37:32,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +50: [2023-04-29 11:37:32,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +62: [2023-04-29 11:37:32,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +43: [2023-04-29 11:37:32,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... +22: [2023-04-29 11:37:32,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +43: [2023-04-29 11:37:32,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt... + 4: [2023-04-29 11:37:32,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +22: [2023-04-29 11:37:32,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +49: [2023-04-29 11:37:32,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +49: [2023-04-29 11:37:32,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +49: [2023-04-29 11:37:32,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +22: [2023-04-29 11:37:32,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +63: [2023-04-29 11:37:32,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +22: [2023-04-29 11:37:32,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +29: [2023-04-29 11:37:32,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +29: [2023-04-29 11:37:32,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 4: [2023-04-29 11:37:32,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +63: [2023-04-29 11:37:32,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +39: [2023-04-29 11:37:32,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +10: [2023-04-29 11:37:32,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +21: [2023-04-29 11:37:32,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +21: [2023-04-29 11:37:32,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +52: [2023-04-29 11:37:32,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +21: [2023-04-29 11:37:32,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +10: [2023-04-29 11:37:32,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +45: [2023-04-29 11:37:32,111] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +10: [2023-04-29 11:37:32,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +21: [2023-04-29 11:37:32,111] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +63: [2023-04-29 11:37:32,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +45: [2023-04-29 11:37:32,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +45: [2023-04-29 11:37:32,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +63: [2023-04-29 11:37:32,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +38: [2023-04-29 11:37:32,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +45: [2023-04-29 11:37:32,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +63: [2023-04-29 11:37:32,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +63: [2023-04-29 11:37:32,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +45: [2023-04-29 11:37:32,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +60: [2023-04-29 11:37:32,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +60: [2023-04-29 11:37:32,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +37: [2023-04-29 11:37:32,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +55: [2023-04-29 11:37:32,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +54: [2023-04-29 11:37:32,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +13: [2023-04-29 11:37:32,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +40: [2023-04-29 11:37:32,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +40: [2023-04-29 11:37:32,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +35: [2023-04-29 11:37:32,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +32: [2023-04-29 11:37:32,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +45: [2023-04-29 11:37:32,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +60: [2023-04-29 11:37:32,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +60: [2023-04-29 11:37:32,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +60: [2023-04-29 11:37:32,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +60: [2023-04-29 11:37:32,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +60: [2023-04-29 11:37:32,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +60: [2023-04-29 11:37:32,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +55: [2023-04-29 11:37:32,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +17: [2023-04-29 11:37:32,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +17: [2023-04-29 11:37:32,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +17: [2023-04-29 11:37:32,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +17: [2023-04-29 11:37:32,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +38: [2023-04-29 11:37:32,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +54: [2023-04-29 11:37:32,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +40: [2023-04-29 11:37:32,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +40: [2023-04-29 11:37:32,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +60: [2023-04-29 11:37:32,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +60: [2023-04-29 11:37:32,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +13: [2023-04-29 11:37:32,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +13: [2023-04-29 11:37:32,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +38: [2023-04-29 11:37:32,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +38: [2023-04-29 11:37:32,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +54: [2023-04-29 11:37:32,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +54: [2023-04-29 11:37:32,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +54: [2023-04-29 11:37:32,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +54: [2023-04-29 11:37:32,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +60: [2023-04-29 11:37:32,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +33: [2023-04-29 11:37:32,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +33: [2023-04-29 11:37:32,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +33: [2023-04-29 11:37:32,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. + 5: [2023-04-29 11:37:32,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +33: [2023-04-29 11:37:32,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +54: [2023-04-29 11:37:32,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +49: [2023-04-29 11:37:32,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +47: [2023-04-29 11:37:32,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 4: [2023-04-29 11:37:32,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +20: [2023-04-29 11:37:32,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +60: [2023-04-29 11:37:32,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +30: [2023-04-29 11:37:32,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +30: [2023-04-29 11:37:32,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +54: [2023-04-29 11:37:32,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +55: [2023-04-29 11:37:32,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +18: [2023-04-29 11:37:32,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +18: [2023-04-29 11:37:32,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +17: [2023-04-29 11:37:32,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +17: [2023-04-29 11:37:32,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +42: [2023-04-29 11:37:32,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +47: [2023-04-29 11:37:32,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +17: [2023-04-29 11:37:32,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +60: [2023-04-29 11:37:32,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +60: [2023-04-29 11:37:32,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +60: [2023-04-29 11:37:32,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +30: [2023-04-29 11:37:32,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +52: [2023-04-29 11:37:32,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 4: [2023-04-29 11:37:32,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +30: [2023-04-29 11:37:32,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +52: [2023-04-29 11:37:32,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +18: [2023-04-29 11:37:32,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +60: [2023-04-29 11:37:32,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +40: [2023-04-29 11:37:32,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +20: [2023-04-29 11:37:32,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +18: [2023-04-29 11:37:32,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +62: [2023-04-29 11:37:32,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +17: [2023-04-29 11:37:32,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 8: [2023-04-29 11:37:32,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +37: [2023-04-29 11:37:32,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +37: [2023-04-29 11:37:32,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +40: [2023-04-29 11:37:32,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +36: [2023-04-29 11:37:32,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +36: [2023-04-29 11:37:32,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +52: [2023-04-29 11:37:32,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +42: [2023-04-29 11:37:32,133] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +42: [2023-04-29 11:37:32,133] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +47: [2023-04-29 11:37:32,133] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +50: [2023-04-29 11:37:32,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +63: [2023-04-29 11:37:32,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +63: [2023-04-29 11:37:32,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +20: [2023-04-29 11:37:32,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +25: [2023-04-29 11:37:32,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +30: [2023-04-29 11:37:32,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +35: [2023-04-29 11:37:32,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +36: [2023-04-29 11:37:32,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +21: [2023-04-29 11:37:32,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +55: [2023-04-29 11:37:32,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +37: [2023-04-29 11:37:32,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +47: [2023-04-29 11:37:32,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +18: [2023-04-29 11:37:32,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +30: [2023-04-29 11:37:32,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +18: [2023-04-29 11:37:32,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +50: [2023-04-29 11:37:32,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +50: [2023-04-29 11:37:32,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +18: [2023-04-29 11:37:32,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +20: [2023-04-29 11:37:32,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +30: [2023-04-29 11:37:32,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 8: [2023-04-29 11:37:32,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +52: [2023-04-29 11:37:32,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +30: [2023-04-29 11:37:32,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +35: [2023-04-29 11:37:32,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +44: [2023-04-29 11:37:32,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +42: [2023-04-29 11:37:32,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +44: [2023-04-29 11:37:32,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +44: [2023-04-29 11:37:32,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +13: [2023-04-29 11:37:32,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +40: [2023-04-29 11:37:32,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... + 8: [2023-04-29 11:37:32,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +44: [2023-04-29 11:37:32,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +41: [2023-04-29 11:37:32,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +32: [2023-04-29 11:37:32,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 2: [2023-04-29 11:37:32,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 2: [2023-04-29 11:37:32,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +20: [2023-04-29 11:37:32,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... + 8: [2023-04-29 11:37:32,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 9: [2023-04-29 11:37:32,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +20: [2023-04-29 11:37:32,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +20: [2023-04-29 11:37:32,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +12: [2023-04-29 11:37:32,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +12: [2023-04-29 11:37:32,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +38: [2023-04-29 11:37:32,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +40: [2023-04-29 11:37:32,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +18: [2023-04-29 11:37:32,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +21: [2023-04-29 11:37:32,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +35: [2023-04-29 11:37:32,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +20: [2023-04-29 11:37:32,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +20: [2023-04-29 11:37:32,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +20: [2023-04-29 11:37:32,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +36: [2023-04-29 11:37:32,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +49: [2023-04-29 11:37:32,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +41: [2023-04-29 11:37:32,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +62: [2023-04-29 11:37:32,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +12: [2023-04-29 11:37:32,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +33: [2023-04-29 11:37:32,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +33: [2023-04-29 11:37:32,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +33: [2023-04-29 11:37:32,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +20: [2023-04-29 11:37:32,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +12: [2023-04-29 11:37:32,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 2: [2023-04-29 11:37:32,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +63: [2023-04-29 11:37:32,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... + 2: [2023-04-29 11:37:32,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +37: [2023-04-29 11:37:32,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +63: [2023-04-29 11:37:32,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... + 8: [2023-04-29 11:37:32,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 8: [2023-04-29 11:37:32,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +49: [2023-04-29 11:37:32,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +49: [2023-04-29 11:37:32,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +50: [2023-04-29 11:37:32,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +35: [2023-04-29 11:37:32,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 2: [2023-04-29 11:37:32,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +20: [2023-04-29 11:37:32,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 2: [2023-04-29 11:37:32,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +12: [2023-04-29 11:37:32,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +20: [2023-04-29 11:37:32,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +12: [2023-04-29 11:37:32,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +33: [2023-04-29 11:37:32,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +40: [2023-04-29 11:37:32,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +20: [2023-04-29 11:37:32,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +25: [2023-04-29 11:37:32,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +32: [2023-04-29 11:37:32,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 8: [2023-04-29 11:37:32,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +54: [2023-04-29 11:37:32,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +62: [2023-04-29 11:37:32,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +62: [2023-04-29 11:37:32,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +62: [2023-04-29 11:37:32,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +55: [2023-04-29 11:37:32,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +20: [2023-04-29 11:37:32,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +36: [2023-04-29 11:37:32,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +21: [2023-04-29 11:37:32,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 2: [2023-04-29 11:37:32,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +20: [2023-04-29 11:37:32,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +33: [2023-04-29 11:37:32,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 5: [2023-04-29 11:37:32,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +33: [2023-04-29 11:37:32,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +63: [2023-04-29 11:37:32,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +33: [2023-04-29 11:37:32,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 2: [2023-04-29 11:37:32,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 5: [2023-04-29 11:37:32,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +13: [2023-04-29 11:37:32,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +12: [2023-04-29 11:37:32,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +36: [2023-04-29 11:37:32,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +32: [2023-04-29 11:37:32,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +41: [2023-04-29 11:37:32,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +32: [2023-04-29 11:37:32,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +12: [2023-04-29 11:37:32,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 8: [2023-04-29 11:37:32,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +33: [2023-04-29 11:37:32,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +36: [2023-04-29 11:37:32,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +63: [2023-04-29 11:37:32,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +55: [2023-04-29 11:37:32,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +33: [2023-04-29 11:37:32,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +21: [2023-04-29 11:37:32,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +25: [2023-04-29 11:37:32,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +25: [2023-04-29 11:37:32,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +13: [2023-04-29 11:37:32,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +41: [2023-04-29 11:37:32,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +13: [2023-04-29 11:37:32,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +45: [2023-04-29 11:37:32,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +45: [2023-04-29 11:37:32,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +62: [2023-04-29 11:37:32,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +62: [2023-04-29 11:37:32,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +45: [2023-04-29 11:37:32,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +40: [2023-04-29 11:37:32,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +62: [2023-04-29 11:37:32,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +43: [2023-04-29 11:37:32,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +54: [2023-04-29 11:37:32,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +45: [2023-04-29 11:37:32,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +38: [2023-04-29 11:37:32,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +36: [2023-04-29 11:37:32,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +63: [2023-04-29 11:37:32,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +54: [2023-04-29 11:37:32,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +51: [2023-04-29 11:37:32,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +51: [2023-04-29 11:37:32,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +51: [2023-04-29 11:37:32,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +43: [2023-04-29 11:37:32,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +51: [2023-04-29 11:37:32,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +51: [2023-04-29 11:37:32,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +51: [2023-04-29 11:37:32,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +51: [2023-04-29 11:37:32,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +54: [2023-04-29 11:37:32,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +51: [2023-04-29 11:37:32,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +54: [2023-04-29 11:37:32,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +52: [2023-04-29 11:37:32,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +52: [2023-04-29 11:37:32,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 5: [2023-04-29 11:37:32,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +56: [2023-04-29 11:37:32,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +56: [2023-04-29 11:37:32,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +63: [2023-04-29 11:37:32,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +33: [2023-04-29 11:37:32,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +45: [2023-04-29 11:37:32,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +55: [2023-04-29 11:37:32,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +25: [2023-04-29 11:37:32,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +54: [2023-04-29 11:37:32,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +37: [2023-04-29 11:37:32,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +36: [2023-04-29 11:37:32,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +40: [2023-04-29 11:37:32,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +40: [2023-04-29 11:37:32,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +40: [2023-04-29 11:37:32,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +38: [2023-04-29 11:37:32,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +38: [2023-04-29 11:37:32,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +45: [2023-04-29 11:37:32,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +37: [2023-04-29 11:37:32,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 4: [2023-04-29 11:37:32,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +52: [2023-04-29 11:37:32,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +45: [2023-04-29 11:37:32,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +45: [2023-04-29 11:37:32,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +56: [2023-04-29 11:37:32,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +56: [2023-04-29 11:37:32,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +56: [2023-04-29 11:37:32,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +56: [2023-04-29 11:37:32,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +56: [2023-04-29 11:37:32,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +56: [2023-04-29 11:37:32,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +33: [2023-04-29 11:37:32,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +54: [2023-04-29 11:37:32,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +36: [2023-04-29 11:37:32,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +44: [2023-04-29 11:37:32,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +51: [2023-04-29 11:37:32,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +51: [2023-04-29 11:37:32,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +36: [2023-04-29 11:37:32,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +54: [2023-04-29 11:37:32,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +44: [2023-04-29 11:37:32,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +44: [2023-04-29 11:37:32,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +37: [2023-04-29 11:37:32,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +56: [2023-04-29 11:37:32,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +33: [2023-04-29 11:37:32,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +56: [2023-04-29 11:37:32,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +43: [2023-04-29 11:37:32,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +46: [2023-04-29 11:37:32,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +50: [2023-04-29 11:37:32,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +36: [2023-04-29 11:37:32,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... + 4: [2023-04-29 11:37:32,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +32: [2023-04-29 11:37:32,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +13: [2023-04-29 11:37:32,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +43: [2023-04-29 11:37:32,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +35: [2023-04-29 11:37:32,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +56: [2023-04-29 11:37:32,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +44: [2023-04-29 11:37:32,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +56: [2023-04-29 11:37:32,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +22: [2023-04-29 11:37:32,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +56: [2023-04-29 11:37:32,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +35: [2023-04-29 11:37:32,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +55: [2023-04-29 11:37:32,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 9: [2023-04-29 11:37:32,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +56: [2023-04-29 11:37:32,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +51: [2023-04-29 11:37:32,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +22: [2023-04-29 11:37:32,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +51: [2023-04-29 11:37:32,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +56: [2023-04-29 11:37:32,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +36: [2023-04-29 11:37:32,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +46: [2023-04-29 11:37:32,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +56: [2023-04-29 11:37:32,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +50: [2023-04-29 11:37:32,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +51: [2023-04-29 11:37:32,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +25: [2023-04-29 11:37:32,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +51: [2023-04-29 11:37:32,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 6: [2023-04-29 11:37:32,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +51: [2023-04-29 11:37:32,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +51: [2023-04-29 11:37:32,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +35: [2023-04-29 11:37:32,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +63: [2023-04-29 11:37:32,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +41: [2023-04-29 11:37:32,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 6: [2023-04-29 11:37:32,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 1: [2023-04-29 11:37:32,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 1: [2023-04-29 11:37:32,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 6: [2023-04-29 11:37:32,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 6: [2023-04-29 11:37:32,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 6: [2023-04-29 11:37:32,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +32: [2023-04-29 11:37:32,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 1: [2023-04-29 11:37:32,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 6: [2023-04-29 11:37:32,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 1: [2023-04-29 11:37:32,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +63: [2023-04-29 11:37:32,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +50: [2023-04-29 11:37:32,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +34: [2023-04-29 11:37:32,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +34: [2023-04-29 11:37:32,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +34: [2023-04-29 11:37:32,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +34: [2023-04-29 11:37:32,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +34: [2023-04-29 11:37:32,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +34: [2023-04-29 11:37:32,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +34: [2023-04-29 11:37:32,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +34: [2023-04-29 11:37:32,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 1: [2023-04-29 11:37:32,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +31: [2023-04-29 11:37:32,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +31: [2023-04-29 11:37:32,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +31: [2023-04-29 11:37:32,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +44: [2023-04-29 11:37:32,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +44: [2023-04-29 11:37:32,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +31: [2023-04-29 11:37:32,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. + 1: [2023-04-29 11:37:32,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 9: [2023-04-29 11:37:32,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +36: [2023-04-29 11:37:32,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... + 6: [2023-04-29 11:37:32,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +46: [2023-04-29 11:37:32,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +46: [2023-04-29 11:37:32,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 1: [2023-04-29 11:37:32,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +22: [2023-04-29 11:37:32,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +22: [2023-04-29 11:37:32,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 6: [2023-04-29 11:37:32,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +32: [2023-04-29 11:37:32,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +34: [2023-04-29 11:37:32,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +43: [2023-04-29 11:37:32,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +34: [2023-04-29 11:37:32,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +34: [2023-04-29 11:37:32,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +34: [2023-04-29 11:37:32,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 4: [2023-04-29 11:37:32,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... + 1: [2023-04-29 11:37:32,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +59: [2023-04-29 11:37:32,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +59: [2023-04-29 11:37:32,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +36: [2023-04-29 11:37:32,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +36: [2023-04-29 11:37:32,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... + 6: [2023-04-29 11:37:32,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +25: [2023-04-29 11:37:32,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +43: [2023-04-29 11:37:32,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +59: [2023-04-29 11:37:32,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +59: [2023-04-29 11:37:32,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +44: [2023-04-29 11:37:32,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 6: [2023-04-29 11:37:32,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +41: [2023-04-29 11:37:32,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +44: [2023-04-29 11:37:32,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +57: [2023-04-29 11:37:32,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +57: [2023-04-29 11:37:32,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +27: [2023-04-29 11:37:32,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +27: [2023-04-29 11:37:32,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +25: [2023-04-29 11:37:32,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +57: [2023-04-29 11:37:32,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +17: [2023-04-29 11:37:32,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +27: [2023-04-29 11:37:32,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +27: [2023-04-29 11:37:32,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +34: [2023-04-29 11:37:32,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +34: [2023-04-29 11:37:32,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +59: [2023-04-29 11:37:32,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +57: [2023-04-29 11:37:32,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +34: [2023-04-29 11:37:32,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... + 7: [2023-04-29 11:37:32,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 7: [2023-04-29 11:37:32,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +34: [2023-04-29 11:37:32,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +18: [2023-04-29 11:37:32,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +18: [2023-04-29 11:37:32,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +31: [2023-04-29 11:37:32,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +31: [2023-04-29 11:37:32,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +31: [2023-04-29 11:37:32,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 7: [2023-04-29 11:37:32,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +31: [2023-04-29 11:37:32,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +41: [2023-04-29 11:37:32,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 7: [2023-04-29 11:37:32,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +18: [2023-04-29 11:37:32,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +16: [2023-04-29 11:37:32,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +18: [2023-04-29 11:37:32,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +16: [2023-04-29 11:37:32,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +16: [2023-04-29 11:37:32,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +59: [2023-04-29 11:37:32,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +59: [2023-04-29 11:37:32,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +16: [2023-04-29 11:37:32,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +59: [2023-04-29 11:37:32,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +41: [2023-04-29 11:37:32,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +57: [2023-04-29 11:37:32,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +57: [2023-04-29 11:37:32,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +57: [2023-04-29 11:37:32,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 4: [2023-04-29 11:37:32,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +60: [2023-04-29 11:37:32,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +57: [2023-04-29 11:37:32,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +31: [2023-04-29 11:37:32,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 4: [2023-04-29 11:37:32,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +63: [2023-04-29 11:37:32,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +63: [2023-04-29 11:37:32,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +31: [2023-04-29 11:37:32,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 7: [2023-04-29 11:37:32,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 7: [2023-04-29 11:37:32,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +46: [2023-04-29 11:37:32,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 7: [2023-04-29 11:37:32,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +43: [2023-04-29 11:37:32,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +60: [2023-04-29 11:37:32,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +31: [2023-04-29 11:37:32,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +43: [2023-04-29 11:37:32,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +31: [2023-04-29 11:37:32,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +18: [2023-04-29 11:37:32,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +22: [2023-04-29 11:37:32,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +40: [2023-04-29 11:37:32,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +40: [2023-04-29 11:37:32,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +46: [2023-04-29 11:37:32,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 7: [2023-04-29 11:37:32,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +60: [2023-04-29 11:37:32,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +16: [2023-04-29 11:37:32,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +22: [2023-04-29 11:37:32,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 8: [2023-04-29 11:37:32,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +40: [2023-04-29 11:37:32,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +16: [2023-04-29 11:37:32,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +63: [2023-04-29 11:37:32,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +16: [2023-04-29 11:37:32,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +16: [2023-04-29 11:37:32,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 4: [2023-04-29 11:37:32,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... + 4: [2023-04-29 11:37:32,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +21: [2023-04-29 11:37:32,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +17: [2023-04-29 11:37:32,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +30: [2023-04-29 11:37:32,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +30: [2023-04-29 11:37:32,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +63: [2023-04-29 11:37:32,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +17: [2023-04-29 11:37:32,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +17: [2023-04-29 11:37:32,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +24: [2023-04-29 11:37:32,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +24: [2023-04-29 11:37:32,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +24: [2023-04-29 11:37:32,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +24: [2023-04-29 11:37:32,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +60: [2023-04-29 11:37:32,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +30: [2023-04-29 11:37:32,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +61: [2023-04-29 11:37:32,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +61: [2023-04-29 11:37:32,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +21: [2023-04-29 11:37:32,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +30: [2023-04-29 11:37:32,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +33: [2023-04-29 11:37:32,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +21: [2023-04-29 11:37:32,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +44: [2023-04-29 11:37:32,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +24: [2023-04-29 11:37:32,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +24: [2023-04-29 11:37:32,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +12: [2023-04-29 11:37:32,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +12: [2023-04-29 11:37:32,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +24: [2023-04-29 11:37:32,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +61: [2023-04-29 11:37:32,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +31: [2023-04-29 11:37:32,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +24: [2023-04-29 11:37:32,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +61: [2023-04-29 11:37:32,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +44: [2023-04-29 11:37:32,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +20: [2023-04-29 11:37:32,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +31: [2023-04-29 11:37:32,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +20: [2023-04-29 11:37:32,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +20: [2023-04-29 11:37:32,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +21: [2023-04-29 11:37:32,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +31: [2023-04-29 11:37:32,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +17: [2023-04-29 11:37:32,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +20: [2023-04-29 11:37:32,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +46: [2023-04-29 11:37:32,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +22: [2023-04-29 11:37:32,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +46: [2023-04-29 11:37:32,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 4: [2023-04-29 11:37:32,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 2: [2023-04-29 11:37:32,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +31: [2023-04-29 11:37:32,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +44: [2023-04-29 11:37:32,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +44: [2023-04-29 11:37:32,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +18: [2023-04-29 11:37:32,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +18: [2023-04-29 11:37:32,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 2: [2023-04-29 11:37:32,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 2: [2023-04-29 11:37:32,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +18: [2023-04-29 11:37:32,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +33: [2023-04-29 11:37:32,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +22: [2023-04-29 11:37:32,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +18: [2023-04-29 11:37:32,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +21: [2023-04-29 11:37:32,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +46: [2023-04-29 11:37:32,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +46: [2023-04-29 11:37:32,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +27: [2023-04-29 11:37:32,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +12: [2023-04-29 11:37:32,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +27: [2023-04-29 11:37:32,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +27: [2023-04-29 11:37:32,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +27: [2023-04-29 11:37:32,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 2: [2023-04-29 11:37:32,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +54: [2023-04-29 11:37:32,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +46: [2023-04-29 11:37:32,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +12: [2023-04-29 11:37:32,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +33: [2023-04-29 11:37:32,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +46: [2023-04-29 11:37:32,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +18: [2023-04-29 11:37:32,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +60: [2023-04-29 11:37:32,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +33: [2023-04-29 11:37:32,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +33: [2023-04-29 11:37:32,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +33: [2023-04-29 11:37:32,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +55: [2023-04-29 11:37:32,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +55: [2023-04-29 11:37:32,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. + 1: [2023-04-29 11:37:32,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. + 1: [2023-04-29 11:37:32,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +55: [2023-04-29 11:37:32,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. + 1: [2023-04-29 11:37:32,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +55: [2023-04-29 11:37:32,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. + 1: [2023-04-29 11:37:32,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +18: [2023-04-29 11:37:32,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +12: [2023-04-29 11:37:32,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +12: [2023-04-29 11:37:32,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +18: [2023-04-29 11:37:32,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +18: [2023-04-29 11:37:32,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +49: [2023-04-29 11:37:32,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +49: [2023-04-29 11:37:32,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +12: [2023-04-29 11:37:32,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +45: [2023-04-29 11:37:32,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +49: [2023-04-29 11:37:32,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +12: [2023-04-29 11:37:32,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +49: [2023-04-29 11:37:32,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. + 8: [2023-04-29 11:37:32,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +54: [2023-04-29 11:37:32,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +60: [2023-04-29 11:37:32,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +21: [2023-04-29 11:37:32,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +54: [2023-04-29 11:37:32,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +21: [2023-04-29 11:37:32,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +60: [2023-04-29 11:37:32,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +45: [2023-04-29 11:37:32,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +63: [2023-04-29 11:37:32,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +63: [2023-04-29 11:37:32,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +56: [2023-04-29 11:37:32,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +54: [2023-04-29 11:37:32,229] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... + 8: [2023-04-29 11:37:32,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +17: [2023-04-29 11:37:32,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 8: [2023-04-29 11:37:32,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +30: [2023-04-29 11:37:32,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +54: [2023-04-29 11:37:32,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +54: [2023-04-29 11:37:32,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +45: [2023-04-29 11:37:32,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +45: [2023-04-29 11:37:32,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +17: [2023-04-29 11:37:32,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +21: [2023-04-29 11:37:32,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +30: [2023-04-29 11:37:32,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +30: [2023-04-29 11:37:32,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +30: [2023-04-29 11:37:32,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +17: [2023-04-29 11:37:32,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +60: [2023-04-29 11:37:32,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 1: [2023-04-29 11:37:32,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +61: [2023-04-29 11:37:32,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +44: [2023-04-29 11:37:32,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +20: [2023-04-29 11:37:32,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 2: [2023-04-29 11:37:32,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 8: [2023-04-29 11:37:32,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +61: [2023-04-29 11:37:32,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +14: [2023-04-29 11:37:32,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +14: [2023-04-29 11:37:32,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +54: [2023-04-29 11:37:32,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +56: [2023-04-29 11:37:32,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +56: [2023-04-29 11:37:32,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +56: [2023-04-29 11:37:32,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +54: [2023-04-29 11:37:32,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +14: [2023-04-29 11:37:32,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +14: [2023-04-29 11:37:32,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +61: [2023-04-29 11:37:32,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +19: [2023-04-29 11:37:32,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +19: [2023-04-29 11:37:32,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +19: [2023-04-29 11:37:32,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +19: [2023-04-29 11:37:32,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +44: [2023-04-29 11:37:32,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... + 4: [2023-04-29 11:37:32,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 6: [2023-04-29 11:37:32,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +12: [2023-04-29 11:37:32,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +61: [2023-04-29 11:37:32,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 8: [2023-04-29 11:37:32,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... + 4: [2023-04-29 11:37:32,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 2: [2023-04-29 11:37:32,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +44: [2023-04-29 11:37:32,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +51: [2023-04-29 11:37:32,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +53: [2023-04-29 11:37:32,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +53: [2023-04-29 11:37:32,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +53: [2023-04-29 11:37:32,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +12: [2023-04-29 11:37:32,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +53: [2023-04-29 11:37:32,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +20: [2023-04-29 11:37:32,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 2: [2023-04-29 11:37:32,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +59: [2023-04-29 11:37:32,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +19: [2023-04-29 11:37:32,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +33: [2023-04-29 11:37:32,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +19: [2023-04-29 11:37:32,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +34: [2023-04-29 11:37:32,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +46: [2023-04-29 11:37:32,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +44: [2023-04-29 11:37:32,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +19: [2023-04-29 11:37:32,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 4: [2023-04-29 11:37:32,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 6: [2023-04-29 11:37:32,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +46: [2023-04-29 11:37:32,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +50: [2023-04-29 11:37:32,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +50: [2023-04-29 11:37:32,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +19: [2023-04-29 11:37:32,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 2: [2023-04-29 11:37:32,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +26: [2023-04-29 11:37:32,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +26: [2023-04-29 11:37:32,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +20: [2023-04-29 11:37:32,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +20: [2023-04-29 11:37:32,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +34: [2023-04-29 11:37:32,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +50: [2023-04-29 11:37:32,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +53: [2023-04-29 11:37:32,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +50: [2023-04-29 11:37:32,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +46: [2023-04-29 11:37:32,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +52: [2023-04-29 11:37:32,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +52: [2023-04-29 11:37:32,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +45: [2023-04-29 11:37:32,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +33: [2023-04-29 11:37:32,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +51: [2023-04-29 11:37:32,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +33: [2023-04-29 11:37:32,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +26: [2023-04-29 11:37:32,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +52: [2023-04-29 11:37:32,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +53: [2023-04-29 11:37:32,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 1: [2023-04-29 11:37:32,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +26: [2023-04-29 11:37:32,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +44: [2023-04-29 11:37:32,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +46: [2023-04-29 11:37:32,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +49: [2023-04-29 11:37:32,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +49: [2023-04-29 11:37:32,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +33: [2023-04-29 11:37:32,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +53: [2023-04-29 11:37:32,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +53: [2023-04-29 11:37:32,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +55: [2023-04-29 11:37:32,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +49: [2023-04-29 11:37:32,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +51: [2023-04-29 11:37:32,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +51: [2023-04-29 11:37:32,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +44: [2023-04-29 11:37:32,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +33: [2023-04-29 11:37:32,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +12: [2023-04-29 11:37:32,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +52: [2023-04-29 11:37:32,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +55: [2023-04-29 11:37:32,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +55: [2023-04-29 11:37:32,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +44: [2023-04-29 11:37:32,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +55: [2023-04-29 11:37:32,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +33: [2023-04-29 11:37:32,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +12: [2023-04-29 11:37:32,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +49: [2023-04-29 11:37:32,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 1: [2023-04-29 11:37:32,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 1: [2023-04-29 11:37:32,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 1: [2023-04-29 11:37:32,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +18: [2023-04-29 11:37:32,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +12: [2023-04-29 11:37:32,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 1: [2023-04-29 11:37:32,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 1: [2023-04-29 11:37:32,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +45: [2023-04-29 11:37:32,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +33: [2023-04-29 11:37:32,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... + 1: [2023-04-29 11:37:32,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +12: [2023-04-29 11:37:32,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +12: [2023-04-29 11:37:32,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +33: [2023-04-29 11:37:32,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +12: [2023-04-29 11:37:32,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +33: [2023-04-29 11:37:32,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +34: [2023-04-29 11:37:32,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +33: [2023-04-29 11:37:32,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +18: [2023-04-29 11:37:32,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +56: [2023-04-29 11:37:32,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 7: [2023-04-29 11:37:32,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +44: [2023-04-29 11:37:32,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +18: [2023-04-29 11:37:32,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +59: [2023-04-29 11:37:32,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +37: [2023-04-29 11:37:32,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +37: [2023-04-29 11:37:32,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +37: [2023-04-29 11:37:32,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +37: [2023-04-29 11:37:32,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +45: [2023-04-29 11:37:32,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +59: [2023-04-29 11:37:32,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +59: [2023-04-29 11:37:32,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +14: [2023-04-29 11:37:32,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +34: [2023-04-29 11:37:32,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +45: [2023-04-29 11:37:32,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 7: [2023-04-29 11:37:32,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 7: [2023-04-29 11:37:32,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +31: [2023-04-29 11:37:32,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 1: [2023-04-29 11:37:32,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 7: [2023-04-29 11:37:32,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +57: [2023-04-29 11:37:32,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 8: [2023-04-29 11:37:32,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +14: [2023-04-29 11:37:32,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +56: [2023-04-29 11:37:32,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +56: [2023-04-29 11:37:32,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +56: [2023-04-29 11:37:32,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +59: [2023-04-29 11:37:32,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +14: [2023-04-29 11:37:32,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +14: [2023-04-29 11:37:32,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +57: [2023-04-29 11:37:32,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +24: [2023-04-29 11:37:32,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +34: [2023-04-29 11:37:32,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +24: [2023-04-29 11:37:32,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +57: [2023-04-29 11:37:32,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +34: [2023-04-29 11:37:32,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +24: [2023-04-29 11:37:32,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +31: [2023-04-29 11:37:32,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +50: [2023-04-29 11:37:32,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +57: [2023-04-29 11:37:32,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 6: [2023-04-29 11:37:32,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +41: [2023-04-29 11:37:32,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +41: [2023-04-29 11:37:32,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +50: [2023-04-29 11:37:32,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 1: [2023-04-29 11:37:32,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +51: [2023-04-29 11:37:32,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +26: [2023-04-29 11:37:32,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +26: [2023-04-29 11:37:32,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +52: [2023-04-29 11:37:32,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +16: [2023-04-29 11:37:32,278] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +16: [2023-04-29 11:37:32,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +16: [2023-04-29 11:37:32,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +16: [2023-04-29 11:37:32,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +41: [2023-04-29 11:37:32,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +24: [2023-04-29 11:37:32,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +26: [2023-04-29 11:37:32,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +41: [2023-04-29 11:37:32,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +26: [2023-04-29 11:37:32,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +31: [2023-04-29 11:37:32,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +31: [2023-04-29 11:37:32,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +50: [2023-04-29 11:37:32,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +52: [2023-04-29 11:37:32,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +18: [2023-04-29 11:37:32,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +50: [2023-04-29 11:37:32,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 1: [2023-04-29 11:37:32,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +61: [2023-04-29 11:37:32,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +61: [2023-04-29 11:37:32,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +61: [2023-04-29 11:37:32,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +61: [2023-04-29 11:37:32,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +51: [2023-04-29 11:37:32,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +27: [2023-04-29 11:37:32,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +51: [2023-04-29 11:37:32,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +18: [2023-04-29 11:37:32,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 7: [2023-04-29 11:37:32,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +14: [2023-04-29 11:37:32,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +14: [2023-04-29 11:37:32,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +14: [2023-04-29 11:37:32,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +15: [2023-04-29 11:37:32,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +15: [2023-04-29 11:37:32,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +52: [2023-04-29 11:37:32,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +14: [2023-04-29 11:37:32,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +37: [2023-04-29 11:37:32,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +51: [2023-04-29 11:37:32,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +27: [2023-04-29 11:37:32,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +27: [2023-04-29 11:37:32,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 1: [2023-04-29 11:37:32,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +15: [2023-04-29 11:37:32,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +34: [2023-04-29 11:37:32,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +31: [2023-04-29 11:37:32,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +31: [2023-04-29 11:37:32,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +52: [2023-04-29 11:37:32,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +61: [2023-04-29 11:37:32,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +27: [2023-04-29 11:37:32,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +15: [2023-04-29 11:37:32,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +59: [2023-04-29 11:37:32,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +59: [2023-04-29 11:37:32,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +59: [2023-04-29 11:37:32,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +61: [2023-04-29 11:37:32,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +27: [2023-04-29 11:37:32,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +15: [2023-04-29 11:37:32,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +61: [2023-04-29 11:37:32,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +37: [2023-04-29 11:37:32,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +61: [2023-04-29 11:37:32,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +15: [2023-04-29 11:37:32,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +37: [2023-04-29 11:37:32,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +37: [2023-04-29 11:37:32,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +14: [2023-04-29 11:37:32,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +15: [2023-04-29 11:37:32,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +27: [2023-04-29 11:37:32,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +11: [2023-04-29 11:37:32,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +11: [2023-04-29 11:37:32,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +27: [2023-04-29 11:37:32,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +14: [2023-04-29 11:37:32,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +18: [2023-04-29 11:37:32,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +18: [2023-04-29 11:37:32,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +14: [2023-04-29 11:37:32,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +34: [2023-04-29 11:37:32,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +11: [2023-04-29 11:37:32,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 2: [2023-04-29 11:37:32,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. + 2: [2023-04-29 11:37:32,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. + 2: [2023-04-29 11:37:32,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +14: [2023-04-29 11:37:32,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +15: [2023-04-29 11:37:32,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +11: [2023-04-29 11:37:32,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +27: [2023-04-29 11:37:32,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... + 2: [2023-04-29 11:37:32,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. + 7: [2023-04-29 11:37:32,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 7: [2023-04-29 11:37:32,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +48: [2023-04-29 11:37:32,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +48: [2023-04-29 11:37:32,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +48: [2023-04-29 11:37:32,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +48: [2023-04-29 11:37:32,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +48: [2023-04-29 11:37:32,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +48: [2023-04-29 11:37:32,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +48: [2023-04-29 11:37:32,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +48: [2023-04-29 11:37:32,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +31: [2023-04-29 11:37:32,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +57: [2023-04-29 11:37:32,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +31: [2023-04-29 11:37:32,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +31: [2023-04-29 11:37:32,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +31: [2023-04-29 11:37:32,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +24: [2023-04-29 11:37:32,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +24: [2023-04-29 11:37:32,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +24: [2023-04-29 11:37:32,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 7: [2023-04-29 11:37:32,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +11: [2023-04-29 11:37:32,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +57: [2023-04-29 11:37:32,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +11: [2023-04-29 11:37:32,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +11: [2023-04-29 11:37:32,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +57: [2023-04-29 11:37:32,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +11: [2023-04-29 11:37:32,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +48: [2023-04-29 11:37:32,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +57: [2023-04-29 11:37:32,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +48: [2023-04-29 11:37:32,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +31: [2023-04-29 11:37:32,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +48: [2023-04-29 11:37:32,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +57: [2023-04-29 11:37:32,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +57: [2023-04-29 11:37:32,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +31: [2023-04-29 11:37:32,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +57: [2023-04-29 11:37:32,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +41: [2023-04-29 11:37:32,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +57: [2023-04-29 11:37:32,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +61: [2023-04-29 11:37:32,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +41: [2023-04-29 11:37:32,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +31: [2023-04-29 11:37:32,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +48: [2023-04-29 11:37:32,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +24: [2023-04-29 11:37:32,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +55: [2023-04-29 11:37:32,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +19: [2023-04-29 11:37:32,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +49: [2023-04-29 11:37:32,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +61: [2023-04-29 11:37:32,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +31: [2023-04-29 11:37:32,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +30: [2023-04-29 11:37:32,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +30: [2023-04-29 11:37:32,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +30: [2023-04-29 11:37:32,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +18: [2023-04-29 11:37:32,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +18: [2023-04-29 11:37:32,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +30: [2023-04-29 11:37:32,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +46: [2023-04-29 11:37:32,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +46: [2023-04-29 11:37:32,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +61: [2023-04-29 11:37:32,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +31: [2023-04-29 11:37:32,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +53: [2023-04-29 11:37:32,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +19: [2023-04-29 11:37:32,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +27: [2023-04-29 11:37:32,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +27: [2023-04-29 11:37:32,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +41: [2023-04-29 11:37:32,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +31: [2023-04-29 11:37:32,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +41: [2023-04-29 11:37:32,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +27: [2023-04-29 11:37:32,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +19: [2023-04-29 11:37:32,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +55: [2023-04-29 11:37:32,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... + 3: [2023-04-29 11:37:32,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 3: [2023-04-29 11:37:32,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 3: [2023-04-29 11:37:32,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 3: [2023-04-29 11:37:32,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +49: [2023-04-29 11:37:32,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +27: [2023-04-29 11:37:32,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +19: [2023-04-29 11:37:32,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +53: [2023-04-29 11:37:32,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +49: [2023-04-29 11:37:32,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +46: [2023-04-29 11:37:32,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +46: [2023-04-29 11:37:32,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +61: [2023-04-29 11:37:32,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +16: [2023-04-29 11:37:32,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +49: [2023-04-29 11:37:32,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +18: [2023-04-29 11:37:32,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +18: [2023-04-29 11:37:32,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... + 3: [2023-04-29 11:37:32,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 3: [2023-04-29 11:37:32,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +49: [2023-04-29 11:37:32,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +12: [2023-04-29 11:37:32,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +27: [2023-04-29 11:37:32,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +27: [2023-04-29 11:37:32,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +27: [2023-04-29 11:37:32,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +27: [2023-04-29 11:37:32,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +61: [2023-04-29 11:37:32,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +16: [2023-04-29 11:37:32,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +16: [2023-04-29 11:37:32,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +55: [2023-04-29 11:37:32,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 2: [2023-04-29 11:37:32,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +46: [2023-04-29 11:37:32,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +46: [2023-04-29 11:37:32,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +28: [2023-04-29 11:37:32,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +28: [2023-04-29 11:37:32,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. + 3: [2023-04-29 11:37:32,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +16: [2023-04-29 11:37:32,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +46: [2023-04-29 11:37:32,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... + 3: [2023-04-29 11:37:32,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +21: [2023-04-29 11:37:32,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +21: [2023-04-29 11:37:32,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +21: [2023-04-29 11:37:32,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +61: [2023-04-29 11:37:32,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +21: [2023-04-29 11:37:32,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +40: [2023-04-29 11:37:32,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +40: [2023-04-29 11:37:32,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +46: [2023-04-29 11:37:32,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +55: [2023-04-29 11:37:32,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +49: [2023-04-29 11:37:32,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +40: [2023-04-29 11:37:32,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +40: [2023-04-29 11:37:32,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +61: [2023-04-29 11:37:32,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +25: [2023-04-29 11:37:32,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +25: [2023-04-29 11:37:32,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +15: [2023-04-29 11:37:32,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +15: [2023-04-29 11:37:32,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +15: [2023-04-29 11:37:32,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +62: [2023-04-29 11:37:32,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +28: [2023-04-29 11:37:32,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +62: [2023-04-29 11:37:32,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +62: [2023-04-29 11:37:32,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +12: [2023-04-29 11:37:32,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +15: [2023-04-29 11:37:32,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +62: [2023-04-29 11:37:32,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +28: [2023-04-29 11:37:32,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +55: [2023-04-29 11:37:32,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +12: [2023-04-29 11:37:32,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +12: [2023-04-29 11:37:32,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 2: [2023-04-29 11:37:32,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 2: [2023-04-29 11:37:32,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +59: [2023-04-29 11:37:32,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +59: [2023-04-29 11:37:32,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +55: [2023-04-29 11:37:32,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +21: [2023-04-29 11:37:32,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +21: [2023-04-29 11:37:32,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +55: [2023-04-29 11:37:32,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +14: [2023-04-29 11:37:32,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +25: [2023-04-29 11:37:32,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +59: [2023-04-29 11:37:32,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. + 2: [2023-04-29 11:37:32,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +25: [2023-04-29 11:37:32,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +21: [2023-04-29 11:37:32,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +59: [2023-04-29 11:37:32,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. + 1: [2023-04-29 11:37:32,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +21: [2023-04-29 11:37:32,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +58: [2023-04-29 11:37:32,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +58: [2023-04-29 11:37:32,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +58: [2023-04-29 11:37:32,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +45: [2023-04-29 11:37:32,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +45: [2023-04-29 11:37:32,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +58: [2023-04-29 11:37:32,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. + 1: [2023-04-29 11:37:32,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +61: [2023-04-29 11:37:32,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +45: [2023-04-29 11:37:32,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +12: [2023-04-29 11:37:32,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +45: [2023-04-29 11:37:32,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +49: [2023-04-29 11:37:32,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +55: [2023-04-29 11:37:32,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... + 0: [2023-04-29 11:37:32,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 0: [2023-04-29 11:37:32,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 0: [2023-04-29 11:37:32,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +28: [2023-04-29 11:37:32,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +28: [2023-04-29 11:37:32,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +62: [2023-04-29 11:37:32,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +62: [2023-04-29 11:37:32,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 0: [2023-04-29 11:37:32,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +57: [2023-04-29 11:37:32,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +62: [2023-04-29 11:37:32,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +23: [2023-04-29 11:37:32,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +23: [2023-04-29 11:37:32,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +50: [2023-04-29 11:37:32,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +12: [2023-04-29 11:37:32,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +62: [2023-04-29 11:37:32,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +12: [2023-04-29 11:37:32,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +14: [2023-04-29 11:37:32,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +53: [2023-04-29 11:37:32,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +10: [2023-04-29 11:37:32,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +10: [2023-04-29 11:37:32,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +10: [2023-04-29 11:37:32,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +19: [2023-04-29 11:37:32,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +10: [2023-04-29 11:37:32,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. + 1: [2023-04-29 11:37:32,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +57: [2023-04-29 11:37:32,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +53: [2023-04-29 11:37:32,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +23: [2023-04-29 11:37:32,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. + 0: [2023-04-29 11:37:32,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +23: [2023-04-29 11:37:32,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +48: [2023-04-29 11:37:32,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +48: [2023-04-29 11:37:32,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +28: [2023-04-29 11:37:32,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +49: [2023-04-29 11:37:32,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... + 1: [2023-04-29 11:37:32,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... + 1: [2023-04-29 11:37:32,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +28: [2023-04-29 11:37:32,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +50: [2023-04-29 11:37:32,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +57: [2023-04-29 11:37:32,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +57: [2023-04-29 11:37:32,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 0: [2023-04-29 11:37:32,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +28: [2023-04-29 11:37:32,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 0: [2023-04-29 11:37:32,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +12: [2023-04-29 11:37:32,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +30: [2023-04-29 11:37:32,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 0: [2023-04-29 11:37:32,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +28: [2023-04-29 11:37:32,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +30: [2023-04-29 11:37:32,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +48: [2023-04-29 11:37:32,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +48: [2023-04-29 11:37:32,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +26: [2023-04-29 11:37:32,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +26: [2023-04-29 11:37:32,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. + 9: [2023-04-29 11:37:32,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +19: [2023-04-29 11:37:32,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +19: [2023-04-29 11:37:32,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +30: [2023-04-29 11:37:32,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +30: [2023-04-29 11:37:32,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 9: [2023-04-29 11:37:32,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +19: [2023-04-29 11:37:32,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 1: [2023-04-29 11:37:32,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 1: [2023-04-29 11:37:32,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... + 9: [2023-04-29 11:37:32,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +53: [2023-04-29 11:37:32,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +26: [2023-04-29 11:37:32,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +53: [2023-04-29 11:37:32,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +28: [2023-04-29 11:37:32,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +26: [2023-04-29 11:37:32,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +50: [2023-04-29 11:37:32,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +26: [2023-04-29 11:37:32,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +11: [2023-04-29 11:37:32,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +11: [2023-04-29 11:37:32,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +14: [2023-04-29 11:37:32,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +11: [2023-04-29 11:37:32,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +11: [2023-04-29 11:37:32,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +28: [2023-04-29 11:37:32,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +50: [2023-04-29 11:37:32,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +26: [2023-04-29 11:37:32,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +26: [2023-04-29 11:37:32,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +14: [2023-04-29 11:37:32,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +14: [2023-04-29 11:37:32,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 1: [2023-04-29 11:37:32,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +26: [2023-04-29 11:37:32,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +26: [2023-04-29 11:37:32,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +28: [2023-04-29 11:37:32,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +26: [2023-04-29 11:37:32,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +50: [2023-04-29 11:37:32,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +50: [2023-04-29 11:37:32,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +52: [2023-04-29 11:37:32,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +40: [2023-04-29 11:37:32,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +40: [2023-04-29 11:37:32,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +59: [2023-04-29 11:37:32,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +59: [2023-04-29 11:37:32,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +14: [2023-04-29 11:37:32,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +25: [2023-04-29 11:37:32,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +25: [2023-04-29 11:37:32,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +28: [2023-04-29 11:37:32,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +28: [2023-04-29 11:37:32,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +26: [2023-04-29 11:37:32,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +52: [2023-04-29 11:37:32,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +38: [2023-04-29 11:37:32,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +38: [2023-04-29 11:37:32,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +38: [2023-04-29 11:37:32,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +14: [2023-04-29 11:37:32,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +14: [2023-04-29 11:37:32,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +38: [2023-04-29 11:37:32,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +23: [2023-04-29 11:37:32,354] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +28: [2023-04-29 11:37:32,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +37: [2023-04-29 11:37:32,354] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +25: [2023-04-29 11:37:32,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +23: [2023-04-29 11:37:32,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +23: [2023-04-29 11:37:32,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +40: [2023-04-29 11:37:32,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +50: [2023-04-29 11:37:32,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +15: [2023-04-29 11:37:32,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +59: [2023-04-29 11:37:32,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +15: [2023-04-29 11:37:32,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +45: [2023-04-29 11:37:32,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +15: [2023-04-29 11:37:32,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +23: [2023-04-29 11:37:32,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +40: [2023-04-29 11:37:32,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +25: [2023-04-29 11:37:32,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +26: [2023-04-29 11:37:32,357] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +52: [2023-04-29 11:37:32,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +26: [2023-04-29 11:37:32,357] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +52: [2023-04-29 11:37:32,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +45: [2023-04-29 11:37:32,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +26: [2023-04-29 11:37:32,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +58: [2023-04-29 11:37:32,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +58: [2023-04-29 11:37:32,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +61: [2023-04-29 11:37:32,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +37: [2023-04-29 11:37:32,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +15: [2023-04-29 11:37:32,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +23: [2023-04-29 11:37:32,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +45: [2023-04-29 11:37:32,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +59: [2023-04-29 11:37:32,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +29: [2023-04-29 11:37:32,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +29: [2023-04-29 11:37:32,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +29: [2023-04-29 11:37:32,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +29: [2023-04-29 11:37:32,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +58: [2023-04-29 11:37:32,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +45: [2023-04-29 11:37:32,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +58: [2023-04-29 11:37:32,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +58: [2023-04-29 11:37:32,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +10: [2023-04-29 11:37:32,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +58: [2023-04-29 11:37:32,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +52: [2023-04-29 11:37:32,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +23: [2023-04-29 11:37:32,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +61: [2023-04-29 11:37:32,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +58: [2023-04-29 11:37:32,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +58: [2023-04-29 11:37:32,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +23: [2023-04-29 11:37:32,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +23: [2023-04-29 11:37:32,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +23: [2023-04-29 11:37:32,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +14: [2023-04-29 11:37:32,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +23: [2023-04-29 11:37:32,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +50: [2023-04-29 11:37:32,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +53: [2023-04-29 11:37:32,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +52: [2023-04-29 11:37:32,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +37: [2023-04-29 11:37:32,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +26: [2023-04-29 11:37:32,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +29: [2023-04-29 11:37:32,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +26: [2023-04-29 11:37:32,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +10: [2023-04-29 11:37:32,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +29: [2023-04-29 11:37:32,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +29: [2023-04-29 11:37:32,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +23: [2023-04-29 11:37:32,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +23: [2023-04-29 11:37:32,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +15: [2023-04-29 11:37:32,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +14: [2023-04-29 11:37:32,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +29: [2023-04-29 11:37:32,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +10: [2023-04-29 11:37:32,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +61: [2023-04-29 11:37:32,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +36: [2023-04-29 11:37:32,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +10: [2023-04-29 11:37:32,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +36: [2023-04-29 11:37:32,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +36: [2023-04-29 11:37:32,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +36: [2023-04-29 11:37:32,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +53: [2023-04-29 11:37:32,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +10: [2023-04-29 11:37:32,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +58: [2023-04-29 11:37:32,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +10: [2023-04-29 11:37:32,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +10: [2023-04-29 11:37:32,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +10: [2023-04-29 11:37:32,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +58: [2023-04-29 11:37:32,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +48: [2023-04-29 11:37:32,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +11: [2023-04-29 11:37:32,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +14: [2023-04-29 11:37:32,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +14: [2023-04-29 11:37:32,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +58: [2023-04-29 11:37:32,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +58: [2023-04-29 11:37:32,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +52: [2023-04-29 11:37:32,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +37: [2023-04-29 11:37:32,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +61: [2023-04-29 11:37:32,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +11: [2023-04-29 11:37:32,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +41: [2023-04-29 11:37:32,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +41: [2023-04-29 11:37:32,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 9: [2023-04-29 11:37:32,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +52: [2023-04-29 11:37:32,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +48: [2023-04-29 11:37:32,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +48: [2023-04-29 11:37:32,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +63: [2023-04-29 11:37:32,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +63: [2023-04-29 11:37:32,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +63: [2023-04-29 11:37:32,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +37: [2023-04-29 11:37:32,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +37: [2023-04-29 11:37:32,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +11: [2023-04-29 11:37:32,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +63: [2023-04-29 11:37:32,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +10: [2023-04-29 11:37:32,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 9: [2023-04-29 11:37:32,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +10: [2023-04-29 11:37:32,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +11: [2023-04-29 11:37:32,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 9: [2023-04-29 11:37:32,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +10: [2023-04-29 11:37:32,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +10: [2023-04-29 11:37:32,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 3: [2023-04-29 11:37:32,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. + 3: [2023-04-29 11:37:32,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. + 7: [2023-04-29 11:37:32,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. + 7: [2023-04-29 11:37:32,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. + 3: [2023-04-29 11:37:32,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. + 3: [2023-04-29 11:37:32,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +11: [2023-04-29 11:37:32,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +47: [2023-04-29 11:37:32,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +47: [2023-04-29 11:37:32,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +47: [2023-04-29 11:37:32,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +47: [2023-04-29 11:37:32,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. + 7: [2023-04-29 11:37:32,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +11: [2023-04-29 11:37:32,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 7: [2023-04-29 11:37:32,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +41: [2023-04-29 11:37:32,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +41: [2023-04-29 11:37:32,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +15: [2023-04-29 11:37:32,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +37: [2023-04-29 11:37:32,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +37: [2023-04-29 11:37:32,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +24: [2023-04-29 11:37:32,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +24: [2023-04-29 11:37:32,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +53: [2023-04-29 11:37:32,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +53: [2023-04-29 11:37:32,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +53: [2023-04-29 11:37:32,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +53: [2023-04-29 11:37:32,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. + 3: [2023-04-29 11:37:32,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +16: [2023-04-29 11:37:32,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +16: [2023-04-29 11:37:32,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +41: [2023-04-29 11:37:32,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +27: [2023-04-29 11:37:32,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +38: [2023-04-29 11:37:32,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +38: [2023-04-29 11:37:32,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +22: [2023-04-29 11:37:32,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +22: [2023-04-29 11:37:32,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +15: [2023-04-29 11:37:32,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +61: [2023-04-29 11:37:32,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 2: [2023-04-29 11:37:32,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +19: [2023-04-29 11:37:32,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +19: [2023-04-29 11:37:32,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +19: [2023-04-29 11:37:32,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +24: [2023-04-29 11:37:32,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +24: [2023-04-29 11:37:32,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. + 2: [2023-04-29 11:37:32,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +38: [2023-04-29 11:37:32,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +22: [2023-04-29 11:37:32,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +22: [2023-04-29 11:37:32,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +16: [2023-04-29 11:37:32,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +16: [2023-04-29 11:37:32,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +38: [2023-04-29 11:37:32,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 3: [2023-04-29 11:37:32,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +27: [2023-04-29 11:37:32,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +21: [2023-04-29 11:37:32,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +62: [2023-04-29 11:37:32,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +27: [2023-04-29 11:37:32,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +27: [2023-04-29 11:37:32,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 2: [2023-04-29 11:37:32,389] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... + 3: [2023-04-29 11:37:32,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +15: [2023-04-29 11:37:32,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 3: [2023-04-29 11:37:32,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +11: [2023-04-29 11:37:32,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 2: [2023-04-29 11:37:32,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +61: [2023-04-29 11:37:32,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +41: [2023-04-29 11:37:32,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +41: [2023-04-29 11:37:32,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +57: [2023-04-29 11:37:32,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +48: [2023-04-29 11:37:32,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +29: [2023-04-29 11:37:32,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +29: [2023-04-29 11:37:32,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +36: [2023-04-29 11:37:32,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +61: [2023-04-29 11:37:32,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +29: [2023-04-29 11:37:32,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +15: [2023-04-29 11:37:32,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +11: [2023-04-29 11:37:32,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +29: [2023-04-29 11:37:32,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +62: [2023-04-29 11:37:32,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +62: [2023-04-29 11:37:32,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. + 5: [2023-04-29 11:37:32,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. + 2: [2023-04-29 11:37:32,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +36: [2023-04-29 11:37:32,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +14: [2023-04-29 11:37:32,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +57: [2023-04-29 11:37:32,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +11: [2023-04-29 11:37:32,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +21: [2023-04-29 11:37:32,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +21: [2023-04-29 11:37:32,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +41: [2023-04-29 11:37:32,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +21: [2023-04-29 11:37:32,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +14: [2023-04-29 11:37:32,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +61: [2023-04-29 11:37:32,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 2: [2023-04-29 11:37:32,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +48: [2023-04-29 11:37:32,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +36: [2023-04-29 11:37:32,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 5: [2023-04-29 11:37:32,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +36: [2023-04-29 11:37:32,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +48: [2023-04-29 11:37:32,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +14: [2023-04-29 11:37:32,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 2: [2023-04-29 11:37:32,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... + 0: [2023-04-29 11:37:32,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 7: [2023-04-29 11:37:32,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +14: [2023-04-29 11:37:32,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +30: [2023-04-29 11:37:32,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 7: [2023-04-29 11:37:32,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 7: [2023-04-29 11:37:32,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +63: [2023-04-29 11:37:32,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 5: [2023-04-29 11:37:32,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +30: [2023-04-29 11:37:32,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +63: [2023-04-29 11:37:32,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +63: [2023-04-29 11:37:32,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +25: [2023-04-29 11:37:32,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +25: [2023-04-29 11:37:32,405] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +25: [2023-04-29 11:37:32,405] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +63: [2023-04-29 11:37:32,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... + 5: [2023-04-29 11:37:32,405] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +57: [2023-04-29 11:37:32,405] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +57: [2023-04-29 11:37:32,405] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +57: [2023-04-29 11:37:32,405] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +25: [2023-04-29 11:37:32,405] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 2: [2023-04-29 11:37:32,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... + 3: [2023-04-29 11:37:32,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 7: [2023-04-29 11:37:32,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 0: [2023-04-29 11:37:32,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 0: [2023-04-29 11:37:32,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 0: [2023-04-29 11:37:32,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +62: [2023-04-29 11:37:32,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +24: [2023-04-29 11:37:32,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +30: [2023-04-29 11:37:32,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +30: [2023-04-29 11:37:32,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +22: [2023-04-29 11:37:32,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +22: [2023-04-29 11:37:32,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +22: [2023-04-29 11:37:32,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 3: [2023-04-29 11:37:32,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +11: [2023-04-29 11:37:32,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 3: [2023-04-29 11:37:32,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 3: [2023-04-29 11:37:32,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +22: [2023-04-29 11:37:32,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +27: [2023-04-29 11:37:32,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +25: [2023-04-29 11:37:32,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +30: [2023-04-29 11:37:32,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +47: [2023-04-29 11:37:32,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +16: [2023-04-29 11:37:32,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +16: [2023-04-29 11:37:32,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +47: [2023-04-29 11:37:32,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +47: [2023-04-29 11:37:32,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +47: [2023-04-29 11:37:32,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +28: [2023-04-29 11:37:32,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +28: [2023-04-29 11:37:32,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +28: [2023-04-29 11:37:32,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +25: [2023-04-29 11:37:32,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 3: [2023-04-29 11:37:32,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +42: [2023-04-29 11:37:32,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +42: [2023-04-29 11:37:32,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +28: [2023-04-29 11:37:32,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +24: [2023-04-29 11:37:32,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... + 5: [2023-04-29 11:37:32,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +42: [2023-04-29 11:37:32,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +15: [2023-04-29 11:37:32,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +48: [2023-04-29 11:37:32,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +28: [2023-04-29 11:37:32,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +42: [2023-04-29 11:37:32,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +57: [2023-04-29 11:37:32,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +57: [2023-04-29 11:37:32,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +57: [2023-04-29 11:37:32,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +53: [2023-04-29 11:37:32,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 5: [2023-04-29 11:37:32,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +53: [2023-04-29 11:37:32,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +53: [2023-04-29 11:37:32,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +25: [2023-04-29 11:37:32,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +40: [2023-04-29 11:37:32,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +53: [2023-04-29 11:37:32,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +25: [2023-04-29 11:37:32,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +30: [2023-04-29 11:37:32,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +13: [2023-04-29 11:37:32,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +13: [2023-04-29 11:37:32,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +13: [2023-04-29 11:37:32,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +25: [2023-04-29 11:37:32,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +32: [2023-04-29 11:37:32,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +32: [2023-04-29 11:37:32,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +13: [2023-04-29 11:37:32,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +21: [2023-04-29 11:37:32,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +24: [2023-04-29 11:37:32,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +26: [2023-04-29 11:37:32,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +28: [2023-04-29 11:37:32,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +26: [2023-04-29 11:37:32,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +59: [2023-04-29 11:37:32,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +59: [2023-04-29 11:37:32,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 3: [2023-04-29 11:37:32,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +40: [2023-04-29 11:37:32,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +48: [2023-04-29 11:37:32,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +27: [2023-04-29 11:37:32,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +15: [2023-04-29 11:37:32,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +22: [2023-04-29 11:37:32,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +30: [2023-04-29 11:37:32,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +27: [2023-04-29 11:37:32,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +26: [2023-04-29 11:37:32,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +26: [2023-04-29 11:37:32,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +25: [2023-04-29 11:37:32,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +22: [2023-04-29 11:37:32,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +22: [2023-04-29 11:37:32,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +32: [2023-04-29 11:37:32,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +13: [2023-04-29 11:37:32,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +22: [2023-04-29 11:37:32,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +13: [2023-04-29 11:37:32,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +16: [2023-04-29 11:37:32,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +13: [2023-04-29 11:37:32,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +40: [2023-04-29 11:37:32,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +32: [2023-04-29 11:37:32,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +13: [2023-04-29 11:37:32,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +24: [2023-04-29 11:37:32,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +62: [2023-04-29 11:37:32,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +28: [2023-04-29 11:37:32,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +15: [2023-04-29 11:37:32,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +22: [2023-04-29 11:37:32,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +16: [2023-04-29 11:37:32,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +27: [2023-04-29 11:37:32,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +25: [2023-04-29 11:37:32,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +40: [2023-04-29 11:37:32,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... + 3: [2023-04-29 11:37:32,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +40: [2023-04-29 11:37:32,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +40: [2023-04-29 11:37:32,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +28: [2023-04-29 11:37:32,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +17: [2023-04-29 11:37:32,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +17: [2023-04-29 11:37:32,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +45: [2023-04-29 11:37:32,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +59: [2023-04-29 11:37:32,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +59: [2023-04-29 11:37:32,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... + 3: [2023-04-29 11:37:32,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +22: [2023-04-29 11:37:32,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +23: [2023-04-29 11:37:32,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +17: [2023-04-29 11:37:32,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +17: [2023-04-29 11:37:32,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +30: [2023-04-29 11:37:32,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +22: [2023-04-29 11:37:32,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +22: [2023-04-29 11:37:32,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +48: [2023-04-29 11:37:32,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +59: [2023-04-29 11:37:32,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +62: [2023-04-29 11:37:32,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +62: [2023-04-29 11:37:32,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 9: [2023-04-29 11:37:32,425] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,425] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +29: [2023-04-29 11:37:32,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +45: [2023-04-29 11:37:32,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +29: [2023-04-29 11:37:32,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +11: [2023-04-29 11:37:32,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +25: [2023-04-29 11:37:32,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +28: [2023-04-29 11:37:32,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +10: [2023-04-29 11:37:32,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +45: [2023-04-29 11:37:32,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +40: [2023-04-29 11:37:32,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... + 5: [2023-04-29 11:37:32,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +40: [2023-04-29 11:37:32,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +28: [2023-04-29 11:37:32,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... + 5: [2023-04-29 11:37:32,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +25: [2023-04-29 11:37:32,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +29: [2023-04-29 11:37:32,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +11: [2023-04-29 11:37:32,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +17: [2023-04-29 11:37:32,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +17: [2023-04-29 11:37:32,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +17: [2023-04-29 11:37:32,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +21: [2023-04-29 11:37:32,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +17: [2023-04-29 11:37:32,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +29: [2023-04-29 11:37:32,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +19: [2023-04-29 11:37:32,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_13-model_01-model_states.pt. +19: [2023-04-29 11:37:32,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +47: [2023-04-29 11:37:32,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +47: [2023-04-29 11:37:32,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +19: [2023-04-29 11:37:32,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +19: [2023-04-29 11:37:32,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +19: [2023-04-29 11:37:32,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +48: [2023-04-29 11:37:32,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +48: [2023-04-29 11:37:32,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +48: [2023-04-29 11:37:32,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +45: [2023-04-29 11:37:32,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +59: [2023-04-29 11:37:32,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt... +21: [2023-04-29 11:37:32,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +21: [2023-04-29 11:37:32,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +58: [2023-04-29 11:37:32,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +25: [2023-04-29 11:37:32,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +45: [2023-04-29 11:37:32,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... + 0: [2023-04-29 11:37:32,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +47: [2023-04-29 11:37:32,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +59: [2023-04-29 11:37:32,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +45: [2023-04-29 11:37:32,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +47: [2023-04-29 11:37:32,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +10: [2023-04-29 11:37:32,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... + 8: [2023-04-29 11:37:32,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +23: [2023-04-29 11:37:32,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 9: [2023-04-29 11:37:32,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +47: [2023-04-29 11:37:32,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +45: [2023-04-29 11:37:32,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +25: [2023-04-29 11:37:32,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +59: [2023-04-29 11:37:32,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +58: [2023-04-29 11:37:32,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +62: [2023-04-29 11:37:32,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 8: [2023-04-29 11:37:32,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +39: [2023-04-29 11:37:32,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +39: [2023-04-29 11:37:32,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +39: [2023-04-29 11:37:32,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +47: [2023-04-29 11:37:32,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +39: [2023-04-29 11:37:32,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +42: [2023-04-29 11:37:32,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +58: [2023-04-29 11:37:32,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +23: [2023-04-29 11:37:32,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +55: [2023-04-29 11:37:32,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +55: [2023-04-29 11:37:32,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +23: [2023-04-29 11:37:32,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +11: [2023-04-29 11:37:32,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +25: [2023-04-29 11:37:32,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +45: [2023-04-29 11:37:32,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +10: [2023-04-29 11:37:32,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +55: [2023-04-29 11:37:32,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +28: [2023-04-29 11:37:32,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +48: [2023-04-29 11:37:32,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... + 0: [2023-04-29 11:37:32,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 0: [2023-04-29 11:37:32,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +47: [2023-04-29 11:37:32,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +48: [2023-04-29 11:37:32,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... + 9: [2023-04-29 11:37:32,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +55: [2023-04-29 11:37:32,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +18: [2023-04-29 11:37:32,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +18: [2023-04-29 11:37:32,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +28: [2023-04-29 11:37:32,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +28: [2023-04-29 11:37:32,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 9: [2023-04-29 11:37:32,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +43: [2023-04-29 11:37:32,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +43: [2023-04-29 11:37:32,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +43: [2023-04-29 11:37:32,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +43: [2023-04-29 11:37:32,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +48: [2023-04-29 11:37:32,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +58: [2023-04-29 11:37:32,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +28: [2023-04-29 11:37:32,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +23: [2023-04-29 11:37:32,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... + 8: [2023-04-29 11:37:32,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 8: [2023-04-29 11:37:32,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +29: [2023-04-29 11:37:32,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +29: [2023-04-29 11:37:32,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 8: [2023-04-29 11:37:32,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +48: [2023-04-29 11:37:32,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +39: [2023-04-29 11:37:32,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 0: [2023-04-29 11:37:32,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +23: [2023-04-29 11:37:32,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +47: [2023-04-29 11:37:32,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +15: [2023-04-29 11:37:32,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +15: [2023-04-29 11:37:32,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +15: [2023-04-29 11:37:32,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +26: [2023-04-29 11:37:32,442] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +26: [2023-04-29 11:37:32,442] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +55: [2023-04-29 11:37:32,442] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +42: [2023-04-29 11:37:32,442] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +11: [2023-04-29 11:37:32,442] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +18: [2023-04-29 11:37:32,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +10: [2023-04-29 11:37:32,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +55: [2023-04-29 11:37:32,442] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +39: [2023-04-29 11:37:32,442] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +28: [2023-04-29 11:37:32,442] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +18: [2023-04-29 11:37:32,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +32: [2023-04-29 11:37:32,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +32: [2023-04-29 11:37:32,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +39: [2023-04-29 11:37:32,442] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +28: [2023-04-29 11:37:32,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +32: [2023-04-29 11:37:32,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +10: [2023-04-29 11:37:32,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +39: [2023-04-29 11:37:32,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +55: [2023-04-29 11:37:32,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +23: [2023-04-29 11:37:32,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +23: [2023-04-29 11:37:32,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +42: [2023-04-29 11:37:32,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +32: [2023-04-29 11:37:32,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +32: [2023-04-29 11:37:32,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +55: [2023-04-29 11:37:32,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +23: [2023-04-29 11:37:32,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +58: [2023-04-29 11:37:32,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +58: [2023-04-29 11:37:32,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +32: [2023-04-29 11:37:32,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +23: [2023-04-29 11:37:32,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +15: [2023-04-29 11:37:32,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +10: [2023-04-29 11:37:32,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +18: [2023-04-29 11:37:32,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +42: [2023-04-29 11:37:32,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +58: [2023-04-29 11:37:32,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +26: [2023-04-29 11:37:32,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +26: [2023-04-29 11:37:32,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +18: [2023-04-29 11:37:32,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +58: [2023-04-29 11:37:32,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +29: [2023-04-29 11:37:32,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +29: [2023-04-29 11:37:32,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +58: [2023-04-29 11:37:32,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +23: [2023-04-29 11:37:32,447] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +32: [2023-04-29 11:37:32,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +18: [2023-04-29 11:37:32,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +32: [2023-04-29 11:37:32,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +10: [2023-04-29 11:37:32,448] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +15: [2023-04-29 11:37:32,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +15: [2023-04-29 11:37:32,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +15: [2023-04-29 11:37:32,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +32: [2023-04-29 11:37:32,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +10: [2023-04-29 11:37:32,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +32: [2023-04-29 11:37:32,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +32: [2023-04-29 11:37:32,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +58: [2023-04-29 11:37:32,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +18: [2023-04-29 11:37:32,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +10: [2023-04-29 11:37:32,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +10: [2023-04-29 11:37:32,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +10: [2023-04-29 11:37:32,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +58: [2023-04-29 11:37:32,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +15: [2023-04-29 11:37:32,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +36: [2023-04-29 11:37:32,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +11: [2023-04-29 11:37:32,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +32: [2023-04-29 11:37:32,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +58: [2023-04-29 11:37:32,453] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +23: [2023-04-29 11:37:32,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +23: [2023-04-29 11:37:32,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +10: [2023-04-29 11:37:32,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... + 9: [2023-04-29 11:37:32,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +36: [2023-04-29 11:37:32,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... + 9: [2023-04-29 11:37:32,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... + 9: [2023-04-29 11:37:32,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +11: [2023-04-29 11:37:32,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +60: [2023-04-29 11:37:32,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +60: [2023-04-29 11:37:32,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +60: [2023-04-29 11:37:32,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +60: [2023-04-29 11:37:32,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +11: [2023-04-29 11:37:32,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 2: [2023-04-29 11:37:32,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 2: [2023-04-29 11:37:32,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,463] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +36: [2023-04-29 11:37:32,464] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +23: [2023-04-29 11:37:32,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +39: [2023-04-29 11:37:32,464] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +39: [2023-04-29 11:37:32,464] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +39: [2023-04-29 11:37:32,464] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. +39: [2023-04-29 11:37:32,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_38-model_01-model_states.pt. + 2: [2023-04-29 11:37:32,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +11: [2023-04-29 11:37:32,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 2: [2023-04-29 11:37:32,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +62: [2023-04-29 11:37:32,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +62: [2023-04-29 11:37:32,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +62: [2023-04-29 11:37:32,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +62: [2023-04-29 11:37:32,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +43: [2023-04-29 11:37:32,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +53: [2023-04-29 11:37:32,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +11: [2023-04-29 11:37:32,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +29: [2023-04-29 11:37:32,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +43: [2023-04-29 11:37:32,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +43: [2023-04-29 11:37:32,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +43: [2023-04-29 11:37:32,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +29: [2023-04-29 11:37:32,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 7: [2023-04-29 11:37:32,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +42: [2023-04-29 11:37:32,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +42: [2023-04-29 11:37:32,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +42: [2023-04-29 11:37:32,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 2: [2023-04-29 11:37:32,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +35: [2023-04-29 11:37:32,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +36: [2023-04-29 11:37:32,470] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +35: [2023-04-29 11:37:32,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +35: [2023-04-29 11:37:32,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +35: [2023-04-29 11:37:32,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. + 2: [2023-04-29 11:37:32,470] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 2: [2023-04-29 11:37:32,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +11: [2023-04-29 11:37:32,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +42: [2023-04-29 11:37:32,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +53: [2023-04-29 11:37:32,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... + 2: [2023-04-29 11:37:32,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +25: [2023-04-29 11:37:32,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +23: [2023-04-29 11:37:32,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +63: [2023-04-29 11:37:32,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +63: [2023-04-29 11:37:32,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 7: [2023-04-29 11:37:32,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +10: [2023-04-29 11:37:32,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 3: [2023-04-29 11:37:32,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +23: [2023-04-29 11:37:32,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +58: [2023-04-29 11:37:32,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +42: [2023-04-29 11:37:32,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +42: [2023-04-29 11:37:32,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 7: [2023-04-29 11:37:32,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +36: [2023-04-29 11:37:32,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +58: [2023-04-29 11:37:32,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +42: [2023-04-29 11:37:32,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 7: [2023-04-29 11:37:32,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +12: [2023-04-29 11:37:32,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +12: [2023-04-29 11:37:32,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +36: [2023-04-29 11:37:32,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +29: [2023-04-29 11:37:32,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +29: [2023-04-29 11:37:32,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +63: [2023-04-29 11:37:32,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +63: [2023-04-29 11:37:32,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 7: [2023-04-29 11:37:32,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +25: [2023-04-29 11:37:32,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 3: [2023-04-29 11:37:32,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +12: [2023-04-29 11:37:32,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 3: [2023-04-29 11:37:32,479] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +12: [2023-04-29 11:37:32,479] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +42: [2023-04-29 11:37:32,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +58: [2023-04-29 11:37:32,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +58: [2023-04-29 11:37:32,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +47: [2023-04-29 11:37:32,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +10: [2023-04-29 11:37:32,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 3: [2023-04-29 11:37:32,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +10: [2023-04-29 11:37:32,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +12: [2023-04-29 11:37:32,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +16: [2023-04-29 11:37:32,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +16: [2023-04-29 11:37:32,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +10: [2023-04-29 11:37:32,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +63: [2023-04-29 11:37:32,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +24: [2023-04-29 11:37:32,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +24: [2023-04-29 11:37:32,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 3: [2023-04-29 11:37:32,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 7: [2023-04-29 11:37:32,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +25: [2023-04-29 11:37:32,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 7: [2023-04-29 11:37:32,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +63: [2023-04-29 11:37:32,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +12: [2023-04-29 11:37:32,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +53: [2023-04-29 11:37:32,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +53: [2023-04-29 11:37:32,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +53: [2023-04-29 11:37:32,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 7: [2023-04-29 11:37:32,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +22: [2023-04-29 11:37:32,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +63: [2023-04-29 11:37:32,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +63: [2023-04-29 11:37:32,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... + 3: [2023-04-29 11:37:32,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +13: [2023-04-29 11:37:32,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +13: [2023-04-29 11:37:32,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 3: [2023-04-29 11:37:32,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +36: [2023-04-29 11:37:32,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +12: [2023-04-29 11:37:32,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +12: [2023-04-29 11:37:32,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +36: [2023-04-29 11:37:32,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +19: [2023-04-29 11:37:32,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +16: [2023-04-29 11:37:32,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +16: [2023-04-29 11:37:32,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +22: [2023-04-29 11:37:32,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +24: [2023-04-29 11:37:32,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +47: [2023-04-29 11:37:32,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +47: [2023-04-29 11:37:32,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 3: [2023-04-29 11:37:32,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +25: [2023-04-29 11:37:32,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +22: [2023-04-29 11:37:32,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +60: [2023-04-29 11:37:32,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +53: [2023-04-29 11:37:32,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +53: [2023-04-29 11:37:32,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +53: [2023-04-29 11:37:32,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +60: [2023-04-29 11:37:32,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +13: [2023-04-29 11:37:32,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +13: [2023-04-29 11:37:32,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +22: [2023-04-29 11:37:32,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +22: [2023-04-29 11:37:32,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +60: [2023-04-29 11:37:32,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +19: [2023-04-29 11:37:32,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +19: [2023-04-29 11:37:32,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +60: [2023-04-29 11:37:32,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +19: [2023-04-29 11:37:32,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +47: [2023-04-29 11:37:32,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +47: [2023-04-29 11:37:32,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +41: [2023-04-29 11:37:32,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +41: [2023-04-29 11:37:32,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +39: [2023-04-29 11:37:32,493] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +17: [2023-04-29 11:37:32,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 1: [2023-04-29 11:37:32,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 1: [2023-04-29 11:37:32,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 1: [2023-04-29 11:37:32,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 1: [2023-04-29 11:37:32,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +47: [2023-04-29 11:37:32,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +39: [2023-04-29 11:37:32,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +24: [2023-04-29 11:37:32,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +24: [2023-04-29 11:37:32,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +24: [2023-04-29 11:37:32,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +24: [2023-04-29 11:37:32,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +22: [2023-04-29 11:37:32,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +22: [2023-04-29 11:37:32,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +22: [2023-04-29 11:37:32,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +29: [2023-04-29 11:37:32,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +19: [2023-04-29 11:37:32,495] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +25: [2023-04-29 11:37:32,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +41: [2023-04-29 11:37:32,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +41: [2023-04-29 11:37:32,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +35: [2023-04-29 11:37:32,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +16: [2023-04-29 11:37:32,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +35: [2023-04-29 11:37:32,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +35: [2023-04-29 11:37:32,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 1: [2023-04-29 11:37:32,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 1: [2023-04-29 11:37:32,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +19: [2023-04-29 11:37:32,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +17: [2023-04-29 11:37:32,499] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +17: [2023-04-29 11:37:32,499] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +17: [2023-04-29 11:37:32,499] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +47: [2023-04-29 11:37:32,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... + 5: [2023-04-29 11:37:32,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +24: [2023-04-29 11:37:32,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... + 5: [2023-04-29 11:37:32,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +19: [2023-04-29 11:37:32,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +47: [2023-04-29 11:37:32,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +16: [2023-04-29 11:37:32,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +22: [2023-04-29 11:37:32,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +43: [2023-04-29 11:37:32,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +22: [2023-04-29 11:37:32,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +43: [2023-04-29 11:37:32,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +22: [2023-04-29 11:37:32,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 1: [2023-04-29 11:37:32,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +43: [2023-04-29 11:37:32,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +29: [2023-04-29 11:37:32,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +35: [2023-04-29 11:37:32,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +43: [2023-04-29 11:37:32,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +41: [2023-04-29 11:37:32,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 1: [2023-04-29 11:37:32,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 9: [2023-04-29 11:37:32,502] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,502] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +41: [2023-04-29 11:37:32,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +47: [2023-04-29 11:37:32,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +41: [2023-04-29 11:37:32,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 5: [2023-04-29 11:37:32,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +39: [2023-04-29 11:37:32,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +39: [2023-04-29 11:37:32,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt... +29: [2023-04-29 11:37:32,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +62: [2023-04-29 11:37:32,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +19: [2023-04-29 11:37:32,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +62: [2023-04-29 11:37:32,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +16: [2023-04-29 11:37:32,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +43: [2023-04-29 11:37:32,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 9: [2023-04-29 11:37:32,505] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +42: [2023-04-29 11:37:32,505] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +41: [2023-04-29 11:37:32,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +62: [2023-04-29 11:37:32,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +25: [2023-04-29 11:37:32,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +29: [2023-04-29 11:37:32,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... + 5: [2023-04-29 11:37:32,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +62: [2023-04-29 11:37:32,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +29: [2023-04-29 11:37:32,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_00-model_states.pt. +43: [2023-04-29 11:37:32,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +16: [2023-04-29 11:37:32,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +43: [2023-04-29 11:37:32,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +43: [2023-04-29 11:37:32,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 8: [2023-04-29 11:37:32,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +29: [2023-04-29 11:37:32,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +22: [2023-04-29 11:37:32,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +18: [2023-04-29 11:37:32,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +42: [2023-04-29 11:37:32,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +32: [2023-04-29 11:37:32,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +13: [2023-04-29 11:37:32,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +13: [2023-04-29 11:37:32,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +25: [2023-04-29 11:37:32,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 9: [2023-04-29 11:37:32,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +55: [2023-04-29 11:37:32,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +47: [2023-04-29 11:37:32,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +13: [2023-04-29 11:37:32,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +39: [2023-04-29 11:37:32,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +29: [2023-04-29 11:37:32,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +29: [2023-04-29 11:37:32,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt... +13: [2023-04-29 11:37:32,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +13: [2023-04-29 11:37:32,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. + 8: [2023-04-29 11:37:32,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +13: [2023-04-29 11:37:32,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +32: [2023-04-29 11:37:32,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +55: [2023-04-29 11:37:32,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +55: [2023-04-29 11:37:32,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +18: [2023-04-29 11:37:32,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +18: [2023-04-29 11:37:32,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +47: [2023-04-29 11:37:32,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +22: [2023-04-29 11:37:32,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +24: [2023-04-29 11:37:32,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +24: [2023-04-29 11:37:32,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +25: [2023-04-29 11:37:32,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +17: [2023-04-29 11:37:32,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +38: [2023-04-29 11:37:32,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +38: [2023-04-29 11:37:32,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +38: [2023-04-29 11:37:32,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +38: [2023-04-29 11:37:32,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +38: [2023-04-29 11:37:32,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +38: [2023-04-29 11:37:32,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +38: [2023-04-29 11:37:32,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +31: [2023-04-29 11:37:32,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +31: [2023-04-29 11:37:32,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +31: [2023-04-29 11:37:32,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +38: [2023-04-29 11:37:32,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +32: [2023-04-29 11:37:32,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +31: [2023-04-29 11:37:32,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +13: [2023-04-29 11:37:32,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +42: [2023-04-29 11:37:32,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +18: [2023-04-29 11:37:32,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +55: [2023-04-29 11:37:32,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +24: [2023-04-29 11:37:32,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +24: [2023-04-29 11:37:32,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +24: [2023-04-29 11:37:32,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +24: [2023-04-29 11:37:32,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +13: [2023-04-29 11:37:32,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +47: [2023-04-29 11:37:32,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +42: [2023-04-29 11:37:32,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +42: [2023-04-29 11:37:32,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +38: [2023-04-29 11:37:32,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +32: [2023-04-29 11:37:32,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +32: [2023-04-29 11:37:32,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +38: [2023-04-29 11:37:32,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 5: [2023-04-29 11:37:32,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +32: [2023-04-29 11:37:32,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +32: [2023-04-29 11:37:32,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +32: [2023-04-29 11:37:32,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +35: [2023-04-29 11:37:32,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +38: [2023-04-29 11:37:32,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +35: [2023-04-29 11:37:32,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +35: [2023-04-29 11:37:32,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +34: [2023-04-29 11:37:32,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +34: [2023-04-29 11:37:32,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +34: [2023-04-29 11:37:32,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +35: [2023-04-29 11:37:32,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +38: [2023-04-29 11:37:32,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +24: [2023-04-29 11:37:32,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +34: [2023-04-29 11:37:32,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +24: [2023-04-29 11:37:32,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +31: [2023-04-29 11:37:32,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +31: [2023-04-29 11:37:32,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +31: [2023-04-29 11:37:32,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +31: [2023-04-29 11:37:32,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +22: [2023-04-29 11:37:32,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +39: [2023-04-29 11:37:32,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +39: [2023-04-29 11:37:32,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +22: [2023-04-29 11:37:32,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +42: [2023-04-29 11:37:32,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +17: [2023-04-29 11:37:32,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +17: [2023-04-29 11:37:32,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +17: [2023-04-29 11:37:32,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +38: [2023-04-29 11:37:32,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +38: [2023-04-29 11:37:32,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +38: [2023-04-29 11:37:32,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +17: [2023-04-29 11:37:32,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +17: [2023-04-29 11:37:32,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +35: [2023-04-29 11:37:32,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +17: [2023-04-29 11:37:32,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +38: [2023-04-29 11:37:32,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +22: [2023-04-29 11:37:32,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +35: [2023-04-29 11:37:32,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +42: [2023-04-29 11:37:32,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... + 7: [2023-04-29 11:37:32,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 7: [2023-04-29 11:37:32,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +17: [2023-04-29 11:37:32,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +32: [2023-04-29 11:37:32,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... + 7: [2023-04-29 11:37:32,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 7: [2023-04-29 11:37:32,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +32: [2023-04-29 11:37:32,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +32: [2023-04-29 11:37:32,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... + 9: [2023-04-29 11:37:32,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 9: [2023-04-29 11:37:32,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +35: [2023-04-29 11:37:32,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +47: [2023-04-29 11:37:32,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +56: [2023-04-29 11:37:32,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +56: [2023-04-29 11:37:32,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +42: [2023-04-29 11:37:32,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... + 2: [2023-04-29 11:37:32,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +56: [2023-04-29 11:37:32,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +55: [2023-04-29 11:37:32,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +18: [2023-04-29 11:37:32,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +56: [2023-04-29 11:37:32,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. + 9: [2023-04-29 11:37:32,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +12: [2023-04-29 11:37:32,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +35: [2023-04-29 11:37:32,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +32: [2023-04-29 11:37:32,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +43: [2023-04-29 11:37:32,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +32: [2023-04-29 11:37:32,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 7: [2023-04-29 11:37:32,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 6: [2023-04-29 11:37:32,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 6: [2023-04-29 11:37:32,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. + 4: [2023-04-29 11:37:32,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. + 4: [2023-04-29 11:37:32,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. + 6: [2023-04-29 11:37:32,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +39: [2023-04-29 11:37:32,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +43: [2023-04-29 11:37:32,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +13: [2023-04-29 11:37:32,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 7: [2023-04-29 11:37:32,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 2: [2023-04-29 11:37:32,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 2: [2023-04-29 11:37:32,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 7: [2023-04-29 11:37:32,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +16: [2023-04-29 11:37:32,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +16: [2023-04-29 11:37:32,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +16: [2023-04-29 11:37:32,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 7: [2023-04-29 11:37:32,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +16: [2023-04-29 11:37:32,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +47: [2023-04-29 11:37:32,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +12: [2023-04-29 11:37:32,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 2: [2023-04-29 11:37:32,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 8: [2023-04-29 11:37:32,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 4: [2023-04-29 11:37:32,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +55: [2023-04-29 11:37:32,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +55: [2023-04-29 11:37:32,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +39: [2023-04-29 11:37:32,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +43: [2023-04-29 11:37:32,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +43: [2023-04-29 11:37:32,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +34: [2023-04-29 11:37:32,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +34: [2023-04-29 11:37:32,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +43: [2023-04-29 11:37:32,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +43: [2023-04-29 11:37:32,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... + 8: [2023-04-29 11:37:32,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +42: [2023-04-29 11:37:32,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +42: [2023-04-29 11:37:32,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +42: [2023-04-29 11:37:32,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +47: [2023-04-29 11:37:32,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +13: [2023-04-29 11:37:32,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +13: [2023-04-29 11:37:32,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 4: [2023-04-29 11:37:32,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +13: [2023-04-29 11:37:32,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +55: [2023-04-29 11:37:32,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +34: [2023-04-29 11:37:32,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 4: [2023-04-29 11:37:32,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 4: [2023-04-29 11:37:32,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +61: [2023-04-29 11:37:32,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +61: [2023-04-29 11:37:32,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +16: [2023-04-29 11:37:32,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 4: [2023-04-29 11:37:32,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +34: [2023-04-29 11:37:32,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +36: [2023-04-29 11:37:32,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +36: [2023-04-29 11:37:32,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +61: [2023-04-29 11:37:32,551] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +34: [2023-04-29 11:37:32,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +16: [2023-04-29 11:37:32,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +16: [2023-04-29 11:37:32,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +61: [2023-04-29 11:37:32,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +32: [2023-04-29 11:37:32,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +43: [2023-04-29 11:37:32,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +43: [2023-04-29 11:37:32,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +16: [2023-04-29 11:37:32,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +12: [2023-04-29 11:37:32,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +19: [2023-04-29 11:37:32,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +19: [2023-04-29 11:37:32,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +19: [2023-04-29 11:37:32,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +32: [2023-04-29 11:37:32,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +19: [2023-04-29 11:37:32,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +47: [2023-04-29 11:37:32,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +18: [2023-04-29 11:37:32,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +34: [2023-04-29 11:37:32,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +34: [2023-04-29 11:37:32,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +36: [2023-04-29 11:37:32,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +18: [2023-04-29 11:37:32,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +17: [2023-04-29 11:37:32,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +36: [2023-04-29 11:37:32,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +12: [2023-04-29 11:37:32,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +36: [2023-04-29 11:37:32,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +36: [2023-04-29 11:37:32,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +19: [2023-04-29 11:37:32,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +42: [2023-04-29 11:37:32,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +18: [2023-04-29 11:37:32,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +19: [2023-04-29 11:37:32,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +19: [2023-04-29 11:37:32,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +34: [2023-04-29 11:37:32,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +17: [2023-04-29 11:37:32,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +17: [2023-04-29 11:37:32,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +34: [2023-04-29 11:37:32,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +52: [2023-04-29 11:37:32,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +52: [2023-04-29 11:37:32,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +39: [2023-04-29 11:37:32,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +19: [2023-04-29 11:37:32,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +39: [2023-04-29 11:37:32,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +52: [2023-04-29 11:37:32,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +52: [2023-04-29 11:37:32,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. + 1: [2023-04-29 11:37:32,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +34: [2023-04-29 11:37:32,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +17: [2023-04-29 11:37:32,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +36: [2023-04-29 11:37:32,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +34: [2023-04-29 11:37:32,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +35: [2023-04-29 11:37:32,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +63: [2023-04-29 11:37:32,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +63: [2023-04-29 11:37:32,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 2: [2023-04-29 11:37:32,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +56: [2023-04-29 11:37:32,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +56: [2023-04-29 11:37:32,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +34: [2023-04-29 11:37:32,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +12: [2023-04-29 11:37:32,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 1: [2023-04-29 11:37:32,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +35: [2023-04-29 11:37:32,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +36: [2023-04-29 11:37:32,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +63: [2023-04-29 11:37:32,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +63: [2023-04-29 11:37:32,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +20: [2023-04-29 11:37:32,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +20: [2023-04-29 11:37:32,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +20: [2023-04-29 11:37:32,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +56: [2023-04-29 11:37:32,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +56: [2023-04-29 11:37:32,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +43: [2023-04-29 11:37:32,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +35: [2023-04-29 11:37:32,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +20: [2023-04-29 11:37:32,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +39: [2023-04-29 11:37:32,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. + 1: [2023-04-29 11:37:32,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +32: [2023-04-29 11:37:32,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +44: [2023-04-29 11:37:32,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +44: [2023-04-29 11:37:32,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +41: [2023-04-29 11:37:32,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +35: [2023-04-29 11:37:32,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +63: [2023-04-29 11:37:32,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +63: [2023-04-29 11:37:32,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +63: [2023-04-29 11:37:32,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +44: [2023-04-29 11:37:32,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +44: [2023-04-29 11:37:32,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +20: [2023-04-29 11:37:32,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +39: [2023-04-29 11:37:32,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +63: [2023-04-29 11:37:32,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 2: [2023-04-29 11:37:32,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +12: [2023-04-29 11:37:32,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +62: [2023-04-29 11:37:32,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +20: [2023-04-29 11:37:32,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +39: [2023-04-29 11:37:32,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... + 2: [2023-04-29 11:37:32,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +20: [2023-04-29 11:37:32,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 1: [2023-04-29 11:37:32,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +20: [2023-04-29 11:37:32,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +35: [2023-04-29 11:37:32,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +35: [2023-04-29 11:37:32,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +41: [2023-04-29 11:37:32,574] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 2: [2023-04-29 11:37:32,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +60: [2023-04-29 11:37:32,574] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +60: [2023-04-29 11:37:32,574] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +41: [2023-04-29 11:37:32,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +38: [2023-04-29 11:37:32,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 4: [2023-04-29 11:37:32,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +42: [2023-04-29 11:37:32,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +60: [2023-04-29 11:37:32,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +60: [2023-04-29 11:37:32,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +60: [2023-04-29 11:37:32,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +60: [2023-04-29 11:37:32,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +60: [2023-04-29 11:37:32,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +60: [2023-04-29 11:37:32,577] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +62: [2023-04-29 11:37:32,577] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +62: [2023-04-29 11:37:32,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +62: [2023-04-29 11:37:32,577] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +43: [2023-04-29 11:37:32,577] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +35: [2023-04-29 11:37:32,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +41: [2023-04-29 11:37:32,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +35: [2023-04-29 11:37:32,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +61: [2023-04-29 11:37:32,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +61: [2023-04-29 11:37:32,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +61: [2023-04-29 11:37:32,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +61: [2023-04-29 11:37:32,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +51: [2023-04-29 11:37:32,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +51: [2023-04-29 11:37:32,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +51: [2023-04-29 11:37:32,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +51: [2023-04-29 11:37:32,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +60: [2023-04-29 11:37:32,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +24: [2023-04-29 11:37:32,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +42: [2023-04-29 11:37:32,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +42: [2023-04-29 11:37:32,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +60: [2023-04-29 11:37:32,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +60: [2023-04-29 11:37:32,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +12: [2023-04-29 11:37:32,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +43: [2023-04-29 11:37:32,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +60: [2023-04-29 11:37:32,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +55: [2023-04-29 11:37:32,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +55: [2023-04-29 11:37:32,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +55: [2023-04-29 11:37:32,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +60: [2023-04-29 11:37:32,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +43: [2023-04-29 11:37:32,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +55: [2023-04-29 11:37:32,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +60: [2023-04-29 11:37:32,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +39: [2023-04-29 11:37:32,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +62: [2023-04-29 11:37:32,584] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +60: [2023-04-29 11:37:32,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +60: [2023-04-29 11:37:32,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +62: [2023-04-29 11:37:32,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +24: [2023-04-29 11:37:32,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +24: [2023-04-29 11:37:32,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 1: [2023-04-29 11:37:32,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +62: [2023-04-29 11:37:32,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +12: [2023-04-29 11:37:32,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +38: [2023-04-29 11:37:32,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +42: [2023-04-29 11:37:32,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +52: [2023-04-29 11:37:32,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +24: [2023-04-29 11:37:32,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +39: [2023-04-29 11:37:32,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +52: [2023-04-29 11:37:32,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +31: [2023-04-29 11:37:32,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +43: [2023-04-29 11:37:32,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 1: [2023-04-29 11:37:32,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +39: [2023-04-29 11:37:32,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_00-model_states.pt. +52: [2023-04-29 11:37:32,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +39: [2023-04-29 11:37:32,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +62: [2023-04-29 11:37:32,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +51: [2023-04-29 11:37:32,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +51: [2023-04-29 11:37:32,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +44: [2023-04-29 11:37:32,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +51: [2023-04-29 11:37:32,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +51: [2023-04-29 11:37:32,597] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +44: [2023-04-29 11:37:32,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +39: [2023-04-29 11:37:32,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +52: [2023-04-29 11:37:32,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +44: [2023-04-29 11:37:32,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +41: [2023-04-29 11:37:32,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +31: [2023-04-29 11:37:32,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +31: [2023-04-29 11:37:32,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +31: [2023-04-29 11:37:32,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +35: [2023-04-29 11:37:32,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +39: [2023-04-29 11:37:32,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt... +44: [2023-04-29 11:37:32,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +38: [2023-04-29 11:37:32,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +38: [2023-04-29 11:37:32,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +35: [2023-04-29 11:37:32,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +51: [2023-04-29 11:37:32,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 1: [2023-04-29 11:37:32,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 7: [2023-04-29 11:37:32,600] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 1: [2023-04-29 11:37:32,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +38: [2023-04-29 11:37:32,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +51: [2023-04-29 11:37:32,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +34: [2023-04-29 11:37:32,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +41: [2023-04-29 11:37:32,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,606] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +13: [2023-04-29 11:37:32,606] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +43: [2023-04-29 11:37:32,607] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +24: [2023-04-29 11:37:32,607] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +41: [2023-04-29 11:37:32,607] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +51: [2023-04-29 11:37:32,608] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +51: [2023-04-29 11:37:32,608] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,608] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +51: [2023-04-29 11:37:32,609] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +51: [2023-04-29 11:37:32,609] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 7: [2023-04-29 11:37:32,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 7: [2023-04-29 11:37:32,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +14: [2023-04-29 11:37:32,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +14: [2023-04-29 11:37:32,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 7: [2023-04-29 11:37:32,610] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +55: [2023-04-29 11:37:32,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +55: [2023-04-29 11:37:32,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +38: [2023-04-29 11:37:32,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +19: [2023-04-29 11:37:32,611] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +17: [2023-04-29 11:37:32,611] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 6: [2023-04-29 11:37:32,611] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +24: [2023-04-29 11:37:32,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +13: [2023-04-29 11:37:32,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +55: [2023-04-29 11:37:32,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +43: [2023-04-29 11:37:32,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +43: [2023-04-29 11:37:32,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +24: [2023-04-29 11:37:32,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +55: [2023-04-29 11:37:32,614] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +31: [2023-04-29 11:37:32,614] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +24: [2023-04-29 11:37:32,614] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +56: [2023-04-29 11:37:32,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +56: [2023-04-29 11:37:32,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +56: [2023-04-29 11:37:32,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +17: [2023-04-29 11:37:32,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +56: [2023-04-29 11:37:32,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +14: [2023-04-29 11:37:32,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +14: [2023-04-29 11:37:32,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +14: [2023-04-29 11:37:32,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +34: [2023-04-29 11:37:32,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +41: [2023-04-29 11:37:32,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +51: [2023-04-29 11:37:32,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 4: [2023-04-29 11:37:32,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +17: [2023-04-29 11:37:32,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +14: [2023-04-29 11:37:32,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +51: [2023-04-29 11:37:32,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +35: [2023-04-29 11:37:32,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +56: [2023-04-29 11:37:32,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +56: [2023-04-29 11:37:32,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +56: [2023-04-29 11:37:32,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +34: [2023-04-29 11:37:32,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +56: [2023-04-29 11:37:32,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +14: [2023-04-29 11:37:32,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +14: [2023-04-29 11:37:32,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +17: [2023-04-29 11:37:32,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +19: [2023-04-29 11:37:32,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +13: [2023-04-29 11:37:32,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +16: [2023-04-29 11:37:32,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +16: [2023-04-29 11:37:32,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +16: [2023-04-29 11:37:32,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +35: [2023-04-29 11:37:32,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +35: [2023-04-29 11:37:32,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +15: [2023-04-29 11:37:32,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +15: [2023-04-29 11:37:32,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +15: [2023-04-29 11:37:32,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +13: [2023-04-29 11:37:32,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +13: [2023-04-29 11:37:32,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +15: [2023-04-29 11:37:32,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +19: [2023-04-29 11:37:32,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +36: [2023-04-29 11:37:32,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +45: [2023-04-29 11:37:32,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +45: [2023-04-29 11:37:32,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +34: [2023-04-29 11:37:32,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +34: [2023-04-29 11:37:32,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +20: [2023-04-29 11:37:32,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +17: [2023-04-29 11:37:32,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +19: [2023-04-29 11:37:32,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +56: [2023-04-29 11:37:32,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +56: [2023-04-29 11:37:32,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +38: [2023-04-29 11:37:32,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +38: [2023-04-29 11:37:32,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +31: [2023-04-29 11:37:32,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +31: [2023-04-29 11:37:32,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +45: [2023-04-29 11:37:32,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +34: [2023-04-29 11:37:32,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 7: [2023-04-29 11:37:32,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +13: [2023-04-29 11:37:32,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +33: [2023-04-29 11:37:32,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +33: [2023-04-29 11:37:32,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +36: [2023-04-29 11:37:32,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +33: [2023-04-29 11:37:32,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +15: [2023-04-29 11:37:32,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +45: [2023-04-29 11:37:32,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +15: [2023-04-29 11:37:32,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +15: [2023-04-29 11:37:32,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +33: [2023-04-29 11:37:32,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +13: [2023-04-29 11:37:32,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +15: [2023-04-29 11:37:32,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +13: [2023-04-29 11:37:32,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +45: [2023-04-29 11:37:32,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +34: [2023-04-29 11:37:32,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +20: [2023-04-29 11:37:32,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +31: [2023-04-29 11:37:32,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +16: [2023-04-29 11:37:32,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +17: [2023-04-29 11:37:32,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +35: [2023-04-29 11:37:32,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +45: [2023-04-29 11:37:32,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +63: [2023-04-29 11:37:32,633] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +36: [2023-04-29 11:37:32,634] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +56: [2023-04-29 11:37:32,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +56: [2023-04-29 11:37:32,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +45: [2023-04-29 11:37:32,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +20: [2023-04-29 11:37:32,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +20: [2023-04-29 11:37:32,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +19: [2023-04-29 11:37:32,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +45: [2023-04-29 11:37:32,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +17: [2023-04-29 11:37:32,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... + 6: [2023-04-29 11:37:32,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +34: [2023-04-29 11:37:32,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +36: [2023-04-29 11:37:32,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +60: [2023-04-29 11:37:32,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 6: [2023-04-29 11:37:32,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +56: [2023-04-29 11:37:32,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +56: [2023-04-29 11:37:32,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +26: [2023-04-29 11:37:32,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +26: [2023-04-29 11:37:32,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +26: [2023-04-29 11:37:32,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +26: [2023-04-29 11:37:32,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +17: [2023-04-29 11:37:32,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +59: [2023-04-29 11:37:32,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +59: [2023-04-29 11:37:32,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 7: [2023-04-29 11:37:32,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +60: [2023-04-29 11:37:32,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +23: [2023-04-29 11:37:32,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +23: [2023-04-29 11:37:32,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +23: [2023-04-29 11:37:32,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +63: [2023-04-29 11:37:32,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +23: [2023-04-29 11:37:32,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +63: [2023-04-29 11:37:32,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +34: [2023-04-29 11:37:32,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +34: [2023-04-29 11:37:32,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +34: [2023-04-29 11:37:32,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +59: [2023-04-29 11:37:32,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +59: [2023-04-29 11:37:32,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 4: [2023-04-29 11:37:32,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 7: [2023-04-29 11:37:32,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +34: [2023-04-29 11:37:32,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +26: [2023-04-29 11:37:32,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +26: [2023-04-29 11:37:32,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +56: [2023-04-29 11:37:32,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +56: [2023-04-29 11:37:32,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +26: [2023-04-29 11:37:32,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +23: [2023-04-29 11:37:32,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +26: [2023-04-29 11:37:32,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +59: [2023-04-29 11:37:32,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +63: [2023-04-29 11:37:32,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 7: [2023-04-29 11:37:32,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +57: [2023-04-29 11:37:32,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +57: [2023-04-29 11:37:32,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +19: [2023-04-29 11:37:32,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +23: [2023-04-29 11:37:32,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +23: [2023-04-29 11:37:32,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +59: [2023-04-29 11:37:32,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 4: [2023-04-29 11:37:32,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +23: [2023-04-29 11:37:32,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +59: [2023-04-29 11:37:32,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +59: [2023-04-29 11:37:32,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +59: [2023-04-29 11:37:32,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +59: [2023-04-29 11:37:32,650] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +52: [2023-04-29 11:37:32,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +59: [2023-04-29 11:37:32,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +34: [2023-04-29 11:37:32,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +59: [2023-04-29 11:37:32,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +52: [2023-04-29 11:37:32,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +57: [2023-04-29 11:37:32,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +20: [2023-04-29 11:37:32,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +57: [2023-04-29 11:37:32,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +35: [2023-04-29 11:37:32,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +19: [2023-04-29 11:37:32,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +36: [2023-04-29 11:37:32,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +34: [2023-04-29 11:37:32,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +57: [2023-04-29 11:37:32,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +57: [2023-04-29 11:37:32,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +16: [2023-04-29 11:37:32,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +16: [2023-04-29 11:37:32,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +60: [2023-04-29 11:37:32,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +63: [2023-04-29 11:37:32,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +52: [2023-04-29 11:37:32,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +52: [2023-04-29 11:37:32,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +19: [2023-04-29 11:37:32,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +60: [2023-04-29 11:37:32,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +33: [2023-04-29 11:37:32,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +36: [2023-04-29 11:37:32,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +57: [2023-04-29 11:37:32,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +34: [2023-04-29 11:37:32,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +20: [2023-04-29 11:37:32,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +16: [2023-04-29 11:37:32,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +10: [2023-04-29 11:37:32,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +10: [2023-04-29 11:37:32,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +57: [2023-04-29 11:37:32,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +33: [2023-04-29 11:37:32,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +33: [2023-04-29 11:37:32,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +35: [2023-04-29 11:37:32,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +33: [2023-04-29 11:37:32,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +57: [2023-04-29 11:37:32,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +57: [2023-04-29 11:37:32,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +10: [2023-04-29 11:37:32,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +10: [2023-04-29 11:37:32,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +52: [2023-04-29 11:37:32,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +57: [2023-04-29 11:37:32,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +30: [2023-04-29 11:37:32,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +30: [2023-04-29 11:37:32,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +30: [2023-04-29 11:37:32,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +30: [2023-04-29 11:37:32,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +20: [2023-04-29 11:37:32,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +46: [2023-04-29 11:37:32,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +46: [2023-04-29 11:37:32,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +46: [2023-04-29 11:37:32,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +46: [2023-04-29 11:37:32,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +36: [2023-04-29 11:37:32,667] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +10: [2023-04-29 11:37:32,667] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +10: [2023-04-29 11:37:32,667] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +20: [2023-04-29 11:37:32,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +16: [2023-04-29 11:37:32,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +36: [2023-04-29 11:37:32,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +60: [2023-04-29 11:37:32,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +10: [2023-04-29 11:37:32,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +52: [2023-04-29 11:37:32,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +10: [2023-04-29 11:37:32,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +57: [2023-04-29 11:37:32,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +41: [2023-04-29 11:37:32,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +41: [2023-04-29 11:37:32,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +41: [2023-04-29 11:37:32,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +52: [2023-04-29 11:37:32,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +30: [2023-04-29 11:37:32,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +41: [2023-04-29 11:37:32,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +28: [2023-04-29 11:37:32,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +28: [2023-04-29 11:37:32,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +30: [2023-04-29 11:37:32,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +28: [2023-04-29 11:37:32,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +28: [2023-04-29 11:37:32,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +30: [2023-04-29 11:37:32,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 4: [2023-04-29 11:37:32,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +45: [2023-04-29 11:37:32,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +45: [2023-04-29 11:37:32,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +30: [2023-04-29 11:37:32,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +60: [2023-04-29 11:37:32,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +45: [2023-04-29 11:37:32,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +45: [2023-04-29 11:37:32,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. + 4: [2023-04-29 11:37:32,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +14: [2023-04-29 11:37:32,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +40: [2023-04-29 11:37:32,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +40: [2023-04-29 11:37:32,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +40: [2023-04-29 11:37:32,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +34: [2023-04-29 11:37:32,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +63: [2023-04-29 11:37:32,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +63: [2023-04-29 11:37:32,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +40: [2023-04-29 11:37:32,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +51: [2023-04-29 11:37:32,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +28: [2023-04-29 11:37:32,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +28: [2023-04-29 11:37:32,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 4: [2023-04-29 11:37:32,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +59: [2023-04-29 11:37:32,677] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +59: [2023-04-29 11:37:32,677] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +63: [2023-04-29 11:37:32,677] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +57: [2023-04-29 11:37:32,677] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +52: [2023-04-29 11:37:32,677] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +55: [2023-04-29 11:37:32,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +28: [2023-04-29 11:37:32,678] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +28: [2023-04-29 11:37:32,678] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +57: [2023-04-29 11:37:32,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +55: [2023-04-29 11:37:32,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +57: [2023-04-29 11:37:32,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +51: [2023-04-29 11:37:32,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +57: [2023-04-29 11:37:32,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +14: [2023-04-29 11:37:32,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +59: [2023-04-29 11:37:32,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +51: [2023-04-29 11:37:32,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +55: [2023-04-29 11:37:32,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +55: [2023-04-29 11:37:32,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +55: [2023-04-29 11:37:32,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +14: [2023-04-29 11:37:32,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +59: [2023-04-29 11:37:32,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +55: [2023-04-29 11:37:32,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +60: [2023-04-29 11:37:32,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 4: [2023-04-29 11:37:32,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +60: [2023-04-29 11:37:32,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +20: [2023-04-29 11:37:32,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +20: [2023-04-29 11:37:32,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +20: [2023-04-29 11:37:32,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +20: [2023-04-29 11:37:32,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +50: [2023-04-29 11:37:32,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +50: [2023-04-29 11:37:32,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +51: [2023-04-29 11:37:32,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +56: [2023-04-29 11:37:32,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +56: [2023-04-29 11:37:32,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +56: [2023-04-29 11:37:32,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +51: [2023-04-29 11:37:32,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +11: [2023-04-29 11:37:32,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +11: [2023-04-29 11:37:32,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +50: [2023-04-29 11:37:32,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +50: [2023-04-29 11:37:32,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +11: [2023-04-29 11:37:32,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +15: [2023-04-29 11:37:32,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +11: [2023-04-29 11:37:32,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +55: [2023-04-29 11:37:32,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +55: [2023-04-29 11:37:32,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +46: [2023-04-29 11:37:32,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +46: [2023-04-29 11:37:32,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +15: [2023-04-29 11:37:32,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +49: [2023-04-29 11:37:32,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +49: [2023-04-29 11:37:32,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +14: [2023-04-29 11:37:32,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +11: [2023-04-29 11:37:32,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +46: [2023-04-29 11:37:32,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +11: [2023-04-29 11:37:32,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +49: [2023-04-29 11:37:32,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +11: [2023-04-29 11:37:32,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +49: [2023-04-29 11:37:32,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +56: [2023-04-29 11:37:32,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +11: [2023-04-29 11:37:32,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +41: [2023-04-29 11:37:32,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +51: [2023-04-29 11:37:32,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +46: [2023-04-29 11:37:32,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +41: [2023-04-29 11:37:32,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +15: [2023-04-29 11:37:32,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +15: [2023-04-29 11:37:32,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +54: [2023-04-29 11:37:32,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +45: [2023-04-29 11:37:32,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +54: [2023-04-29 11:37:32,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +54: [2023-04-29 11:37:32,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +54: [2023-04-29 11:37:32,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +41: [2023-04-29 11:37:32,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +36: [2023-04-29 11:37:32,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +36: [2023-04-29 11:37:32,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +36: [2023-04-29 11:37:32,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +36: [2023-04-29 11:37:32,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +41: [2023-04-29 11:37:32,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +45: [2023-04-29 11:37:32,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +25: [2023-04-29 11:37:32,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +40: [2023-04-29 11:37:32,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +40: [2023-04-29 11:37:32,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +25: [2023-04-29 11:37:32,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +25: [2023-04-29 11:37:32,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +25: [2023-04-29 11:37:32,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +45: [2023-04-29 11:37:32,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +14: [2023-04-29 11:37:32,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +45: [2023-04-29 11:37:32,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +45: [2023-04-29 11:37:32,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +40: [2023-04-29 11:37:32,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +40: [2023-04-29 11:37:32,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +26: [2023-04-29 11:37:32,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +26: [2023-04-29 11:37:32,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +25: [2023-04-29 11:37:32,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +25: [2023-04-29 11:37:32,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +25: [2023-04-29 11:37:32,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +23: [2023-04-29 11:37:32,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +45: [2023-04-29 11:37:32,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +14: [2023-04-29 11:37:32,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +25: [2023-04-29 11:37:32,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +23: [2023-04-29 11:37:32,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +26: [2023-04-29 11:37:32,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +26: [2023-04-29 11:37:32,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +59: [2023-04-29 11:37:32,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +14: [2023-04-29 11:37:32,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +51: [2023-04-29 11:37:32,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +51: [2023-04-29 11:37:32,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +20: [2023-04-29 11:37:32,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +50: [2023-04-29 11:37:32,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +45: [2023-04-29 11:37:32,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +20: [2023-04-29 11:37:32,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +23: [2023-04-29 11:37:32,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +56: [2023-04-29 11:37:32,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +50: [2023-04-29 11:37:32,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +61: [2023-04-29 11:37:32,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +61: [2023-04-29 11:37:32,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +37: [2023-04-29 11:37:32,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +56: [2023-04-29 11:37:32,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +37: [2023-04-29 11:37:32,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +37: [2023-04-29 11:37:32,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +37: [2023-04-29 11:37:32,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +20: [2023-04-29 11:37:32,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +20: [2023-04-29 11:37:32,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +61: [2023-04-29 11:37:32,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +61: [2023-04-29 11:37:32,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +61: [2023-04-29 11:37:32,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +61: [2023-04-29 11:37:32,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +61: [2023-04-29 11:37:32,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +56: [2023-04-29 11:37:32,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +61: [2023-04-29 11:37:32,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +15: [2023-04-29 11:37:32,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +23: [2023-04-29 11:37:32,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +61: [2023-04-29 11:37:32,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +61: [2023-04-29 11:37:32,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +49: [2023-04-29 11:37:32,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +49: [2023-04-29 11:37:32,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +15: [2023-04-29 11:37:32,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +49: [2023-04-29 11:37:32,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +61: [2023-04-29 11:37:32,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +50: [2023-04-29 11:37:32,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +49: [2023-04-29 11:37:32,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +51: [2023-04-29 11:37:32,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +61: [2023-04-29 11:37:32,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +51: [2023-04-29 11:37:32,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +56: [2023-04-29 11:37:32,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +14: [2023-04-29 11:37:32,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +61: [2023-04-29 11:37:32,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... + 5: [2023-04-29 11:37:32,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +61: [2023-04-29 11:37:32,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +61: [2023-04-29 11:37:32,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +61: [2023-04-29 11:37:32,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +50: [2023-04-29 11:37:32,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +54: [2023-04-29 11:37:32,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +59: [2023-04-29 11:37:32,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +51: [2023-04-29 11:37:32,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +59: [2023-04-29 11:37:32,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +59: [2023-04-29 11:37:32,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +36: [2023-04-29 11:37:32,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +63: [2023-04-29 11:37:32,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +63: [2023-04-29 11:37:32,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +63: [2023-04-29 11:37:32,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +63: [2023-04-29 11:37:32,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +54: [2023-04-29 11:37:32,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +54: [2023-04-29 11:37:32,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +54: [2023-04-29 11:37:32,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +15: [2023-04-29 11:37:32,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +15: [2023-04-29 11:37:32,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +27: [2023-04-29 11:37:32,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +27: [2023-04-29 11:37:32,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +36: [2023-04-29 11:37:32,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +36: [2023-04-29 11:37:32,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +57: [2023-04-29 11:37:32,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +57: [2023-04-29 11:37:32,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +26: [2023-04-29 11:37:32,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 5: [2023-04-29 11:37:32,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +30: [2023-04-29 11:37:32,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +53: [2023-04-29 11:37:32,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +53: [2023-04-29 11:37:32,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +53: [2023-04-29 11:37:32,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. + 5: [2023-04-29 11:37:32,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +53: [2023-04-29 11:37:32,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. + 5: [2023-04-29 11:37:32,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 5: [2023-04-29 11:37:32,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +26: [2023-04-29 11:37:32,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +10: [2023-04-29 11:37:32,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +45: [2023-04-29 11:37:32,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +23: [2023-04-29 11:37:32,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +51: [2023-04-29 11:37:32,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +27: [2023-04-29 11:37:32,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +27: [2023-04-29 11:37:32,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +36: [2023-04-29 11:37:32,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +51: [2023-04-29 11:37:32,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +10: [2023-04-29 11:37:32,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +10: [2023-04-29 11:37:32,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +10: [2023-04-29 11:37:32,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +27: [2023-04-29 11:37:32,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +23: [2023-04-29 11:37:32,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +27: [2023-04-29 11:37:32,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +57: [2023-04-29 11:37:32,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +30: [2023-04-29 11:37:32,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +28: [2023-04-29 11:37:32,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +28: [2023-04-29 11:37:32,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +30: [2023-04-29 11:37:32,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +45: [2023-04-29 11:37:32,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +51: [2023-04-29 11:37:32,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... + 9: [2023-04-29 11:37:32,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +59: [2023-04-29 11:37:32,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +45: [2023-04-29 11:37:32,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 9: [2023-04-29 11:37:32,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +37: [2023-04-29 11:37:32,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +27: [2023-04-29 11:37:32,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +30: [2023-04-29 11:37:32,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +27: [2023-04-29 11:37:32,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +45: [2023-04-29 11:37:32,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +26: [2023-04-29 11:37:32,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +26: [2023-04-29 11:37:32,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 9: [2023-04-29 11:37:32,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +11: [2023-04-29 11:37:32,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +23: [2023-04-29 11:37:32,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +37: [2023-04-29 11:37:32,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +28: [2023-04-29 11:37:32,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +28: [2023-04-29 11:37:32,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 9: [2023-04-29 11:37:32,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +59: [2023-04-29 11:37:32,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +59: [2023-04-29 11:37:32,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +37: [2023-04-29 11:37:32,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +27: [2023-04-29 11:37:32,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +27: [2023-04-29 11:37:32,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +23: [2023-04-29 11:37:32,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +27: [2023-04-29 11:37:32,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +27: [2023-04-29 11:37:32,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. + 9: [2023-04-29 11:37:32,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +43: [2023-04-29 11:37:32,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +43: [2023-04-29 11:37:32,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +43: [2023-04-29 11:37:32,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +37: [2023-04-29 11:37:32,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +43: [2023-04-29 11:37:32,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +51: [2023-04-29 11:37:32,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +13: [2023-04-29 11:37:32,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +13: [2023-04-29 11:37:32,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +13: [2023-04-29 11:37:32,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +13: [2023-04-29 11:37:32,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +57: [2023-04-29 11:37:32,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +57: [2023-04-29 11:37:32,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +57: [2023-04-29 11:37:32,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +59: [2023-04-29 11:37:32,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +59: [2023-04-29 11:37:32,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +59: [2023-04-29 11:37:32,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +63: [2023-04-29 11:37:32,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +63: [2023-04-29 11:37:32,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 2: [2023-04-29 11:37:32,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 2: [2023-04-29 11:37:32,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +51: [2023-04-29 11:37:32,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +59: [2023-04-29 11:37:32,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +57: [2023-04-29 11:37:32,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +57: [2023-04-29 11:37:32,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +13: [2023-04-29 11:37:32,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +13: [2023-04-29 11:37:32,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +57: [2023-04-29 11:37:32,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 2: [2023-04-29 11:37:32,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +30: [2023-04-29 11:37:32,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +13: [2023-04-29 11:37:32,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 2: [2023-04-29 11:37:32,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +13: [2023-04-29 11:37:32,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +59: [2023-04-29 11:37:32,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +40: [2023-04-29 11:37:32,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +31: [2023-04-29 11:37:32,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +31: [2023-04-29 11:37:32,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +31: [2023-04-29 11:37:32,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +31: [2023-04-29 11:37:32,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +57: [2023-04-29 11:37:32,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +41: [2023-04-29 11:37:32,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +63: [2023-04-29 11:37:32,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +53: [2023-04-29 11:37:32,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 0: [2023-04-29 11:37:32,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. + 0: [2023-04-29 11:37:32,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +63: [2023-04-29 11:37:32,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 0: [2023-04-29 11:37:32,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. + 0: [2023-04-29 11:37:32,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +30: [2023-04-29 11:37:32,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +59: [2023-04-29 11:37:32,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +57: [2023-04-29 11:37:32,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +57: [2023-04-29 11:37:32,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... + 3: [2023-04-29 11:37:32,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 3: [2023-04-29 11:37:32,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 3: [2023-04-29 11:37:32,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +11: [2023-04-29 11:37:32,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +11: [2023-04-29 11:37:32,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 2: [2023-04-29 11:37:32,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 2: [2023-04-29 11:37:32,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 3: [2023-04-29 11:37:32,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +53: [2023-04-29 11:37:32,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +53: [2023-04-29 11:37:32,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 2: [2023-04-29 11:37:32,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +11: [2023-04-29 11:37:32,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +53: [2023-04-29 11:37:32,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +28: [2023-04-29 11:37:32,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 2: [2023-04-29 11:37:32,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 8: [2023-04-29 11:37:32,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. + 8: [2023-04-29 11:37:32,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. + 8: [2023-04-29 11:37:32,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +41: [2023-04-29 11:37:32,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +41: [2023-04-29 11:37:32,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +57: [2023-04-29 11:37:32,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +57: [2023-04-29 11:37:32,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +28: [2023-04-29 11:37:32,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +41: [2023-04-29 11:37:32,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +57: [2023-04-29 11:37:32,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +10: [2023-04-29 11:37:32,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +59: [2023-04-29 11:37:32,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +30: [2023-04-29 11:37:32,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +10: [2023-04-29 11:37:32,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +10: [2023-04-29 11:37:32,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +10: [2023-04-29 11:37:32,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +40: [2023-04-29 11:37:32,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +45: [2023-04-29 11:37:32,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +45: [2023-04-29 11:37:32,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +59: [2023-04-29 11:37:32,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +40: [2023-04-29 11:37:32,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +30: [2023-04-29 11:37:32,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +41: [2023-04-29 11:37:32,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 3: [2023-04-29 11:37:32,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 3: [2023-04-29 11:37:32,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +11: [2023-04-29 11:37:32,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 3: [2023-04-29 11:37:32,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +21: [2023-04-29 11:37:32,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +21: [2023-04-29 11:37:32,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +21: [2023-04-29 11:37:32,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +21: [2023-04-29 11:37:32,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +20: [2023-04-29 11:37:32,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +41: [2023-04-29 11:37:32,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... + 3: [2023-04-29 11:37:32,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +25: [2023-04-29 11:37:32,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +45: [2023-04-29 11:37:32,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +59: [2023-04-29 11:37:32,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +61: [2023-04-29 11:37:32,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +40: [2023-04-29 11:37:32,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +39: [2023-04-29 11:37:32,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +39: [2023-04-29 11:37:32,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +41: [2023-04-29 11:37:32,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +40: [2023-04-29 11:37:32,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +21: [2023-04-29 11:37:32,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +39: [2023-04-29 11:37:32,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +39: [2023-04-29 11:37:32,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_39-model_01-model_states.pt. +12: [2023-04-29 11:37:32,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +12: [2023-04-29 11:37:32,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +28: [2023-04-29 11:37:32,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +41: [2023-04-29 11:37:32,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +20: [2023-04-29 11:37:32,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +21: [2023-04-29 11:37:32,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +25: [2023-04-29 11:37:32,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +21: [2023-04-29 11:37:32,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +26: [2023-04-29 11:37:32,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +26: [2023-04-29 11:37:32,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +26: [2023-04-29 11:37:32,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +21: [2023-04-29 11:37:32,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +26: [2023-04-29 11:37:32,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +28: [2023-04-29 11:37:32,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +45: [2023-04-29 11:37:32,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +40: [2023-04-29 11:37:32,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +12: [2023-04-29 11:37:32,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +27: [2023-04-29 11:37:32,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +12: [2023-04-29 11:37:32,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +40: [2023-04-29 11:37:32,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +12: [2023-04-29 11:37:32,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +27: [2023-04-29 11:37:32,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +27: [2023-04-29 11:37:32,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +12: [2023-04-29 11:37:32,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +43: [2023-04-29 11:37:32,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +61: [2023-04-29 11:37:32,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +43: [2023-04-29 11:37:32,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +57: [2023-04-29 11:37:32,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +27: [2023-04-29 11:37:32,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +43: [2023-04-29 11:37:32,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +25: [2023-04-29 11:37:32,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +25: [2023-04-29 11:37:32,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +43: [2023-04-29 11:37:32,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +40: [2023-04-29 11:37:32,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +20: [2023-04-29 11:37:32,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +45: [2023-04-29 11:37:32,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +12: [2023-04-29 11:37:32,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 0: [2023-04-29 11:37:32,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 0: [2023-04-29 11:37:32,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 0: [2023-04-29 11:37:32,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 0: [2023-04-29 11:37:32,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +12: [2023-04-29 11:37:32,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +36: [2023-04-29 11:37:32,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +20: [2023-04-29 11:37:32,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +20: [2023-04-29 11:37:32,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +31: [2023-04-29 11:37:32,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +36: [2023-04-29 11:37:32,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 0: [2023-04-29 11:37:32,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +45: [2023-04-29 11:37:32,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +45: [2023-04-29 11:37:32,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +20: [2023-04-29 11:37:32,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... + 8: [2023-04-29 11:37:32,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +31: [2023-04-29 11:37:32,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +11: [2023-04-29 11:37:32,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +31: [2023-04-29 11:37:32,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +61: [2023-04-29 11:37:32,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +31: [2023-04-29 11:37:32,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 0: [2023-04-29 11:37:32,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +36: [2023-04-29 11:37:32,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +47: [2023-04-29 11:37:32,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +47: [2023-04-29 11:37:32,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +36: [2023-04-29 11:37:32,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... + 0: [2023-04-29 11:37:32,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 0: [2023-04-29 11:37:32,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 0: [2023-04-29 11:37:32,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 0: [2023-04-29 11:37:32,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 0: [2023-04-29 11:37:32,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +11: [2023-04-29 11:37:32,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 8: [2023-04-29 11:37:32,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +20: [2023-04-29 11:37:32,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +11: [2023-04-29 11:37:32,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +45: [2023-04-29 11:37:32,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... + 0: [2023-04-29 11:37:32,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +45: [2023-04-29 11:37:32,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +20: [2023-04-29 11:37:32,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +61: [2023-04-29 11:37:32,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +47: [2023-04-29 11:37:32,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +36: [2023-04-29 11:37:32,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +47: [2023-04-29 11:37:32,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +61: [2023-04-29 11:37:32,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 8: [2023-04-29 11:37:32,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 8: [2023-04-29 11:37:32,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +39: [2023-04-29 11:37:32,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +36: [2023-04-29 11:37:32,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +25: [2023-04-29 11:37:32,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +26: [2023-04-29 11:37:32,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 5: [2023-04-29 11:37:32,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 5: [2023-04-29 11:37:32,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +39: [2023-04-29 11:37:32,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +25: [2023-04-29 11:37:32,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +39: [2023-04-29 11:37:32,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +39: [2023-04-29 11:37:32,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt... +36: [2023-04-29 11:37:32,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +26: [2023-04-29 11:37:32,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +27: [2023-04-29 11:37:32,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +61: [2023-04-29 11:37:32,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +26: [2023-04-29 11:37:32,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +26: [2023-04-29 11:37:32,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +29: [2023-04-29 11:37:32,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +29: [2023-04-29 11:37:32,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +29: [2023-04-29 11:37:32,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +29: [2023-04-29 11:37:32,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +36: [2023-04-29 11:37:32,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +25: [2023-04-29 11:37:32,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +25: [2023-04-29 11:37:32,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 9: [2023-04-29 11:37:32,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +29: [2023-04-29 11:37:32,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +29: [2023-04-29 11:37:32,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +29: [2023-04-29 11:37:32,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +29: [2023-04-29 11:37:32,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 9: [2023-04-29 11:37:32,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +17: [2023-04-29 11:37:32,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +17: [2023-04-29 11:37:32,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +17: [2023-04-29 11:37:32,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +61: [2023-04-29 11:37:32,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +27: [2023-04-29 11:37:32,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +17: [2023-04-29 11:37:32,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +48: [2023-04-29 11:37:32,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +48: [2023-04-29 11:37:32,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +48: [2023-04-29 11:37:32,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +27: [2023-04-29 11:37:32,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +27: [2023-04-29 11:37:32,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +48: [2023-04-29 11:37:32,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. + 2: [2023-04-29 11:37:32,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +47: [2023-04-29 11:37:32,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +47: [2023-04-29 11:37:32,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +47: [2023-04-29 11:37:32,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 2: [2023-04-29 11:37:32,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +63: [2023-04-29 11:37:32,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +13: [2023-04-29 11:37:32,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +13: [2023-04-29 11:37:32,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +47: [2023-04-29 11:37:32,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +63: [2023-04-29 11:37:32,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +17: [2023-04-29 11:37:32,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +17: [2023-04-29 11:37:32,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +17: [2023-04-29 11:37:32,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +17: [2023-04-29 11:37:32,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +38: [2023-04-29 11:37:32,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +38: [2023-04-29 11:37:32,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +63: [2023-04-29 11:37:32,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +63: [2023-04-29 11:37:32,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +61: [2023-04-29 11:37:32,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +63: [2023-04-29 11:37:32,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +38: [2023-04-29 11:37:32,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +27: [2023-04-29 11:37:32,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 2: [2023-04-29 11:37:32,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +38: [2023-04-29 11:37:32,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. + 2: [2023-04-29 11:37:32,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +63: [2023-04-29 11:37:32,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +13: [2023-04-29 11:37:32,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +13: [2023-04-29 11:37:32,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 3: [2023-04-29 11:37:32,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +21: [2023-04-29 11:37:32,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 7: [2023-04-29 11:37:32,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 3: [2023-04-29 11:37:32,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 7: [2023-04-29 11:37:32,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 7: [2023-04-29 11:37:32,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 7: [2023-04-29 11:37:32,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +63: [2023-04-29 11:37:32,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +63: [2023-04-29 11:37:32,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... + 9: [2023-04-29 11:37:32,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 5: [2023-04-29 11:37:32,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 5: [2023-04-29 11:37:32,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 5: [2023-04-29 11:37:32,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 3: [2023-04-29 11:37:32,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 3: [2023-04-29 11:37:32,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 7: [2023-04-29 11:37:32,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 5: [2023-04-29 11:37:32,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 7: [2023-04-29 11:37:32,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 7: [2023-04-29 11:37:32,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +52: [2023-04-29 11:37:32,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +52: [2023-04-29 11:37:32,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. + 7: [2023-04-29 11:37:32,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +52: [2023-04-29 11:37:32,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +52: [2023-04-29 11:37:32,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +12: [2023-04-29 11:37:32,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +12: [2023-04-29 11:37:32,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +43: [2023-04-29 11:37:32,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +21: [2023-04-29 11:37:32,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +21: [2023-04-29 11:37:32,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +21: [2023-04-29 11:37:32,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +50: [2023-04-29 11:37:32,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +50: [2023-04-29 11:37:32,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +43: [2023-04-29 11:37:32,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +50: [2023-04-29 11:37:32,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +32: [2023-04-29 11:37:32,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +32: [2023-04-29 11:37:32,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +54: [2023-04-29 11:37:32,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +54: [2023-04-29 11:37:32,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +54: [2023-04-29 11:37:32,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +54: [2023-04-29 11:37:32,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +54: [2023-04-29 11:37:32,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +50: [2023-04-29 11:37:32,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +50: [2023-04-29 11:37:32,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +54: [2023-04-29 11:37:32,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +54: [2023-04-29 11:37:32,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +50: [2023-04-29 11:37:32,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +50: [2023-04-29 11:37:32,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +54: [2023-04-29 11:37:32,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +50: [2023-04-29 11:37:32,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +32: [2023-04-29 11:37:32,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +53: [2023-04-29 11:37:32,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +53: [2023-04-29 11:37:32,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +53: [2023-04-29 11:37:32,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +53: [2023-04-29 11:37:32,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +53: [2023-04-29 11:37:32,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +53: [2023-04-29 11:37:32,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +53: [2023-04-29 11:37:32,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +53: [2023-04-29 11:37:32,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +32: [2023-04-29 11:37:32,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +12: [2023-04-29 11:37:32,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 2: [2023-04-29 11:37:32,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 6: [2023-04-29 11:37:32,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 6: [2023-04-29 11:37:32,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 6: [2023-04-29 11:37:32,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +43: [2023-04-29 11:37:32,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +43: [2023-04-29 11:37:32,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +43: [2023-04-29 11:37:32,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +31: [2023-04-29 11:37:32,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +31: [2023-04-29 11:37:32,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +31: [2023-04-29 11:37:32,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 9: [2023-04-29 11:37:32,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +31: [2023-04-29 11:37:32,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +50: [2023-04-29 11:37:32,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +13: [2023-04-29 11:37:32,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +13: [2023-04-29 11:37:32,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 9: [2023-04-29 11:37:32,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 9: [2023-04-29 11:37:32,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +12: [2023-04-29 11:37:32,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +54: [2023-04-29 11:37:32,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +54: [2023-04-29 11:37:32,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +44: [2023-04-29 11:37:32,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +44: [2023-04-29 11:37:32,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +44: [2023-04-29 11:37:32,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +44: [2023-04-29 11:37:32,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +43: [2023-04-29 11:37:32,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +44: [2023-04-29 11:37:32,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +50: [2023-04-29 11:37:32,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +50: [2023-04-29 11:37:32,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +44: [2023-04-29 11:37:32,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +44: [2023-04-29 11:37:32,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +44: [2023-04-29 11:37:32,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +54: [2023-04-29 11:37:32,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +54: [2023-04-29 11:37:32,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +27: [2023-04-29 11:37:32,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +27: [2023-04-29 11:37:32,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 0: [2023-04-29 11:37:32,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 6: [2023-04-29 11:37:32,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +53: [2023-04-29 11:37:32,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +53: [2023-04-29 11:37:32,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... + 2: [2023-04-29 11:37:32,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +54: [2023-04-29 11:37:32,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... + 8: [2023-04-29 11:37:32,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +54: [2023-04-29 11:37:32,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +27: [2023-04-29 11:37:32,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +54: [2023-04-29 11:37:32,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +53: [2023-04-29 11:37:32,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +48: [2023-04-29 11:37:32,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +53: [2023-04-29 11:37:32,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +54: [2023-04-29 11:37:32,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +48: [2023-04-29 11:37:32,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +48: [2023-04-29 11:37:32,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +38: [2023-04-29 11:37:32,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +21: [2023-04-29 11:37:32,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +38: [2023-04-29 11:37:32,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +43: [2023-04-29 11:37:32,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +53: [2023-04-29 11:37:32,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +53: [2023-04-29 11:37:32,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +53: [2023-04-29 11:37:32,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +53: [2023-04-29 11:37:32,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +43: [2023-04-29 11:37:32,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +31: [2023-04-29 11:37:32,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +50: [2023-04-29 11:37:32,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +31: [2023-04-29 11:37:32,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +48: [2023-04-29 11:37:32,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +44: [2023-04-29 11:37:32,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +44: [2023-04-29 11:37:32,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +50: [2023-04-29 11:37:32,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +44: [2023-04-29 11:37:32,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +31: [2023-04-29 11:37:32,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +44: [2023-04-29 11:37:32,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +44: [2023-04-29 11:37:32,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +44: [2023-04-29 11:37:32,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +31: [2023-04-29 11:37:32,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +44: [2023-04-29 11:37:32,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... + 0: [2023-04-29 11:37:32,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +50: [2023-04-29 11:37:32,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +44: [2023-04-29 11:37:32,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 3: [2023-04-29 11:37:32,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +31: [2023-04-29 11:37:32,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +50: [2023-04-29 11:37:32,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 3: [2023-04-29 11:37:32,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +50: [2023-04-29 11:37:32,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... + 2: [2023-04-29 11:37:32,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +39: [2023-04-29 11:37:32,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +38: [2023-04-29 11:37:32,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +38: [2023-04-29 11:37:32,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +13: [2023-04-29 11:37:32,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +13: [2023-04-29 11:37:32,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +27: [2023-04-29 11:37:32,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +27: [2023-04-29 11:37:32,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 2: [2023-04-29 11:37:32,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +31: [2023-04-29 11:37:32,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +22: [2023-04-29 11:37:32,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +22: [2023-04-29 11:37:32,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +22: [2023-04-29 11:37:32,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 0: [2023-04-29 11:37:32,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +22: [2023-04-29 11:37:32,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 3: [2023-04-29 11:37:32,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +27: [2023-04-29 11:37:32,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +27: [2023-04-29 11:37:32,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +31: [2023-04-29 11:37:32,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... + 3: [2023-04-29 11:37:32,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +39: [2023-04-29 11:37:32,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +39: [2023-04-29 11:37:32,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +26: [2023-04-29 11:37:32,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +26: [2023-04-29 11:37:32,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 0: [2023-04-29 11:37:32,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 0: [2023-04-29 11:37:32,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +27: [2023-04-29 11:37:32,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +27: [2023-04-29 11:37:32,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +52: [2023-04-29 11:37:32,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +31: [2023-04-29 11:37:32,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 0: [2023-04-29 11:37:32,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 0: [2023-04-29 11:37:32,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 0: [2023-04-29 11:37:32,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +22: [2023-04-29 11:37:32,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +31: [2023-04-29 11:37:32,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +12: [2023-04-29 11:37:32,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +12: [2023-04-29 11:37:32,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +22: [2023-04-29 11:37:32,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +22: [2023-04-29 11:37:32,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +22: [2023-04-29 11:37:32,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 8: [2023-04-29 11:37:32,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +27: [2023-04-29 11:37:32,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... + 0: [2023-04-29 11:37:32,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +27: [2023-04-29 11:37:32,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +21: [2023-04-29 11:37:32,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +21: [2023-04-29 11:37:32,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +16: [2023-04-29 11:37:32,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +16: [2023-04-29 11:37:32,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +16: [2023-04-29 11:37:32,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +21: [2023-04-29 11:37:32,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +16: [2023-04-29 11:37:32,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +39: [2023-04-29 11:37:32,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... + 0: [2023-04-29 11:37:32,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +52: [2023-04-29 11:37:32,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +32: [2023-04-29 11:37:32,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +31: [2023-04-29 11:37:32,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +31: [2023-04-29 11:37:32,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... + 0: [2023-04-29 11:37:32,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +26: [2023-04-29 11:37:32,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +26: [2023-04-29 11:37:32,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +12: [2023-04-29 11:37:32,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +32: [2023-04-29 11:37:32,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +17: [2023-04-29 11:37:32,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 0: [2023-04-29 11:37:32,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +32: [2023-04-29 11:37:32,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +32: [2023-04-29 11:37:32,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +39: [2023-04-29 11:37:32,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +29: [2023-04-29 11:37:32,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +52: [2023-04-29 11:37:32,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +52: [2023-04-29 11:37:32,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +29: [2023-04-29 11:37:32,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +31: [2023-04-29 11:37:32,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +26: [2023-04-29 11:37:32,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +16: [2023-04-29 11:37:32,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +12: [2023-04-29 11:37:32,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +26: [2023-04-29 11:37:32,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +16: [2023-04-29 11:37:32,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +39: [2023-04-29 11:37:32,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_00-model_states.pt. +16: [2023-04-29 11:37:32,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +16: [2023-04-29 11:37:32,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +35: [2023-04-29 11:37:32,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +35: [2023-04-29 11:37:32,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +35: [2023-04-29 11:37:32,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +35: [2023-04-29 11:37:32,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. + 8: [2023-04-29 11:37:32,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +29: [2023-04-29 11:37:32,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +29: [2023-04-29 11:37:32,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +39: [2023-04-29 11:37:32,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... +26: [2023-04-29 11:37:32,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +26: [2023-04-29 11:37:32,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... + 8: [2023-04-29 11:37:32,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... + 8: [2023-04-29 11:37:32,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +39: [2023-04-29 11:37:32,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt... + 0: [2023-04-29 11:37:32,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 8: [2023-04-29 11:37:32,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 8: [2023-04-29 11:37:32,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 8: [2023-04-29 11:37:32,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 8: [2023-04-29 11:37:32,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 7: [2023-04-29 11:37:32,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +17: [2023-04-29 11:37:32,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +15: [2023-04-29 11:37:32,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +15: [2023-04-29 11:37:32,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +15: [2023-04-29 11:37:32,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 0: [2023-04-29 11:37:32,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +15: [2023-04-29 11:37:32,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 0: [2023-04-29 11:37:32,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 0: [2023-04-29 11:37:32,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +17: [2023-04-29 11:37:32,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +17: [2023-04-29 11:37:32,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +15: [2023-04-29 11:37:32,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +15: [2023-04-29 11:37:32,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +17: [2023-04-29 11:37:32,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +15: [2023-04-29 11:37:32,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +15: [2023-04-29 11:37:32,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 7: [2023-04-29 11:37:32,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 7: [2023-04-29 11:37:32,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 6: [2023-04-29 11:37:32,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +29: [2023-04-29 11:37:32,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 7: [2023-04-29 11:37:32,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +53: [2023-04-29 11:37:32,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +29: [2023-04-29 11:37:32,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +58: [2023-04-29 11:37:32,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +58: [2023-04-29 11:37:32,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +58: [2023-04-29 11:37:32,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +35: [2023-04-29 11:37:32,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +58: [2023-04-29 11:37:32,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +54: [2023-04-29 11:37:32,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +50: [2023-04-29 11:37:32,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +24: [2023-04-29 11:37:32,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +24: [2023-04-29 11:37:32,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +35: [2023-04-29 11:37:32,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +35: [2023-04-29 11:37:32,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +29: [2023-04-29 11:37:32,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +29: [2023-04-29 11:37:32,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +35: [2023-04-29 11:37:32,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +14: [2023-04-29 11:37:32,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +14: [2023-04-29 11:37:32,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +54: [2023-04-29 11:37:32,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +24: [2023-04-29 11:37:32,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +24: [2023-04-29 11:37:32,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +24: [2023-04-29 11:37:32,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +24: [2023-04-29 11:37:32,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +62: [2023-04-29 11:37:32,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +62: [2023-04-29 11:37:32,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +62: [2023-04-29 11:37:32,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +62: [2023-04-29 11:37:32,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +24: [2023-04-29 11:37:32,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +42: [2023-04-29 11:37:32,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +42: [2023-04-29 11:37:32,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +42: [2023-04-29 11:37:32,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +42: [2023-04-29 11:37:32,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +24: [2023-04-29 11:37:32,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +54: [2023-04-29 11:37:32,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +14: [2023-04-29 11:37:32,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +14: [2023-04-29 11:37:32,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 7: [2023-04-29 11:37:32,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +44: [2023-04-29 11:37:32,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +44: [2023-04-29 11:37:32,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +14: [2023-04-29 11:37:32,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +14: [2023-04-29 11:37:32,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +31: [2023-04-29 11:37:32,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +18: [2023-04-29 11:37:32,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +18: [2023-04-29 11:37:32,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +54: [2023-04-29 11:37:32,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 6: [2023-04-29 11:37:32,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 6: [2023-04-29 11:37:32,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +53: [2023-04-29 11:37:32,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +53: [2023-04-29 11:37:32,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +53: [2023-04-29 11:37:32,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +18: [2023-04-29 11:37:32,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +14: [2023-04-29 11:37:32,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +18: [2023-04-29 11:37:32,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +14: [2023-04-29 11:37:32,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +44: [2023-04-29 11:37:32,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +44: [2023-04-29 11:37:32,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +22: [2023-04-29 11:37:32,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +50: [2023-04-29 11:37:32,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +52: [2023-04-29 11:37:32,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +31: [2023-04-29 11:37:32,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +31: [2023-04-29 11:37:32,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +31: [2023-04-29 11:37:32,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +18: [2023-04-29 11:37:32,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +18: [2023-04-29 11:37:32,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +50: [2023-04-29 11:37:32,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +18: [2023-04-29 11:37:32,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +17: [2023-04-29 11:37:32,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +52: [2023-04-29 11:37:32,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +50: [2023-04-29 11:37:32,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +53: [2023-04-29 11:37:32,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +50: [2023-04-29 11:37:32,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +18: [2023-04-29 11:37:32,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +60: [2023-04-29 11:37:32,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +60: [2023-04-29 11:37:32,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +17: [2023-04-29 11:37:32,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +17: [2023-04-29 11:37:32,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +22: [2023-04-29 11:37:32,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +22: [2023-04-29 11:37:32,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +22: [2023-04-29 11:37:32,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +58: [2023-04-29 11:37:32,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +60: [2023-04-29 11:37:32,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. + 7: [2023-04-29 11:37:32,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +60: [2023-04-29 11:37:32,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +58: [2023-04-29 11:37:32,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +54: [2023-04-29 11:37:32,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 7: [2023-04-29 11:37:32,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +52: [2023-04-29 11:37:32,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +58: [2023-04-29 11:37:32,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +58: [2023-04-29 11:37:32,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +14: [2023-04-29 11:37:32,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +14: [2023-04-29 11:37:32,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +14: [2023-04-29 11:37:32,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +14: [2023-04-29 11:37:32,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +54: [2023-04-29 11:37:32,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +16: [2023-04-29 11:37:32,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 7: [2023-04-29 11:37:32,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +42: [2023-04-29 11:37:32,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +16: [2023-04-29 11:37:32,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +52: [2023-04-29 11:37:32,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... + 6: [2023-04-29 11:37:32,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +52: [2023-04-29 11:37:32,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +52: [2023-04-29 11:37:32,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +42: [2023-04-29 11:37:32,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +44: [2023-04-29 11:37:32,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +44: [2023-04-29 11:37:32,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +54: [2023-04-29 11:37:32,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +54: [2023-04-29 11:37:32,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 6: [2023-04-29 11:37:32,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +31: [2023-04-29 11:37:32,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +22: [2023-04-29 11:37:32,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 8: [2023-04-29 11:37:32,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +44: [2023-04-29 11:37:32,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +62: [2023-04-29 11:37:32,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +62: [2023-04-29 11:37:32,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +53: [2023-04-29 11:37:32,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +42: [2023-04-29 11:37:32,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +42: [2023-04-29 11:37:32,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +52: [2023-04-29 11:37:32,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... + 8: [2023-04-29 11:37:32,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +53: [2023-04-29 11:37:32,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +62: [2023-04-29 11:37:32,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +52: [2023-04-29 11:37:32,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +44: [2023-04-29 11:37:32,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +62: [2023-04-29 11:37:32,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +53: [2023-04-29 11:37:32,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +16: [2023-04-29 11:37:32,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +59: [2023-04-29 11:37:32,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +59: [2023-04-29 11:37:32,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +59: [2023-04-29 11:37:32,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +59: [2023-04-29 11:37:32,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +31: [2023-04-29 11:37:32,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +37: [2023-04-29 11:37:32,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +37: [2023-04-29 11:37:32,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +37: [2023-04-29 11:37:32,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +37: [2023-04-29 11:37:32,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +37: [2023-04-29 11:37:32,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +37: [2023-04-29 11:37:32,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +37: [2023-04-29 11:37:32,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +37: [2023-04-29 11:37:32,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +15: [2023-04-29 11:37:32,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +31: [2023-04-29 11:37:32,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +31: [2023-04-29 11:37:32,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +50: [2023-04-29 11:37:32,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +16: [2023-04-29 11:37:32,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 4: [2023-04-29 11:37:32,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +50: [2023-04-29 11:37:32,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 1: [2023-04-29 11:37:32,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +14: [2023-04-29 11:37:32,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 1: [2023-04-29 11:37:32,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 1: [2023-04-29 11:37:32,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 1: [2023-04-29 11:37:32,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +37: [2023-04-29 11:37:32,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +37: [2023-04-29 11:37:32,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... + 8: [2023-04-29 11:37:32,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 8: [2023-04-29 11:37:32,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +60: [2023-04-29 11:37:32,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +60: [2023-04-29 11:37:32,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +50: [2023-04-29 11:37:32,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +22: [2023-04-29 11:37:32,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +22: [2023-04-29 11:37:32,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 4: [2023-04-29 11:37:32,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 1: [2023-04-29 11:37:32,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +34: [2023-04-29 11:37:32,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +34: [2023-04-29 11:37:32,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. + 1: [2023-04-29 11:37:32,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 4: [2023-04-29 11:37:32,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 4: [2023-04-29 11:37:32,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 4: [2023-04-29 11:37:32,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +15: [2023-04-29 11:37:32,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +15: [2023-04-29 11:37:32,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 1: [2023-04-29 11:37:32,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +34: [2023-04-29 11:37:32,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +15: [2023-04-29 11:37:32,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +37: [2023-04-29 11:37:32,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +22: [2023-04-29 11:37:32,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +37: [2023-04-29 11:37:32,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +34: [2023-04-29 11:37:32,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +60: [2023-04-29 11:37:32,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +37: [2023-04-29 11:37:32,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... + 1: [2023-04-29 11:37:32,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +37: [2023-04-29 11:37:32,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +37: [2023-04-29 11:37:32,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +37: [2023-04-29 11:37:32,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +60: [2023-04-29 11:37:32,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +14: [2023-04-29 11:37:32,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +14: [2023-04-29 11:37:32,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +14: [2023-04-29 11:37:32,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +16: [2023-04-29 11:37:32,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +20: [2023-04-29 11:37:32,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +20: [2023-04-29 11:37:32,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +20: [2023-04-29 11:37:32,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +20: [2023-04-29 11:37:32,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +24: [2023-04-29 11:37:32,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +24: [2023-04-29 11:37:32,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +56: [2023-04-29 11:37:32,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +56: [2023-04-29 11:37:32,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +56: [2023-04-29 11:37:32,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +56: [2023-04-29 11:37:32,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +16: [2023-04-29 11:37:32,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +20: [2023-04-29 11:37:32,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +20: [2023-04-29 11:37:32,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +20: [2023-04-29 11:37:32,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +24: [2023-04-29 11:37:32,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +24: [2023-04-29 11:37:32,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +20: [2023-04-29 11:37:32,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 8: [2023-04-29 11:37:32,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 8: [2023-04-29 11:37:32,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +18: [2023-04-29 11:37:32,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +59: [2023-04-29 11:37:32,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +59: [2023-04-29 11:37:32,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +59: [2023-04-29 11:37:32,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +59: [2023-04-29 11:37:32,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +15: [2023-04-29 11:37:32,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +16: [2023-04-29 11:37:32,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +14: [2023-04-29 11:37:32,998] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +14: [2023-04-29 11:37:32,998] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +18: [2023-04-29 11:37:32,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +18: [2023-04-29 11:37:32,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +15: [2023-04-29 11:37:33,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +16: [2023-04-29 11:37:33,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +34: [2023-04-29 11:37:33,001] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +34: [2023-04-29 11:37:33,001] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +15: [2023-04-29 11:37:33,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 8: [2023-04-29 11:37:33,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 8: [2023-04-29 11:37:33,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +15: [2023-04-29 11:37:33,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +14: [2023-04-29 11:37:33,003] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +24: [2023-04-29 11:37:33,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +34: [2023-04-29 11:37:33,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +40: [2023-04-29 11:37:33,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +34: [2023-04-29 11:37:33,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +40: [2023-04-29 11:37:33,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +40: [2023-04-29 11:37:33,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +40: [2023-04-29 11:37:33,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +56: [2023-04-29 11:37:33,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +56: [2023-04-29 11:37:33,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +56: [2023-04-29 11:37:33,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +24: [2023-04-29 11:37:33,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +18: [2023-04-29 11:37:33,010] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +24: [2023-04-29 11:37:33,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +56: [2023-04-29 11:37:33,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +18: [2023-04-29 11:37:33,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +40: [2023-04-29 11:37:33,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +24: [2023-04-29 11:37:33,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +14: [2023-04-29 11:37:33,013] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +40: [2023-04-29 11:37:33,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +40: [2023-04-29 11:37:33,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +40: [2023-04-29 11:37:33,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +19: [2023-04-29 11:37:33,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +19: [2023-04-29 11:37:33,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +19: [2023-04-29 11:37:33,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +19: [2023-04-29 11:37:33,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +61: [2023-04-29 11:37:33,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +61: [2023-04-29 11:37:33,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +30: [2023-04-29 11:37:33,020] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +30: [2023-04-29 11:37:33,020] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +30: [2023-04-29 11:37:33,020] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +30: [2023-04-29 11:37:33,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +19: [2023-04-29 11:37:33,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +19: [2023-04-29 11:37:33,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +61: [2023-04-29 11:37:33,022] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +19: [2023-04-29 11:37:33,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +61: [2023-04-29 11:37:33,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +19: [2023-04-29 11:37:33,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +18: [2023-04-29 11:37:33,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +14: [2023-04-29 11:37:33,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +18: [2023-04-29 11:37:33,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 1: [2023-04-29 11:37:33,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. + 1: [2023-04-29 11:37:33,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. + 1: [2023-04-29 11:37:33,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +51: [2023-04-29 11:37:33,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +51: [2023-04-29 11:37:33,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +51: [2023-04-29 11:37:33,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. + 1: [2023-04-29 11:37:33,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +51: [2023-04-29 11:37:33,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +14: [2023-04-29 11:37:33,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +37: [2023-04-29 11:37:33,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +26: [2023-04-29 11:37:33,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +26: [2023-04-29 11:37:33,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +26: [2023-04-29 11:37:33,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +14: [2023-04-29 11:37:33,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +26: [2023-04-29 11:37:33,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +14: [2023-04-29 11:37:33,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +43: [2023-04-29 11:37:33,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +43: [2023-04-29 11:37:33,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +43: [2023-04-29 11:37:33,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +43: [2023-04-29 11:37:33,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +57: [2023-04-29 11:37:33,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +57: [2023-04-29 11:37:33,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +57: [2023-04-29 11:37:33,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +57: [2023-04-29 11:37:33,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. + 1: [2023-04-29 11:37:33,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 4: [2023-04-29 11:37:33,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 4: [2023-04-29 11:37:33,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 4: [2023-04-29 11:37:33,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +18: [2023-04-29 11:37:33,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +14: [2023-04-29 11:37:33,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +26: [2023-04-29 11:37:33,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +26: [2023-04-29 11:37:33,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +26: [2023-04-29 11:37:33,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +26: [2023-04-29 11:37:33,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 4: [2023-04-29 11:37:33,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 1: [2023-04-29 11:37:33,044] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +59: [2023-04-29 11:37:33,044] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +30: [2023-04-29 11:37:33,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +10: [2023-04-29 11:37:33,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +10: [2023-04-29 11:37:33,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +10: [2023-04-29 11:37:33,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +10: [2023-04-29 11:37:33,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +14: [2023-04-29 11:37:33,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +25: [2023-04-29 11:37:33,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +25: [2023-04-29 11:37:33,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +20: [2023-04-29 11:37:33,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +61: [2023-04-29 11:37:33,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +61: [2023-04-29 11:37:33,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +61: [2023-04-29 11:37:33,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +25: [2023-04-29 11:37:33,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +59: [2023-04-29 11:37:33,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +25: [2023-04-29 11:37:33,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +41: [2023-04-29 11:37:33,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +41: [2023-04-29 11:37:33,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +30: [2023-04-29 11:37:33,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +41: [2023-04-29 11:37:33,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +41: [2023-04-29 11:37:33,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +37: [2023-04-29 11:37:33,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +37: [2023-04-29 11:37:33,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +37: [2023-04-29 11:37:33,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +30: [2023-04-29 11:37:33,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +12: [2023-04-29 11:37:33,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +12: [2023-04-29 11:37:33,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +12: [2023-04-29 11:37:33,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +61: [2023-04-29 11:37:33,052] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +12: [2023-04-29 11:37:33,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +20: [2023-04-29 11:37:33,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +30: [2023-04-29 11:37:33,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +11: [2023-04-29 11:37:33,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +11: [2023-04-29 11:37:33,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +21: [2023-04-29 11:37:33,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +21: [2023-04-29 11:37:33,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +11: [2023-04-29 11:37:33,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +45: [2023-04-29 11:37:33,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +45: [2023-04-29 11:37:33,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +45: [2023-04-29 11:37:33,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +11: [2023-04-29 11:37:33,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. + 1: [2023-04-29 11:37:33,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +45: [2023-04-29 11:37:33,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +21: [2023-04-29 11:37:33,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +21: [2023-04-29 11:37:33,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. + 1: [2023-04-29 11:37:33,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +20: [2023-04-29 11:37:33,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +20: [2023-04-29 11:37:33,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +39: [2023-04-29 11:37:33,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +59: [2023-04-29 11:37:33,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +59: [2023-04-29 11:37:33,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +18: [2023-04-29 11:37:33,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +18: [2023-04-29 11:37:33,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +18: [2023-04-29 11:37:33,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +51: [2023-04-29 11:37:33,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +51: [2023-04-29 11:37:33,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +18: [2023-04-29 11:37:33,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +39: [2023-04-29 11:37:33,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +37: [2023-04-29 11:37:33,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +59: [2023-04-29 11:37:33,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. + 1: [2023-04-29 11:37:33,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +14: [2023-04-29 11:37:33,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +14: [2023-04-29 11:37:33,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +14: [2023-04-29 11:37:33,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 1: [2023-04-29 11:37:33,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +39: [2023-04-29 11:37:33,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +39: [2023-04-29 11:37:33,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_40-model_01-model_states.pt. +59: [2023-04-29 11:37:33,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +51: [2023-04-29 11:37:33,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +59: [2023-04-29 11:37:33,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +57: [2023-04-29 11:37:33,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +55: [2023-04-29 11:37:33,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +55: [2023-04-29 11:37:33,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +55: [2023-04-29 11:37:33,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +59: [2023-04-29 11:37:33,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +51: [2023-04-29 11:37:33,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +55: [2023-04-29 11:37:33,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +57: [2023-04-29 11:37:33,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +57: [2023-04-29 11:37:33,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +14: [2023-04-29 11:37:33,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +14: [2023-04-29 11:37:33,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... + 4: [2023-04-29 11:37:33,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +57: [2023-04-29 11:37:33,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +43: [2023-04-29 11:37:33,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +43: [2023-04-29 11:37:33,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 4: [2023-04-29 11:37:33,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +13: [2023-04-29 11:37:33,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +13: [2023-04-29 11:37:33,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 4: [2023-04-29 11:37:33,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +13: [2023-04-29 11:37:33,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +20: [2023-04-29 11:37:33,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +13: [2023-04-29 11:37:33,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +43: [2023-04-29 11:37:33,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +14: [2023-04-29 11:37:33,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +43: [2023-04-29 11:37:33,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... + 4: [2023-04-29 11:37:33,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +25: [2023-04-29 11:37:33,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +12: [2023-04-29 11:37:33,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +40: [2023-04-29 11:37:33,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +10: [2023-04-29 11:37:33,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +25: [2023-04-29 11:37:33,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +41: [2023-04-29 11:37:33,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +41: [2023-04-29 11:37:33,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +20: [2023-04-29 11:37:33,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +21: [2023-04-29 11:37:33,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +25: [2023-04-29 11:37:33,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +10: [2023-04-29 11:37:33,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +10: [2023-04-29 11:37:33,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +10: [2023-04-29 11:37:33,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +21: [2023-04-29 11:37:33,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +11: [2023-04-29 11:37:33,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +25: [2023-04-29 11:37:33,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +40: [2023-04-29 11:37:33,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +40: [2023-04-29 11:37:33,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. + 6: [2023-04-29 11:37:33,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +45: [2023-04-29 11:37:33,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 6: [2023-04-29 11:37:33,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. + 6: [2023-04-29 11:37:33,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. + 6: [2023-04-29 11:37:33,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +45: [2023-04-29 11:37:33,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +12: [2023-04-29 11:37:33,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +11: [2023-04-29 11:37:33,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +11: [2023-04-29 11:37:33,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +45: [2023-04-29 11:37:33,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +12: [2023-04-29 11:37:33,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +11: [2023-04-29 11:37:33,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +12: [2023-04-29 11:37:33,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +40: [2023-04-29 11:37:33,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +18: [2023-04-29 11:37:33,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +40: [2023-04-29 11:37:33,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +18: [2023-04-29 11:37:33,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +45: [2023-04-29 11:37:33,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +37: [2023-04-29 11:37:33,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +30: [2023-04-29 11:37:33,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +20: [2023-04-29 11:37:33,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +20: [2023-04-29 11:37:33,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +30: [2023-04-29 11:37:33,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +30: [2023-04-29 11:37:33,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +19: [2023-04-29 11:37:33,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +19: [2023-04-29 11:37:33,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +63: [2023-04-29 11:37:33,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +63: [2023-04-29 11:37:33,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +41: [2023-04-29 11:37:33,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +63: [2023-04-29 11:37:33,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +41: [2023-04-29 11:37:33,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +37: [2023-04-29 11:37:33,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +30: [2023-04-29 11:37:33,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +40: [2023-04-29 11:37:33,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +63: [2023-04-29 11:37:33,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +40: [2023-04-29 11:37:33,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +40: [2023-04-29 11:37:33,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +39: [2023-04-29 11:37:33,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +37: [2023-04-29 11:37:33,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +21: [2023-04-29 11:37:33,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +19: [2023-04-29 11:37:33,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +18: [2023-04-29 11:37:33,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +39: [2023-04-29 11:37:33,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +21: [2023-04-29 11:37:33,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +30: [2023-04-29 11:37:33,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +30: [2023-04-29 11:37:33,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +19: [2023-04-29 11:37:33,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +18: [2023-04-29 11:37:33,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +39: [2023-04-29 11:37:33,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +55: [2023-04-29 11:37:33,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +55: [2023-04-29 11:37:33,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +30: [2023-04-29 11:37:33,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +30: [2023-04-29 11:37:33,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +13: [2023-04-29 11:37:33,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +55: [2023-04-29 11:37:33,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +39: [2023-04-29 11:37:33,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt... +55: [2023-04-29 11:37:33,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +55: [2023-04-29 11:37:33,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +58: [2023-04-29 11:37:33,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +58: [2023-04-29 11:37:33,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +58: [2023-04-29 11:37:33,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +58: [2023-04-29 11:37:33,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +58: [2023-04-29 11:37:33,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +58: [2023-04-29 11:37:33,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +58: [2023-04-29 11:37:33,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +55: [2023-04-29 11:37:33,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +58: [2023-04-29 11:37:33,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +55: [2023-04-29 11:37:33,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +55: [2023-04-29 11:37:33,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +17: [2023-04-29 11:37:33,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +17: [2023-04-29 11:37:33,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +17: [2023-04-29 11:37:33,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +17: [2023-04-29 11:37:33,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +55: [2023-04-29 11:37:33,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +40: [2023-04-29 11:37:33,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +13: [2023-04-29 11:37:33,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +13: [2023-04-29 11:37:33,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +13: [2023-04-29 11:37:33,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +55: [2023-04-29 11:37:33,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +58: [2023-04-29 11:37:33,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +58: [2023-04-29 11:37:33,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +58: [2023-04-29 11:37:33,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +58: [2023-04-29 11:37:33,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +58: [2023-04-29 11:37:33,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +58: [2023-04-29 11:37:33,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +26: [2023-04-29 11:37:33,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +58: [2023-04-29 11:37:33,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +58: [2023-04-29 11:37:33,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +55: [2023-04-29 11:37:33,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +55: [2023-04-29 11:37:33,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +62: [2023-04-29 11:37:33,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +62: [2023-04-29 11:37:33,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +62: [2023-04-29 11:37:33,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +62: [2023-04-29 11:37:33,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +62: [2023-04-29 11:37:33,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +62: [2023-04-29 11:37:33,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +62: [2023-04-29 11:37:33,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +62: [2023-04-29 11:37:33,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +40: [2023-04-29 11:37:33,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +40: [2023-04-29 11:37:33,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +49: [2023-04-29 11:37:33,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +11: [2023-04-29 11:37:33,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +49: [2023-04-29 11:37:33,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +49: [2023-04-29 11:37:33,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +11: [2023-04-29 11:37:33,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +49: [2023-04-29 11:37:33,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +49: [2023-04-29 11:37:33,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +49: [2023-04-29 11:37:33,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +49: [2023-04-29 11:37:33,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +49: [2023-04-29 11:37:33,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +26: [2023-04-29 11:37:33,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +26: [2023-04-29 11:37:33,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +19: [2023-04-29 11:37:33,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +26: [2023-04-29 11:37:33,112] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +62: [2023-04-29 11:37:33,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +62: [2023-04-29 11:37:33,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 6: [2023-04-29 11:37:33,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +30: [2023-04-29 11:37:33,112] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +19: [2023-04-29 11:37:33,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 6: [2023-04-29 11:37:33,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +11: [2023-04-29 11:37:33,114] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +49: [2023-04-29 11:37:33,114] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +20: [2023-04-29 11:37:33,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +20: [2023-04-29 11:37:33,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +49: [2023-04-29 11:37:33,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +19: [2023-04-29 11:37:33,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +11: [2023-04-29 11:37:33,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +11: [2023-04-29 11:37:33,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +63: [2023-04-29 11:37:33,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +49: [2023-04-29 11:37:33,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +63: [2023-04-29 11:37:33,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +63: [2023-04-29 11:37:33,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +19: [2023-04-29 11:37:33,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +11: [2023-04-29 11:37:33,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +63: [2023-04-29 11:37:33,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +30: [2023-04-29 11:37:33,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +62: [2023-04-29 11:37:33,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +30: [2023-04-29 11:37:33,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +40: [2023-04-29 11:37:33,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +20: [2023-04-29 11:37:33,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +20: [2023-04-29 11:37:33,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +49: [2023-04-29 11:37:33,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +62: [2023-04-29 11:37:33,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +49: [2023-04-29 11:37:33,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +49: [2023-04-29 11:37:33,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +40: [2023-04-29 11:37:33,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +62: [2023-04-29 11:37:33,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +49: [2023-04-29 11:37:33,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +49: [2023-04-29 11:37:33,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +62: [2023-04-29 11:37:33,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +62: [2023-04-29 11:37:33,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +62: [2023-04-29 11:37:33,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +11: [2023-04-29 11:37:33,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +40: [2023-04-29 11:37:33,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +11: [2023-04-29 11:37:33,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +17: [2023-04-29 11:37:33,123] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +40: [2023-04-29 11:37:33,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +30: [2023-04-29 11:37:33,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +40: [2023-04-29 11:37:33,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +23: [2023-04-29 11:37:33,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +23: [2023-04-29 11:37:33,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +23: [2023-04-29 11:37:33,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +23: [2023-04-29 11:37:33,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +27: [2023-04-29 11:37:33,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +27: [2023-04-29 11:37:33,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +27: [2023-04-29 11:37:33,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +27: [2023-04-29 11:37:33,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +10: [2023-04-29 11:37:33,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +30: [2023-04-29 11:37:33,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +30: [2023-04-29 11:37:33,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +23: [2023-04-29 11:37:33,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... + 1: [2023-04-29 11:37:33,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +25: [2023-04-29 11:37:33,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +25: [2023-04-29 11:37:33,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +23: [2023-04-29 11:37:33,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +23: [2023-04-29 11:37:33,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +25: [2023-04-29 11:37:33,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +23: [2023-04-29 11:37:33,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +25: [2023-04-29 11:37:33,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +23: [2023-04-29 11:37:33,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +43: [2023-04-29 11:37:33,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +43: [2023-04-29 11:37:33,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +17: [2023-04-29 11:37:33,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +23: [2023-04-29 11:37:33,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +23: [2023-04-29 11:37:33,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +23: [2023-04-29 11:37:33,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +27: [2023-04-29 11:37:33,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +10: [2023-04-29 11:37:33,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +27: [2023-04-29 11:37:33,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +27: [2023-04-29 11:37:33,133] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +27: [2023-04-29 11:37:33,133] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +17: [2023-04-29 11:37:33,133] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +17: [2023-04-29 11:37:33,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +43: [2023-04-29 11:37:33,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +43: [2023-04-29 11:37:33,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +21: [2023-04-29 11:37:33,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +25: [2023-04-29 11:37:33,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +25: [2023-04-29 11:37:33,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +43: [2023-04-29 11:37:33,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +43: [2023-04-29 11:37:33,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... + 1: [2023-04-29 11:37:33,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +26: [2023-04-29 11:37:33,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +25: [2023-04-29 11:37:33,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +30: [2023-04-29 11:37:33,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +30: [2023-04-29 11:37:33,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +25: [2023-04-29 11:37:33,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +21: [2023-04-29 11:37:33,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +43: [2023-04-29 11:37:33,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +43: [2023-04-29 11:37:33,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +26: [2023-04-29 11:37:33,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 2: [2023-04-29 11:37:33,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. + 2: [2023-04-29 11:37:33,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. + 2: [2023-04-29 11:37:33,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. + 2: [2023-04-29 11:37:33,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. + 1: [2023-04-29 11:37:33,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +12: [2023-04-29 11:37:33,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +19: [2023-04-29 11:37:33,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +19: [2023-04-29 11:37:33,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +21: [2023-04-29 11:37:33,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +19: [2023-04-29 11:37:33,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +19: [2023-04-29 11:37:33,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +26: [2023-04-29 11:37:33,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +18: [2023-04-29 11:37:33,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 1: [2023-04-29 11:37:33,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +25: [2023-04-29 11:37:33,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +25: [2023-04-29 11:37:33,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +10: [2023-04-29 11:37:33,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 9: [2023-04-29 11:37:33,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 9: [2023-04-29 11:37:33,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +47: [2023-04-29 11:37:33,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +47: [2023-04-29 11:37:33,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +47: [2023-04-29 11:37:33,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +47: [2023-04-29 11:37:33,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +20: [2023-04-29 11:37:33,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +47: [2023-04-29 11:37:33,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 9: [2023-04-29 11:37:33,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +47: [2023-04-29 11:37:33,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +47: [2023-04-29 11:37:33,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +47: [2023-04-29 11:37:33,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 9: [2023-04-29 11:37:33,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +26: [2023-04-29 11:37:33,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +20: [2023-04-29 11:37:33,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +21: [2023-04-29 11:37:33,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +18: [2023-04-29 11:37:33,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +10: [2023-04-29 11:37:33,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +20: [2023-04-29 11:37:33,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +11: [2023-04-29 11:37:33,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +20: [2023-04-29 11:37:33,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +25: [2023-04-29 11:37:33,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +25: [2023-04-29 11:37:33,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +25: [2023-04-29 11:37:33,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... + 9: [2023-04-29 11:37:33,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +39: [2023-04-29 11:37:33,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +47: [2023-04-29 11:37:33,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +10: [2023-04-29 11:37:33,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +47: [2023-04-29 11:37:33,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +47: [2023-04-29 11:37:33,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +47: [2023-04-29 11:37:33,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +47: [2023-04-29 11:37:33,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +47: [2023-04-29 11:37:33,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +12: [2023-04-29 11:37:33,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 9: [2023-04-29 11:37:33,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 9: [2023-04-29 11:37:33,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +47: [2023-04-29 11:37:33,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +10: [2023-04-29 11:37:33,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +47: [2023-04-29 11:37:33,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +10: [2023-04-29 11:37:33,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +12: [2023-04-29 11:37:33,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... + 9: [2023-04-29 11:37:33,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +12: [2023-04-29 11:37:33,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +12: [2023-04-29 11:37:33,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +10: [2023-04-29 11:37:33,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +10: [2023-04-29 11:37:33,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +18: [2023-04-29 11:37:33,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +25: [2023-04-29 11:37:33,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +25: [2023-04-29 11:37:33,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +11: [2023-04-29 11:37:33,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +30: [2023-04-29 11:37:33,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +36: [2023-04-29 11:37:33,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +10: [2023-04-29 11:37:33,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +36: [2023-04-29 11:37:33,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +36: [2023-04-29 11:37:33,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +12: [2023-04-29 11:37:33,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +10: [2023-04-29 11:37:33,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +36: [2023-04-29 11:37:33,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +39: [2023-04-29 11:37:33,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +39: [2023-04-29 11:37:33,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +21: [2023-04-29 11:37:33,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +21: [2023-04-29 11:37:33,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +21: [2023-04-29 11:37:33,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +21: [2023-04-29 11:37:33,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 5: [2023-04-29 11:37:33,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 5: [2023-04-29 11:37:33,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 5: [2023-04-29 11:37:33,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +30: [2023-04-29 11:37:33,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 5: [2023-04-29 11:37:33,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +11: [2023-04-29 11:37:33,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +11: [2023-04-29 11:37:33,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +39: [2023-04-29 11:37:33,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +23: [2023-04-29 11:37:33,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +23: [2023-04-29 11:37:33,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +18: [2023-04-29 11:37:33,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +13: [2023-04-29 11:37:33,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +10: [2023-04-29 11:37:33,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +33: [2023-04-29 11:37:33,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +33: [2023-04-29 11:37:33,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +52: [2023-04-29 11:37:33,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +11: [2023-04-29 11:37:33,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +52: [2023-04-29 11:37:33,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +52: [2023-04-29 11:37:33,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +29: [2023-04-29 11:37:33,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +29: [2023-04-29 11:37:33,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +52: [2023-04-29 11:37:33,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +29: [2023-04-29 11:37:33,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +10: [2023-04-29 11:37:33,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +10: [2023-04-29 11:37:33,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +55: [2023-04-29 11:37:33,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +33: [2023-04-29 11:37:33,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +12: [2023-04-29 11:37:33,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +12: [2023-04-29 11:37:33,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +25: [2023-04-29 11:37:33,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +33: [2023-04-29 11:37:33,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +33: [2023-04-29 11:37:33,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +29: [2023-04-29 11:37:33,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +18: [2023-04-29 11:37:33,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +33: [2023-04-29 11:37:33,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +33: [2023-04-29 11:37:33,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +33: [2023-04-29 11:37:33,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +10: [2023-04-29 11:37:33,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 2: [2023-04-29 11:37:33,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +38: [2023-04-29 11:37:33,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +38: [2023-04-29 11:37:33,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +10: [2023-04-29 11:37:33,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +48: [2023-04-29 11:37:33,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +48: [2023-04-29 11:37:33,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +48: [2023-04-29 11:37:33,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +39: [2023-04-29 11:37:33,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_00-model_states.pt. +55: [2023-04-29 11:37:33,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +48: [2023-04-29 11:37:33,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +48: [2023-04-29 11:37:33,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +48: [2023-04-29 11:37:33,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +48: [2023-04-29 11:37:33,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +39: [2023-04-29 11:37:33,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +23: [2023-04-29 11:37:33,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +48: [2023-04-29 11:37:33,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +38: [2023-04-29 11:37:33,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +38: [2023-04-29 11:37:33,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +13: [2023-04-29 11:37:33,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +38: [2023-04-29 11:37:33,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +38: [2023-04-29 11:37:33,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +38: [2023-04-29 11:37:33,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +38: [2023-04-29 11:37:33,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +21: [2023-04-29 11:37:33,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +18: [2023-04-29 11:37:33,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +52: [2023-04-29 11:37:33,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +23: [2023-04-29 11:37:33,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +39: [2023-04-29 11:37:33,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +58: [2023-04-29 11:37:33,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +21: [2023-04-29 11:37:33,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +52: [2023-04-29 11:37:33,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +11: [2023-04-29 11:37:33,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +33: [2023-04-29 11:37:33,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +21: [2023-04-29 11:37:33,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 5: [2023-04-29 11:37:33,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +11: [2023-04-29 11:37:33,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... + 5: [2023-04-29 11:37:33,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +21: [2023-04-29 11:37:33,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 5: [2023-04-29 11:37:33,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 5: [2023-04-29 11:37:33,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +11: [2023-04-29 11:37:33,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +52: [2023-04-29 11:37:33,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +21: [2023-04-29 11:37:33,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +33: [2023-04-29 11:37:33,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +30: [2023-04-29 11:37:33,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +30: [2023-04-29 11:37:33,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +52: [2023-04-29 11:37:33,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +32: [2023-04-29 11:37:33,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +48: [2023-04-29 11:37:33,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +21: [2023-04-29 11:37:33,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +32: [2023-04-29 11:37:33,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +38: [2023-04-29 11:37:33,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +32: [2023-04-29 11:37:33,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +32: [2023-04-29 11:37:33,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +32: [2023-04-29 11:37:33,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +32: [2023-04-29 11:37:33,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +32: [2023-04-29 11:37:33,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +32: [2023-04-29 11:37:33,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +33: [2023-04-29 11:37:33,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 2: [2023-04-29 11:37:33,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 2: [2023-04-29 11:37:33,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +48: [2023-04-29 11:37:33,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +33: [2023-04-29 11:37:33,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +38: [2023-04-29 11:37:33,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +33: [2023-04-29 11:37:33,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... + 2: [2023-04-29 11:37:33,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +55: [2023-04-29 11:37:33,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +48: [2023-04-29 11:37:33,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +38: [2023-04-29 11:37:33,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +38: [2023-04-29 11:37:33,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +55: [2023-04-29 11:37:33,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +33: [2023-04-29 11:37:33,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +33: [2023-04-29 11:37:33,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +33: [2023-04-29 11:37:33,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +18: [2023-04-29 11:37:33,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... + 6: [2023-04-29 11:37:33,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +55: [2023-04-29 11:37:33,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +19: [2023-04-29 11:37:33,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +39: [2023-04-29 11:37:33,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt... +48: [2023-04-29 11:37:33,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +48: [2023-04-29 11:37:33,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +18: [2023-04-29 11:37:33,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +41: [2023-04-29 11:37:33,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +41: [2023-04-29 11:37:33,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +41: [2023-04-29 11:37:33,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +41: [2023-04-29 11:37:33,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +41: [2023-04-29 11:37:33,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +41: [2023-04-29 11:37:33,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +41: [2023-04-29 11:37:33,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +41: [2023-04-29 11:37:33,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +48: [2023-04-29 11:37:33,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +32: [2023-04-29 11:37:33,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +32: [2023-04-29 11:37:33,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +32: [2023-04-29 11:37:33,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +48: [2023-04-29 11:37:33,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +48: [2023-04-29 11:37:33,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +58: [2023-04-29 11:37:33,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +38: [2023-04-29 11:37:33,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +55: [2023-04-29 11:37:33,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +55: [2023-04-29 11:37:33,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +38: [2023-04-29 11:37:33,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +38: [2023-04-29 11:37:33,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +32: [2023-04-29 11:37:33,175] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 3: [2023-04-29 11:37:33,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 3: [2023-04-29 11:37:33,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 3: [2023-04-29 11:37:33,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +13: [2023-04-29 11:37:33,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 3: [2023-04-29 11:37:33,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +34: [2023-04-29 11:37:33,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +34: [2023-04-29 11:37:33,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +19: [2023-04-29 11:37:33,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +38: [2023-04-29 11:37:33,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +34: [2023-04-29 11:37:33,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +34: [2023-04-29 11:37:33,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +11: [2023-04-29 11:37:33,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +34: [2023-04-29 11:37:33,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +34: [2023-04-29 11:37:33,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +34: [2023-04-29 11:37:33,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +34: [2023-04-29 11:37:33,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +21: [2023-04-29 11:37:33,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +32: [2023-04-29 11:37:33,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +19: [2023-04-29 11:37:33,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +32: [2023-04-29 11:37:33,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +40: [2023-04-29 11:37:33,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +13: [2023-04-29 11:37:33,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +13: [2023-04-29 11:37:33,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +32: [2023-04-29 11:37:33,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +62: [2023-04-29 11:37:33,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +62: [2023-04-29 11:37:33,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +19: [2023-04-29 11:37:33,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +58: [2023-04-29 11:37:33,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +49: [2023-04-29 11:37:33,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 3: [2023-04-29 11:37:33,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +58: [2023-04-29 11:37:33,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +41: [2023-04-29 11:37:33,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +32: [2023-04-29 11:37:33,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +21: [2023-04-29 11:37:33,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +41: [2023-04-29 11:37:33,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +41: [2023-04-29 11:37:33,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... + 6: [2023-04-29 11:37:33,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +34: [2023-04-29 11:37:33,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... + 3: [2023-04-29 11:37:33,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +55: [2023-04-29 11:37:33,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +55: [2023-04-29 11:37:33,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +55: [2023-04-29 11:37:33,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +34: [2023-04-29 11:37:33,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +34: [2023-04-29 11:37:33,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +34: [2023-04-29 11:37:33,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +36: [2023-04-29 11:37:33,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 3: [2023-04-29 11:37:33,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +13: [2023-04-29 11:37:33,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +40: [2023-04-29 11:37:33,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 3: [2023-04-29 11:37:33,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +30: [2023-04-29 11:37:33,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +13: [2023-04-29 11:37:33,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +41: [2023-04-29 11:37:33,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +41: [2023-04-29 11:37:33,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +13: [2023-04-29 11:37:33,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +34: [2023-04-29 11:37:33,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +41: [2023-04-29 11:37:33,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +40: [2023-04-29 11:37:33,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +46: [2023-04-29 11:37:33,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +46: [2023-04-29 11:37:33,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +46: [2023-04-29 11:37:33,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +46: [2023-04-29 11:37:33,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 3: [2023-04-29 11:37:33,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. + 3: [2023-04-29 11:37:33,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +46: [2023-04-29 11:37:33,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +46: [2023-04-29 11:37:33,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +46: [2023-04-29 11:37:33,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +41: [2023-04-29 11:37:33,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +46: [2023-04-29 11:37:33,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +41: [2023-04-29 11:37:33,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 9: [2023-04-29 11:37:33,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. + 9: [2023-04-29 11:37:33,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +55: [2023-04-29 11:37:33,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +17: [2023-04-29 11:37:33,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +40: [2023-04-29 11:37:33,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 3: [2023-04-29 11:37:33,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +34: [2023-04-29 11:37:33,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 3: [2023-04-29 11:37:33,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +55: [2023-04-29 11:37:33,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +28: [2023-04-29 11:37:33,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +28: [2023-04-29 11:37:33,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... + 9: [2023-04-29 11:37:33,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. + 6: [2023-04-29 11:37:33,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +34: [2023-04-29 11:37:33,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +34: [2023-04-29 11:37:33,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 9: [2023-04-29 11:37:33,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +40: [2023-04-29 11:37:33,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +35: [2023-04-29 11:37:33,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +35: [2023-04-29 11:37:33,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +35: [2023-04-29 11:37:33,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +35: [2023-04-29 11:37:33,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +42: [2023-04-29 11:37:33,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +42: [2023-04-29 11:37:33,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +42: [2023-04-29 11:37:33,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +42: [2023-04-29 11:37:33,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +42: [2023-04-29 11:37:33,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +42: [2023-04-29 11:37:33,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +42: [2023-04-29 11:37:33,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +35: [2023-04-29 11:37:33,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +35: [2023-04-29 11:37:33,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +35: [2023-04-29 11:37:33,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +42: [2023-04-29 11:37:33,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +36: [2023-04-29 11:37:33,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +23: [2023-04-29 11:37:33,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +35: [2023-04-29 11:37:33,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +29: [2023-04-29 11:37:33,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +28: [2023-04-29 11:37:33,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +28: [2023-04-29 11:37:33,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +30: [2023-04-29 11:37:33,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +46: [2023-04-29 11:37:33,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +46: [2023-04-29 11:37:33,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +17: [2023-04-29 11:37:33,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +46: [2023-04-29 11:37:33,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +29: [2023-04-29 11:37:33,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +46: [2023-04-29 11:37:33,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +40: [2023-04-29 11:37:33,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +42: [2023-04-29 11:37:33,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +28: [2023-04-29 11:37:33,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +29: [2023-04-29 11:37:33,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +28: [2023-04-29 11:37:33,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +46: [2023-04-29 11:37:33,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +62: [2023-04-29 11:37:33,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +62: [2023-04-29 11:37:33,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +36: [2023-04-29 11:37:33,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +49: [2023-04-29 11:37:33,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +49: [2023-04-29 11:37:33,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +49: [2023-04-29 11:37:33,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 7: [2023-04-29 11:37:33,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. + 7: [2023-04-29 11:37:33,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +36: [2023-04-29 11:37:33,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +31: [2023-04-29 11:37:33,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +31: [2023-04-29 11:37:33,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +31: [2023-04-29 11:37:33,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 7: [2023-04-29 11:37:33,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +46: [2023-04-29 11:37:33,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +46: [2023-04-29 11:37:33,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +35: [2023-04-29 11:37:33,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +31: [2023-04-29 11:37:33,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 7: [2023-04-29 11:37:33,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +46: [2023-04-29 11:37:33,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +55: [2023-04-29 11:37:33,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +40: [2023-04-29 11:37:33,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +11: [2023-04-29 11:37:33,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +42: [2023-04-29 11:37:33,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +42: [2023-04-29 11:37:33,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +42: [2023-04-29 11:37:33,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 0: [2023-04-29 11:37:33,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 0: [2023-04-29 11:37:33,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 0: [2023-04-29 11:37:33,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +11: [2023-04-29 11:37:33,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +25: [2023-04-29 11:37:33,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +27: [2023-04-29 11:37:33,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +29: [2023-04-29 11:37:33,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 4: [2023-04-29 11:37:33,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 4: [2023-04-29 11:37:33,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +35: [2023-04-29 11:37:33,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... + 4: [2023-04-29 11:37:33,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +35: [2023-04-29 11:37:33,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... + 4: [2023-04-29 11:37:33,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 0: [2023-04-29 11:37:33,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +13: [2023-04-29 11:37:33,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +13: [2023-04-29 11:37:33,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +58: [2023-04-29 11:37:33,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +28: [2023-04-29 11:37:33,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +11: [2023-04-29 11:37:33,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +42: [2023-04-29 11:37:33,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +60: [2023-04-29 11:37:33,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +60: [2023-04-29 11:37:33,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +60: [2023-04-29 11:37:33,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +60: [2023-04-29 11:37:33,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +60: [2023-04-29 11:37:33,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +30: [2023-04-29 11:37:33,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +60: [2023-04-29 11:37:33,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +60: [2023-04-29 11:37:33,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +60: [2023-04-29 11:37:33,197] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +42: [2023-04-29 11:37:33,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +28: [2023-04-29 11:37:33,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +17: [2023-04-29 11:37:33,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +13: [2023-04-29 11:37:33,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +13: [2023-04-29 11:37:33,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 2: [2023-04-29 11:37:33,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 2: [2023-04-29 11:37:33,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 2: [2023-04-29 11:37:33,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +42: [2023-04-29 11:37:33,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 2: [2023-04-29 11:37:33,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +42: [2023-04-29 11:37:33,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +16: [2023-04-29 11:37:33,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +16: [2023-04-29 11:37:33,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +35: [2023-04-29 11:37:33,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +27: [2023-04-29 11:37:33,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +25: [2023-04-29 11:37:33,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +16: [2023-04-29 11:37:33,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +52: [2023-04-29 11:37:33,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +52: [2023-04-29 11:37:33,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +16: [2023-04-29 11:37:33,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +30: [2023-04-29 11:37:33,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +35: [2023-04-29 11:37:33,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +35: [2023-04-29 11:37:33,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +35: [2023-04-29 11:37:33,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +52: [2023-04-29 11:37:33,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +35: [2023-04-29 11:37:33,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +40: [2023-04-29 11:37:33,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +52: [2023-04-29 11:37:33,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +13: [2023-04-29 11:37:33,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +13: [2023-04-29 11:37:33,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +60: [2023-04-29 11:37:33,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +27: [2023-04-29 11:37:33,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +27: [2023-04-29 11:37:33,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +60: [2023-04-29 11:37:33,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +60: [2023-04-29 11:37:33,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 7: [2023-04-29 11:37:33,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 7: [2023-04-29 11:37:33,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +60: [2023-04-29 11:37:33,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +60: [2023-04-29 11:37:33,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +60: [2023-04-29 11:37:33,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +13: [2023-04-29 11:37:33,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +60: [2023-04-29 11:37:33,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +11: [2023-04-29 11:37:33,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +25: [2023-04-29 11:37:33,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 2: [2023-04-29 11:37:33,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +58: [2023-04-29 11:37:33,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +17: [2023-04-29 11:37:33,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +17: [2023-04-29 11:37:33,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +13: [2023-04-29 11:37:33,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 2: [2023-04-29 11:37:33,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 2: [2023-04-29 11:37:33,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +60: [2023-04-29 11:37:33,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... + 2: [2023-04-29 11:37:33,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +62: [2023-04-29 11:37:33,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +62: [2023-04-29 11:37:33,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +17: [2023-04-29 11:37:33,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +49: [2023-04-29 11:37:33,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 7: [2023-04-29 11:37:33,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 7: [2023-04-29 11:37:33,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +55: [2023-04-29 11:37:33,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 7: [2023-04-29 11:37:33,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +17: [2023-04-29 11:37:33,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +23: [2023-04-29 11:37:33,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +58: [2023-04-29 11:37:33,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 7: [2023-04-29 11:37:33,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +20: [2023-04-29 11:37:33,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +20: [2023-04-29 11:37:33,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +25: [2023-04-29 11:37:33,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +58: [2023-04-29 11:37:33,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 9: [2023-04-29 11:37:33,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +55: [2023-04-29 11:37:33,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +55: [2023-04-29 11:37:33,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 7: [2023-04-29 11:37:33,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 7: [2023-04-29 11:37:33,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +17: [2023-04-29 11:37:33,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +20: [2023-04-29 11:37:33,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 3: [2023-04-29 11:37:33,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 3: [2023-04-29 11:37:33,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 3: [2023-04-29 11:37:33,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 7: [2023-04-29 11:37:33,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +23: [2023-04-29 11:37:33,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +47: [2023-04-29 11:37:33,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +47: [2023-04-29 11:37:33,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 9: [2023-04-29 11:37:33,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 9: [2023-04-29 11:37:33,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +25: [2023-04-29 11:37:33,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 3: [2023-04-29 11:37:33,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +27: [2023-04-29 11:37:33,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +23: [2023-04-29 11:37:33,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +23: [2023-04-29 11:37:33,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 9: [2023-04-29 11:37:33,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +20: [2023-04-29 11:37:33,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +20: [2023-04-29 11:37:33,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +11: [2023-04-29 11:37:33,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +20: [2023-04-29 11:37:33,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 7: [2023-04-29 11:37:33,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 7: [2023-04-29 11:37:33,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 4: [2023-04-29 11:37:33,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +20: [2023-04-29 11:37:33,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... + 7: [2023-04-29 11:37:33,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +47: [2023-04-29 11:37:33,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +56: [2023-04-29 11:37:33,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +56: [2023-04-29 11:37:33,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +62: [2023-04-29 11:37:33,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +11: [2023-04-29 11:37:33,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +47: [2023-04-29 11:37:33,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 2: [2023-04-29 11:37:33,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +28: [2023-04-29 11:37:33,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +28: [2023-04-29 11:37:33,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +49: [2023-04-29 11:37:33,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +21: [2023-04-29 11:37:33,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 0: [2023-04-29 11:37:33,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 4: [2023-04-29 11:37:33,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +28: [2023-04-29 11:37:33,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +16: [2023-04-29 11:37:33,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +31: [2023-04-29 11:37:33,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +49: [2023-04-29 11:37:33,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +28: [2023-04-29 11:37:33,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +31: [2023-04-29 11:37:33,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +31: [2023-04-29 11:37:33,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +49: [2023-04-29 11:37:33,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +56: [2023-04-29 11:37:33,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +31: [2023-04-29 11:37:33,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +56: [2023-04-29 11:37:33,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +56: [2023-04-29 11:37:33,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +31: [2023-04-29 11:37:33,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +56: [2023-04-29 11:37:33,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +56: [2023-04-29 11:37:33,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 0: [2023-04-29 11:37:33,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +56: [2023-04-29 11:37:33,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +31: [2023-04-29 11:37:33,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +31: [2023-04-29 11:37:33,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +62: [2023-04-29 11:37:33,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +25: [2023-04-29 11:37:33,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +16: [2023-04-29 11:37:33,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +12: [2023-04-29 11:37:33,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +12: [2023-04-29 11:37:33,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +17: [2023-04-29 11:37:33,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +17: [2023-04-29 11:37:33,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +17: [2023-04-29 11:37:33,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 0: [2023-04-29 11:37:33,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 0: [2023-04-29 11:37:33,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 0: [2023-04-29 11:37:33,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +17: [2023-04-29 11:37:33,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +32: [2023-04-29 11:37:33,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +12: [2023-04-29 11:37:33,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +48: [2023-04-29 11:37:33,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 0: [2023-04-29 11:37:33,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 2: [2023-04-29 11:37:33,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... + 4: [2023-04-29 11:37:33,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +12: [2023-04-29 11:37:33,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 4: [2023-04-29 11:37:33,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +52: [2023-04-29 11:37:33,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +52: [2023-04-29 11:37:33,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +56: [2023-04-29 11:37:33,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +31: [2023-04-29 11:37:33,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +20: [2023-04-29 11:37:33,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +27: [2023-04-29 11:37:33,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +26: [2023-04-29 11:37:33,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +26: [2023-04-29 11:37:33,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +26: [2023-04-29 11:37:33,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +26: [2023-04-29 11:37:33,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +56: [2023-04-29 11:37:33,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... + 0: [2023-04-29 11:37:33,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +56: [2023-04-29 11:37:33,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +23: [2023-04-29 11:37:33,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +23: [2023-04-29 11:37:33,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +10: [2023-04-29 11:37:33,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +10: [2023-04-29 11:37:33,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +10: [2023-04-29 11:37:33,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 0: [2023-04-29 11:37:33,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +56: [2023-04-29 11:37:33,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +31: [2023-04-29 11:37:33,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +56: [2023-04-29 11:37:33,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +11: [2023-04-29 11:37:33,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +38: [2023-04-29 11:37:33,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +31: [2023-04-29 11:37:33,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +25: [2023-04-29 11:37:33,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +31: [2023-04-29 11:37:33,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +56: [2023-04-29 11:37:33,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +56: [2023-04-29 11:37:33,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +27: [2023-04-29 11:37:33,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +27: [2023-04-29 11:37:33,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +56: [2023-04-29 11:37:33,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +33: [2023-04-29 11:37:33,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +17: [2023-04-29 11:37:33,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +10: [2023-04-29 11:37:33,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +31: [2023-04-29 11:37:33,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +17: [2023-04-29 11:37:33,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 0: [2023-04-29 11:37:33,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +17: [2023-04-29 11:37:33,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +52: [2023-04-29 11:37:33,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +17: [2023-04-29 11:37:33,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +19: [2023-04-29 11:37:33,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 9: [2023-04-29 11:37:33,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 9: [2023-04-29 11:37:33,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +12: [2023-04-29 11:37:33,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +12: [2023-04-29 11:37:33,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 0: [2023-04-29 11:37:33,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 0: [2023-04-29 11:37:33,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +16: [2023-04-29 11:37:33,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +48: [2023-04-29 11:37:33,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +48: [2023-04-29 11:37:33,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +12: [2023-04-29 11:37:33,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +38: [2023-04-29 11:37:33,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 9: [2023-04-29 11:37:33,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +21: [2023-04-29 11:37:33,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +21: [2023-04-29 11:37:33,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +21: [2023-04-29 11:37:33,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 9: [2023-04-29 11:37:33,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +52: [2023-04-29 11:37:33,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +12: [2023-04-29 11:37:33,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +52: [2023-04-29 11:37:33,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 5: [2023-04-29 11:37:33,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 5: [2023-04-29 11:37:33,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 5: [2023-04-29 11:37:33,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 5: [2023-04-29 11:37:33,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 0: [2023-04-29 11:37:33,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +48: [2023-04-29 11:37:33,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +23: [2023-04-29 11:37:33,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +23: [2023-04-29 11:37:33,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +16: [2023-04-29 11:37:33,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 2: [2023-04-29 11:37:33,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 2: [2023-04-29 11:37:33,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +52: [2023-04-29 11:37:33,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +33: [2023-04-29 11:37:33,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +33: [2023-04-29 11:37:33,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +33: [2023-04-29 11:37:33,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +19: [2023-04-29 11:37:33,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +38: [2023-04-29 11:37:33,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +38: [2023-04-29 11:37:33,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +32: [2023-04-29 11:37:33,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +25: [2023-04-29 11:37:33,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +34: [2023-04-29 11:37:33,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +51: [2023-04-29 11:37:33,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +51: [2023-04-29 11:37:33,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +51: [2023-04-29 11:37:33,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +51: [2023-04-29 11:37:33,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +51: [2023-04-29 11:37:33,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +51: [2023-04-29 11:37:33,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +51: [2023-04-29 11:37:33,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +51: [2023-04-29 11:37:33,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 2: [2023-04-29 11:37:33,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +47: [2023-04-29 11:37:33,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 2: [2023-04-29 11:37:33,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +23: [2023-04-29 11:37:33,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +34: [2023-04-29 11:37:33,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +32: [2023-04-29 11:37:33,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +41: [2023-04-29 11:37:33,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +45: [2023-04-29 11:37:33,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +45: [2023-04-29 11:37:33,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +45: [2023-04-29 11:37:33,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +45: [2023-04-29 11:37:33,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +45: [2023-04-29 11:37:33,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +45: [2023-04-29 11:37:33,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +45: [2023-04-29 11:37:33,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +14: [2023-04-29 11:37:33,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +14: [2023-04-29 11:37:33,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +45: [2023-04-29 11:37:33,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 3: [2023-04-29 11:37:33,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +19: [2023-04-29 11:37:33,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +41: [2023-04-29 11:37:33,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +47: [2023-04-29 11:37:33,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +23: [2023-04-29 11:37:33,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +21: [2023-04-29 11:37:33,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +52: [2023-04-29 11:37:33,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +19: [2023-04-29 11:37:33,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +51: [2023-04-29 11:37:33,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +51: [2023-04-29 11:37:33,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +23: [2023-04-29 11:37:33,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 2: [2023-04-29 11:37:33,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +23: [2023-04-29 11:37:33,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +46: [2023-04-29 11:37:33,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +47: [2023-04-29 11:37:33,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +44: [2023-04-29 11:37:33,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +44: [2023-04-29 11:37:33,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +32: [2023-04-29 11:37:33,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +44: [2023-04-29 11:37:33,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +14: [2023-04-29 11:37:33,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +44: [2023-04-29 11:37:33,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +48: [2023-04-29 11:37:33,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 3: [2023-04-29 11:37:33,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +14: [2023-04-29 11:37:33,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +23: [2023-04-29 11:37:33,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +45: [2023-04-29 11:37:33,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +45: [2023-04-29 11:37:33,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +47: [2023-04-29 11:37:33,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +45: [2023-04-29 11:37:33,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +45: [2023-04-29 11:37:33,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +28: [2023-04-29 11:37:33,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +14: [2023-04-29 11:37:33,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +24: [2023-04-29 11:37:33,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +19: [2023-04-29 11:37:33,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +45: [2023-04-29 11:37:33,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 8: [2023-04-29 11:37:33,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +24: [2023-04-29 11:37:33,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +24: [2023-04-29 11:37:33,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. + 8: [2023-04-29 11:37:33,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +34: [2023-04-29 11:37:33,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 8: [2023-04-29 11:37:33,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 3: [2023-04-29 11:37:33,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 8: [2023-04-29 11:37:33,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +24: [2023-04-29 11:37:33,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +45: [2023-04-29 11:37:33,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +45: [2023-04-29 11:37:33,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +29: [2023-04-29 11:37:33,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +45: [2023-04-29 11:37:33,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +32: [2023-04-29 11:37:33,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +19: [2023-04-29 11:37:33,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +14: [2023-04-29 11:37:33,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +35: [2023-04-29 11:37:33,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +51: [2023-04-29 11:37:33,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +23: [2023-04-29 11:37:33,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +51: [2023-04-29 11:37:33,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +51: [2023-04-29 11:37:33,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +28: [2023-04-29 11:37:33,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +51: [2023-04-29 11:37:33,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +51: [2023-04-29 11:37:33,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +34: [2023-04-29 11:37:33,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +51: [2023-04-29 11:37:33,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +28: [2023-04-29 11:37:33,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +19: [2023-04-29 11:37:33,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +14: [2023-04-29 11:37:33,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +26: [2023-04-29 11:37:33,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +52: [2023-04-29 11:37:33,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 2: [2023-04-29 11:37:33,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +26: [2023-04-29 11:37:33,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +28: [2023-04-29 11:37:33,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +15: [2023-04-29 11:37:33,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +15: [2023-04-29 11:37:33,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +15: [2023-04-29 11:37:33,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. + 3: [2023-04-29 11:37:33,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +15: [2023-04-29 11:37:33,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +14: [2023-04-29 11:37:33,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +23: [2023-04-29 11:37:33,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +41: [2023-04-29 11:37:33,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +29: [2023-04-29 11:37:33,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +46: [2023-04-29 11:37:33,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +46: [2023-04-29 11:37:33,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +46: [2023-04-29 11:37:33,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +42: [2023-04-29 11:37:33,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +42: [2023-04-29 11:37:33,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +42: [2023-04-29 11:37:33,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +52: [2023-04-29 11:37:33,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +29: [2023-04-29 11:37:33,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +10: [2023-04-29 11:37:33,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +26: [2023-04-29 11:37:33,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +38: [2023-04-29 11:37:33,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +33: [2023-04-29 11:37:33,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +26: [2023-04-29 11:37:33,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +38: [2023-04-29 11:37:33,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +19: [2023-04-29 11:37:33,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +42: [2023-04-29 11:37:33,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +13: [2023-04-29 11:37:33,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +13: [2023-04-29 11:37:33,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +41: [2023-04-29 11:37:33,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +10: [2023-04-29 11:37:33,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +10: [2023-04-29 11:37:33,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +10: [2023-04-29 11:37:33,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +52: [2023-04-29 11:37:33,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +29: [2023-04-29 11:37:33,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +29: [2023-04-29 11:37:33,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +48: [2023-04-29 11:37:33,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +48: [2023-04-29 11:37:33,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +29: [2023-04-29 11:37:33,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +60: [2023-04-29 11:37:33,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +60: [2023-04-29 11:37:33,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +34: [2023-04-29 11:37:33,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 9: [2023-04-29 11:37:33,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +28: [2023-04-29 11:37:33,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +28: [2023-04-29 11:37:33,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 9: [2023-04-29 11:37:33,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 9: [2023-04-29 11:37:33,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +28: [2023-04-29 11:37:33,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +13: [2023-04-29 11:37:33,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 2: [2023-04-29 11:37:33,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +59: [2023-04-29 11:37:33,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +59: [2023-04-29 11:37:33,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +54: [2023-04-29 11:37:33,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +48: [2023-04-29 11:37:33,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +54: [2023-04-29 11:37:33,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +53: [2023-04-29 11:37:33,272] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +53: [2023-04-29 11:37:33,272] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +54: [2023-04-29 11:37:33,272] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +53: [2023-04-29 11:37:33,272] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +54: [2023-04-29 11:37:33,272] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +53: [2023-04-29 11:37:33,272] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +60: [2023-04-29 11:37:33,272] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +21: [2023-04-29 11:37:33,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +32: [2023-04-29 11:37:33,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 9: [2023-04-29 11:37:33,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +34: [2023-04-29 11:37:33,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +33: [2023-04-29 11:37:33,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +33: [2023-04-29 11:37:33,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +33: [2023-04-29 11:37:33,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +29: [2023-04-29 11:37:33,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +38: [2023-04-29 11:37:33,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +38: [2023-04-29 11:37:33,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +35: [2023-04-29 11:37:33,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +35: [2023-04-29 11:37:33,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +21: [2023-04-29 11:37:33,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +35: [2023-04-29 11:37:33,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +21: [2023-04-29 11:37:33,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +13: [2023-04-29 11:37:33,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +28: [2023-04-29 11:37:33,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +29: [2023-04-29 11:37:33,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +59: [2023-04-29 11:37:33,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +50: [2023-04-29 11:37:33,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +50: [2023-04-29 11:37:33,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +50: [2023-04-29 11:37:33,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +59: [2023-04-29 11:37:33,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +54: [2023-04-29 11:37:33,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +50: [2023-04-29 11:37:33,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. + 5: [2023-04-29 11:37:33,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 5: [2023-04-29 11:37:33,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +54: [2023-04-29 11:37:33,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +60: [2023-04-29 11:37:33,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 5: [2023-04-29 11:37:33,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 5: [2023-04-29 11:37:33,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 3: [2023-04-29 11:37:33,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +54: [2023-04-29 11:37:33,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +54: [2023-04-29 11:37:33,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +32: [2023-04-29 11:37:33,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +50: [2023-04-29 11:37:33,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 2: [2023-04-29 11:37:33,278] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 2: [2023-04-29 11:37:33,278] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 2: [2023-04-29 11:37:33,278] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 3: [2023-04-29 11:37:33,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +35: [2023-04-29 11:37:33,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +24: [2023-04-29 11:37:33,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +46: [2023-04-29 11:37:33,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +44: [2023-04-29 11:37:33,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +52: [2023-04-29 11:37:33,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +44: [2023-04-29 11:37:33,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +44: [2023-04-29 11:37:33,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 8: [2023-04-29 11:37:33,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +32: [2023-04-29 11:37:33,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 7: [2023-04-29 11:37:33,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +50: [2023-04-29 11:37:33,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +50: [2023-04-29 11:37:33,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +22: [2023-04-29 11:37:33,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +22: [2023-04-29 11:37:33,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +41: [2023-04-29 11:37:33,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +44: [2023-04-29 11:37:33,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +50: [2023-04-29 11:37:33,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 3: [2023-04-29 11:37:33,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +41: [2023-04-29 11:37:33,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +24: [2023-04-29 11:37:33,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +22: [2023-04-29 11:37:33,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +34: [2023-04-29 11:37:33,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +22: [2023-04-29 11:37:33,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. + 7: [2023-04-29 11:37:33,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +34: [2023-04-29 11:37:33,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +24: [2023-04-29 11:37:33,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 7: [2023-04-29 11:37:33,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +39: [2023-04-29 11:37:33,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +39: [2023-04-29 11:37:33,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +24: [2023-04-29 11:37:33,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +39: [2023-04-29 11:37:33,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 4: [2023-04-29 11:37:33,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 3: [2023-04-29 11:37:33,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +39: [2023-04-29 11:37:33,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 7: [2023-04-29 11:37:33,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +52: [2023-04-29 11:37:33,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 3: [2023-04-29 11:37:33,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 8: [2023-04-29 11:37:33,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 4: [2023-04-29 11:37:33,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 8: [2023-04-29 11:37:33,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 8: [2023-04-29 11:37:33,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +59: [2023-04-29 11:37:33,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +59: [2023-04-29 11:37:33,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +46: [2023-04-29 11:37:33,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 9: [2023-04-29 11:37:33,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +15: [2023-04-29 11:37:33,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +13: [2023-04-29 11:37:33,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +13: [2023-04-29 11:37:33,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +59: [2023-04-29 11:37:33,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +42: [2023-04-29 11:37:33,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +59: [2023-04-29 11:37:33,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +56: [2023-04-29 11:37:33,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +42: [2023-04-29 11:37:33,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +42: [2023-04-29 11:37:33,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +15: [2023-04-29 11:37:33,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +46: [2023-04-29 11:37:33,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 7: [2023-04-29 11:37:33,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +15: [2023-04-29 11:37:33,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +46: [2023-04-29 11:37:33,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +60: [2023-04-29 11:37:33,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +61: [2023-04-29 11:37:33,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +61: [2023-04-29 11:37:33,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 3: [2023-04-29 11:37:33,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +63: [2023-04-29 11:37:33,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +63: [2023-04-29 11:37:33,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +63: [2023-04-29 11:37:33,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +63: [2023-04-29 11:37:33,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +63: [2023-04-29 11:37:33,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 0: [2023-04-29 11:37:33,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +63: [2023-04-29 11:37:33,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +63: [2023-04-29 11:37:33,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 4: [2023-04-29 11:37:33,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +63: [2023-04-29 11:37:33,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +15: [2023-04-29 11:37:33,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +39: [2023-04-29 11:37:33,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +39: [2023-04-29 11:37:33,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +39: [2023-04-29 11:37:33,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +39: [2023-04-29 11:37:33,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +60: [2023-04-29 11:37:33,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 9: [2023-04-29 11:37:33,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... + 4: [2023-04-29 11:37:33,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... + 3: [2023-04-29 11:37:33,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 3: [2023-04-29 11:37:33,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +59: [2023-04-29 11:37:33,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +41: [2023-04-29 11:37:33,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +16: [2023-04-29 11:37:33,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +16: [2023-04-29 11:37:33,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +53: [2023-04-29 11:37:33,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +61: [2023-04-29 11:37:33,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +61: [2023-04-29 11:37:33,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +61: [2023-04-29 11:37:33,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +61: [2023-04-29 11:37:33,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +61: [2023-04-29 11:37:33,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +61: [2023-04-29 11:37:33,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +59: [2023-04-29 11:37:33,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 7: [2023-04-29 11:37:33,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 7: [2023-04-29 11:37:33,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +42: [2023-04-29 11:37:33,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +63: [2023-04-29 11:37:33,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +59: [2023-04-29 11:37:33,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +63: [2023-04-29 11:37:33,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +60: [2023-04-29 11:37:33,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +59: [2023-04-29 11:37:33,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 2: [2023-04-29 11:37:33,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 0: [2023-04-29 11:37:33,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +28: [2023-04-29 11:37:33,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +36: [2023-04-29 11:37:33,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +36: [2023-04-29 11:37:33,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +28: [2023-04-29 11:37:33,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 3: [2023-04-29 11:37:33,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +28: [2023-04-29 11:37:33,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +63: [2023-04-29 11:37:33,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +63: [2023-04-29 11:37:33,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +63: [2023-04-29 11:37:33,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +61: [2023-04-29 11:37:33,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +61: [2023-04-29 11:37:33,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +59: [2023-04-29 11:37:33,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +59: [2023-04-29 11:37:33,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +63: [2023-04-29 11:37:33,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 3: [2023-04-29 11:37:33,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +13: [2023-04-29 11:37:33,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +63: [2023-04-29 11:37:33,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... + 3: [2023-04-29 11:37:33,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +53: [2023-04-29 11:37:33,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +41: [2023-04-29 11:37:33,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 9: [2023-04-29 11:37:33,301] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 9: [2023-04-29 11:37:33,301] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +16: [2023-04-29 11:37:33,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +16: [2023-04-29 11:37:33,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +63: [2023-04-29 11:37:33,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +56: [2023-04-29 11:37:33,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +56: [2023-04-29 11:37:33,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +56: [2023-04-29 11:37:33,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +12: [2023-04-29 11:37:33,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +12: [2023-04-29 11:37:33,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +54: [2023-04-29 11:37:33,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +54: [2023-04-29 11:37:33,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +54: [2023-04-29 11:37:33,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +17: [2023-04-29 11:37:33,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +17: [2023-04-29 11:37:33,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +17: [2023-04-29 11:37:33,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +28: [2023-04-29 11:37:33,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 4: [2023-04-29 11:37:33,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 4: [2023-04-29 11:37:33,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +54: [2023-04-29 11:37:33,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +53: [2023-04-29 11:37:33,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +53: [2023-04-29 11:37:33,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 6: [2023-04-29 11:37:33,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +35: [2023-04-29 11:37:33,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 6: [2023-04-29 11:37:33,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +61: [2023-04-29 11:37:33,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +61: [2023-04-29 11:37:33,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +61: [2023-04-29 11:37:33,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +31: [2023-04-29 11:37:33,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 7: [2023-04-29 11:37:33,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +36: [2023-04-29 11:37:33,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +36: [2023-04-29 11:37:33,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +36: [2023-04-29 11:37:33,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +36: [2023-04-29 11:37:33,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +36: [2023-04-29 11:37:33,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +36: [2023-04-29 11:37:33,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +59: [2023-04-29 11:37:33,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 7: [2023-04-29 11:37:33,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +13: [2023-04-29 11:37:33,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 7: [2023-04-29 11:37:33,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... + 7: [2023-04-29 11:37:33,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +60: [2023-04-29 11:37:33,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +61: [2023-04-29 11:37:33,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +12: [2023-04-29 11:37:33,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 9: [2023-04-29 11:37:33,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 3: [2023-04-29 11:37:33,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +61: [2023-04-29 11:37:33,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +36: [2023-04-29 11:37:33,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +61: [2023-04-29 11:37:33,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 0: [2023-04-29 11:37:33,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +17: [2023-04-29 11:37:33,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +31: [2023-04-29 11:37:33,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +31: [2023-04-29 11:37:33,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +59: [2023-04-29 11:37:33,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +36: [2023-04-29 11:37:33,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... + 9: [2023-04-29 11:37:33,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +35: [2023-04-29 11:37:33,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 9: [2023-04-29 11:37:33,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +35: [2023-04-29 11:37:33,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +31: [2023-04-29 11:37:33,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +31: [2023-04-29 11:37:33,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +31: [2023-04-29 11:37:33,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 4: [2023-04-29 11:37:33,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... + 6: [2023-04-29 11:37:33,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 6: [2023-04-29 11:37:33,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 4: [2023-04-29 11:37:33,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +52: [2023-04-29 11:37:33,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +12: [2023-04-29 11:37:33,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +36: [2023-04-29 11:37:33,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... + 6: [2023-04-29 11:37:33,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +36: [2023-04-29 11:37:33,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 0: [2023-04-29 11:37:33,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 0: [2023-04-29 11:37:33,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 0: [2023-04-29 11:37:33,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +52: [2023-04-29 11:37:33,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 2: [2023-04-29 11:37:33,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +22: [2023-04-29 11:37:33,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +31: [2023-04-29 11:37:33,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 2: [2023-04-29 11:37:33,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 0: [2023-04-29 11:37:33,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 0: [2023-04-29 11:37:33,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +31: [2023-04-29 11:37:33,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... + 9: [2023-04-29 11:37:33,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +22: [2023-04-29 11:37:33,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 2: [2023-04-29 11:37:33,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +22: [2023-04-29 11:37:33,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +31: [2023-04-29 11:37:33,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +22: [2023-04-29 11:37:33,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +36: [2023-04-29 11:37:33,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +45: [2023-04-29 11:37:33,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +31: [2023-04-29 11:37:33,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... + 0: [2023-04-29 11:37:33,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +36: [2023-04-29 11:37:33,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +36: [2023-04-29 11:37:33,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +52: [2023-04-29 11:37:33,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +52: [2023-04-29 11:37:33,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +36: [2023-04-29 11:37:33,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +31: [2023-04-29 11:37:33,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 7: [2023-04-29 11:37:33,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... + 7: [2023-04-29 11:37:33,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +52: [2023-04-29 11:37:33,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +16: [2023-04-29 11:37:33,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +14: [2023-04-29 11:37:33,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 0: [2023-04-29 11:37:33,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +45: [2023-04-29 11:37:33,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 0: [2023-04-29 11:37:33,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... + 0: [2023-04-29 11:37:33,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +31: [2023-04-29 11:37:33,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +45: [2023-04-29 11:37:33,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +45: [2023-04-29 11:37:33,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +16: [2023-04-29 11:37:33,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +56: [2023-04-29 11:37:33,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +16: [2023-04-29 11:37:33,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... + 7: [2023-04-29 11:37:33,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +28: [2023-04-29 11:37:33,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 7: [2023-04-29 11:37:33,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +52: [2023-04-29 11:37:33,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +52: [2023-04-29 11:37:33,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +22: [2023-04-29 11:37:33,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +22: [2023-04-29 11:37:33,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +22: [2023-04-29 11:37:33,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +22: [2023-04-29 11:37:33,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +28: [2023-04-29 11:37:33,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... + 8: [2023-04-29 11:37:33,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 8: [2023-04-29 11:37:33,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +16: [2023-04-29 11:37:33,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... + 8: [2023-04-29 11:37:33,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 8: [2023-04-29 11:37:33,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +51: [2023-04-29 11:37:33,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +14: [2023-04-29 11:37:33,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +26: [2023-04-29 11:37:33,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +29: [2023-04-29 11:37:33,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +29: [2023-04-29 11:37:33,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +29: [2023-04-29 11:37:33,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +14: [2023-04-29 11:37:33,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +14: [2023-04-29 11:37:33,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +52: [2023-04-29 11:37:33,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +29: [2023-04-29 11:37:33,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +14: [2023-04-29 11:37:33,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +50: [2023-04-29 11:37:33,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +56: [2023-04-29 11:37:33,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +22: [2023-04-29 11:37:33,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +22: [2023-04-29 11:37:33,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +54: [2023-04-29 11:37:33,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +54: [2023-04-29 11:37:33,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +51: [2023-04-29 11:37:33,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +51: [2023-04-29 11:37:33,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +51: [2023-04-29 11:37:33,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +17: [2023-04-29 11:37:33,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +22: [2023-04-29 11:37:33,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +14: [2023-04-29 11:37:33,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +26: [2023-04-29 11:37:33,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +22: [2023-04-29 11:37:33,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +17: [2023-04-29 11:37:33,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 8: [2023-04-29 11:37:33,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +12: [2023-04-29 11:37:33,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +12: [2023-04-29 11:37:33,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 8: [2023-04-29 11:37:33,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +56: [2023-04-29 11:37:33,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +17: [2023-04-29 11:37:33,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +54: [2023-04-29 11:37:33,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +56: [2023-04-29 11:37:33,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +54: [2023-04-29 11:37:33,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +54: [2023-04-29 11:37:33,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +28: [2023-04-29 11:37:33,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +28: [2023-04-29 11:37:33,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +17: [2023-04-29 11:37:33,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +29: [2023-04-29 11:37:33,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +29: [2023-04-29 11:37:33,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +29: [2023-04-29 11:37:33,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +29: [2023-04-29 11:37:33,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 8: [2023-04-29 11:37:33,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 8: [2023-04-29 11:37:33,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 7: [2023-04-29 11:37:33,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +12: [2023-04-29 11:37:33,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +26: [2023-04-29 11:37:33,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +14: [2023-04-29 11:37:33,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +18: [2023-04-29 11:37:33,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +18: [2023-04-29 11:37:33,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +28: [2023-04-29 11:37:33,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +44: [2023-04-29 11:37:33,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +44: [2023-04-29 11:37:33,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +44: [2023-04-29 11:37:33,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +44: [2023-04-29 11:37:33,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +26: [2023-04-29 11:37:33,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +18: [2023-04-29 11:37:33,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +18: [2023-04-29 11:37:33,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +14: [2023-04-29 11:37:33,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +12: [2023-04-29 11:37:33,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +24: [2023-04-29 11:37:33,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +24: [2023-04-29 11:37:33,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 0: [2023-04-29 11:37:33,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +26: [2023-04-29 11:37:33,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +26: [2023-04-29 11:37:33,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +31: [2023-04-29 11:37:33,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +45: [2023-04-29 11:37:33,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +31: [2023-04-29 11:37:33,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 5: [2023-04-29 11:37:33,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. + 5: [2023-04-29 11:37:33,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. + 5: [2023-04-29 11:37:33,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +28: [2023-04-29 11:37:33,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +28: [2023-04-29 11:37:33,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... + 5: [2023-04-29 11:37:33,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_14-model_01-model_states.pt. +31: [2023-04-29 11:37:33,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +44: [2023-04-29 11:37:33,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 0: [2023-04-29 11:37:33,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 0: [2023-04-29 11:37:33,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +24: [2023-04-29 11:37:33,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +24: [2023-04-29 11:37:33,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +18: [2023-04-29 11:37:33,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +24: [2023-04-29 11:37:33,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +44: [2023-04-29 11:37:33,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +28: [2023-04-29 11:37:33,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +44: [2023-04-29 11:37:33,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +24: [2023-04-29 11:37:33,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +31: [2023-04-29 11:37:33,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +18: [2023-04-29 11:37:33,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +24: [2023-04-29 11:37:33,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +44: [2023-04-29 11:37:33,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +44: [2023-04-29 11:37:33,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +18: [2023-04-29 11:37:33,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 0: [2023-04-29 11:37:33,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +45: [2023-04-29 11:37:33,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +26: [2023-04-29 11:37:33,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +26: [2023-04-29 11:37:33,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +14: [2023-04-29 11:37:33,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 8: [2023-04-29 11:37:33,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +18: [2023-04-29 11:37:33,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +50: [2023-04-29 11:37:33,349] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +24: [2023-04-29 11:37:33,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +45: [2023-04-29 11:37:33,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +45: [2023-04-29 11:37:33,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +54: [2023-04-29 11:37:33,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +24: [2023-04-29 11:37:33,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +24: [2023-04-29 11:37:33,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +63: [2023-04-29 11:37:33,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +44: [2023-04-29 11:37:33,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +44: [2023-04-29 11:37:33,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +44: [2023-04-29 11:37:33,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +50: [2023-04-29 11:37:33,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 8: [2023-04-29 11:37:33,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +44: [2023-04-29 11:37:33,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +50: [2023-04-29 11:37:33,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +14: [2023-04-29 11:37:33,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +39: [2023-04-29 11:37:33,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +44: [2023-04-29 11:37:33,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +44: [2023-04-29 11:37:33,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +24: [2023-04-29 11:37:33,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +16: [2023-04-29 11:37:33,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +16: [2023-04-29 11:37:33,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +16: [2023-04-29 11:37:33,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +59: [2023-04-29 11:37:33,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +16: [2023-04-29 11:37:33,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +54: [2023-04-29 11:37:33,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +63: [2023-04-29 11:37:33,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +15: [2023-04-29 11:37:33,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +15: [2023-04-29 11:37:33,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +15: [2023-04-29 11:37:33,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +44: [2023-04-29 11:37:33,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +24: [2023-04-29 11:37:33,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +24: [2023-04-29 11:37:33,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +54: [2023-04-29 11:37:33,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +54: [2023-04-29 11:37:33,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +50: [2023-04-29 11:37:33,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +14: [2023-04-29 11:37:33,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +59: [2023-04-29 11:37:33,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +39: [2023-04-29 11:37:33,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +39: [2023-04-29 11:37:33,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +39: [2023-04-29 11:37:33,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +61: [2023-04-29 11:37:33,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +27: [2023-04-29 11:37:33,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +27: [2023-04-29 11:37:33,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +27: [2023-04-29 11:37:33,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +61: [2023-04-29 11:37:33,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +16: [2023-04-29 11:37:33,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +14: [2023-04-29 11:37:33,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +14: [2023-04-29 11:37:33,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +43: [2023-04-29 11:37:33,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +43: [2023-04-29 11:37:33,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +27: [2023-04-29 11:37:33,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +14: [2023-04-29 11:37:33,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +24: [2023-04-29 11:37:33,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +15: [2023-04-29 11:37:33,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +16: [2023-04-29 11:37:33,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 5: [2023-04-29 11:37:33,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +24: [2023-04-29 11:37:33,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... + 1: [2023-04-29 11:37:33,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +16: [2023-04-29 11:37:33,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +24: [2023-04-29 11:37:33,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... + 1: [2023-04-29 11:37:33,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +15: [2023-04-29 11:37:33,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +15: [2023-04-29 11:37:33,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +15: [2023-04-29 11:37:33,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +43: [2023-04-29 11:37:33,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +36: [2023-04-29 11:37:33,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +43: [2023-04-29 11:37:33,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +14: [2023-04-29 11:37:33,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +36: [2023-04-29 11:37:33,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +51: [2023-04-29 11:37:33,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +51: [2023-04-29 11:37:33,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +16: [2023-04-29 11:37:33,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +51: [2023-04-29 11:37:33,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 8: [2023-04-29 11:37:33,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +63: [2023-04-29 11:37:33,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +63: [2023-04-29 11:37:33,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +59: [2023-04-29 11:37:33,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +59: [2023-04-29 11:37:33,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 5: [2023-04-29 11:37:33,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +14: [2023-04-29 11:37:33,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +15: [2023-04-29 11:37:33,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +15: [2023-04-29 11:37:33,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 5: [2023-04-29 11:37:33,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +59: [2023-04-29 11:37:33,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +59: [2023-04-29 11:37:33,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +61: [2023-04-29 11:37:33,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +51: [2023-04-29 11:37:33,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +61: [2023-04-29 11:37:33,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +15: [2023-04-29 11:37:33,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... + 1: [2023-04-29 11:37:33,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +57: [2023-04-29 11:37:33,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 8: [2023-04-29 11:37:33,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 8: [2023-04-29 11:37:33,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +57: [2023-04-29 11:37:33,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 5: [2023-04-29 11:37:33,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt... +57: [2023-04-29 11:37:33,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +57: [2023-04-29 11:37:33,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +59: [2023-04-29 11:37:33,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +15: [2023-04-29 11:37:33,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +57: [2023-04-29 11:37:33,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +57: [2023-04-29 11:37:33,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +57: [2023-04-29 11:37:33,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +57: [2023-04-29 11:37:33,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +59: [2023-04-29 11:37:33,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +63: [2023-04-29 11:37:33,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +15: [2023-04-29 11:37:33,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 1: [2023-04-29 11:37:33,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +15: [2023-04-29 11:37:33,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 6: [2023-04-29 11:37:33,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +22: [2023-04-29 11:37:33,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +22: [2023-04-29 11:37:33,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +54: [2023-04-29 11:37:33,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +15: [2023-04-29 11:37:33,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +59: [2023-04-29 11:37:33,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +50: [2023-04-29 11:37:33,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 8: [2023-04-29 11:37:33,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +57: [2023-04-29 11:37:33,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +57: [2023-04-29 11:37:33,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +57: [2023-04-29 11:37:33,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +36: [2023-04-29 11:37:33,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +15: [2023-04-29 11:37:33,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +57: [2023-04-29 11:37:33,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +57: [2023-04-29 11:37:33,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +57: [2023-04-29 11:37:33,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +57: [2023-04-29 11:37:33,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +22: [2023-04-29 11:37:33,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +57: [2023-04-29 11:37:33,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +36: [2023-04-29 11:37:33,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +63: [2023-04-29 11:37:33,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 8: [2023-04-29 11:37:33,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... + 8: [2023-04-29 11:37:33,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +15: [2023-04-29 11:37:33,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +22: [2023-04-29 11:37:33,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +22: [2023-04-29 11:37:33,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +59: [2023-04-29 11:37:33,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +30: [2023-04-29 11:37:33,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +30: [2023-04-29 11:37:33,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +30: [2023-04-29 11:37:33,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +30: [2023-04-29 11:37:33,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +39: [2023-04-29 11:37:33,389] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +59: [2023-04-29 11:37:33,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +19: [2023-04-29 11:37:33,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +19: [2023-04-29 11:37:33,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +19: [2023-04-29 11:37:33,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +19: [2023-04-29 11:37:33,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +61: [2023-04-29 11:37:33,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +50: [2023-04-29 11:37:33,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +22: [2023-04-29 11:37:33,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +39: [2023-04-29 11:37:33,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +61: [2023-04-29 11:37:33,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +39: [2023-04-29 11:37:33,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +19: [2023-04-29 11:37:33,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +39: [2023-04-29 11:37:33,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +19: [2023-04-29 11:37:33,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +54: [2023-04-29 11:37:33,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +19: [2023-04-29 11:37:33,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +22: [2023-04-29 11:37:33,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +54: [2023-04-29 11:37:33,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +27: [2023-04-29 11:37:33,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +19: [2023-04-29 11:37:33,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +27: [2023-04-29 11:37:33,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +27: [2023-04-29 11:37:33,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +44: [2023-04-29 11:37:33,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +27: [2023-04-29 11:37:33,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +59: [2023-04-29 11:37:33,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +50: [2023-04-29 11:37:33,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +22: [2023-04-29 11:37:33,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +29: [2023-04-29 11:37:33,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +43: [2023-04-29 11:37:33,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +36: [2023-04-29 11:37:33,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +36: [2023-04-29 11:37:33,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 6: [2023-04-29 11:37:33,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 8: [2023-04-29 11:37:33,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +43: [2023-04-29 11:37:33,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +43: [2023-04-29 11:37:33,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +43: [2023-04-29 11:37:33,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +63: [2023-04-29 11:37:33,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +29: [2023-04-29 11:37:33,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 8: [2023-04-29 11:37:33,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +59: [2023-04-29 11:37:33,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +59: [2023-04-29 11:37:33,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +22: [2023-04-29 11:37:33,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +59: [2023-04-29 11:37:33,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +59: [2023-04-29 11:37:33,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +63: [2023-04-29 11:37:33,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +22: [2023-04-29 11:37:33,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +61: [2023-04-29 11:37:33,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +54: [2023-04-29 11:37:33,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +29: [2023-04-29 11:37:33,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +29: [2023-04-29 11:37:33,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 6: [2023-04-29 11:37:33,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +44: [2023-04-29 11:37:33,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +18: [2023-04-29 11:37:33,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +61: [2023-04-29 11:37:33,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +54: [2023-04-29 11:37:33,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +24: [2023-04-29 11:37:33,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +24: [2023-04-29 11:37:33,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +26: [2023-04-29 11:37:33,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +26: [2023-04-29 11:37:33,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +26: [2023-04-29 11:37:33,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +26: [2023-04-29 11:37:33,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +54: [2023-04-29 11:37:33,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +22: [2023-04-29 11:37:33,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +22: [2023-04-29 11:37:33,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +24: [2023-04-29 11:37:33,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +54: [2023-04-29 11:37:33,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +50: [2023-04-29 11:37:33,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +50: [2023-04-29 11:37:33,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +26: [2023-04-29 11:37:33,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +44: [2023-04-29 11:37:33,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +26: [2023-04-29 11:37:33,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +36: [2023-04-29 11:37:33,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 8: [2023-04-29 11:37:33,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +50: [2023-04-29 11:37:33,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. + 8: [2023-04-29 11:37:33,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +26: [2023-04-29 11:37:33,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +50: [2023-04-29 11:37:33,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +26: [2023-04-29 11:37:33,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +36: [2023-04-29 11:37:33,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +24: [2023-04-29 11:37:33,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +44: [2023-04-29 11:37:33,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +30: [2023-04-29 11:37:33,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +30: [2023-04-29 11:37:33,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +30: [2023-04-29 11:37:33,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +18: [2023-04-29 11:37:33,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +18: [2023-04-29 11:37:33,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +18: [2023-04-29 11:37:33,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +44: [2023-04-29 11:37:33,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +54: [2023-04-29 11:37:33,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +54: [2023-04-29 11:37:33,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +14: [2023-04-29 11:37:33,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +30: [2023-04-29 11:37:33,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +29: [2023-04-29 11:37:33,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 8: [2023-04-29 11:37:33,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +14: [2023-04-29 11:37:33,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +29: [2023-04-29 11:37:33,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +54: [2023-04-29 11:37:33,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +54: [2023-04-29 11:37:33,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... + 8: [2023-04-29 11:37:33,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +18: [2023-04-29 11:37:33,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +16: [2023-04-29 11:37:33,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +22: [2023-04-29 11:37:33,432] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +23: [2023-04-29 11:37:33,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +23: [2023-04-29 11:37:33,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +23: [2023-04-29 11:37:33,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +23: [2023-04-29 11:37:33,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 1: [2023-04-29 11:37:33,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 1: [2023-04-29 11:37:33,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 1: [2023-04-29 11:37:33,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 1: [2023-04-29 11:37:33,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +29: [2023-04-29 11:37:33,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +29: [2023-04-29 11:37:33,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +44: [2023-04-29 11:37:33,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +25: [2023-04-29 11:37:33,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +25: [2023-04-29 11:37:33,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +25: [2023-04-29 11:37:33,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +25: [2023-04-29 11:37:33,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +24: [2023-04-29 11:37:33,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +24: [2023-04-29 11:37:33,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 5: [2023-04-29 11:37:33,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 1: [2023-04-29 11:37:33,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +53: [2023-04-29 11:37:33,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +22: [2023-04-29 11:37:33,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +23: [2023-04-29 11:37:33,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +53: [2023-04-29 11:37:33,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +53: [2023-04-29 11:37:33,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +53: [2023-04-29 11:37:33,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +53: [2023-04-29 11:37:33,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +53: [2023-04-29 11:37:33,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +53: [2023-04-29 11:37:33,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +14: [2023-04-29 11:37:33,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +14: [2023-04-29 11:37:33,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +53: [2023-04-29 11:37:33,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +23: [2023-04-29 11:37:33,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +23: [2023-04-29 11:37:33,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +23: [2023-04-29 11:37:33,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +25: [2023-04-29 11:37:33,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +24: [2023-04-29 11:37:33,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 4: [2023-04-29 11:37:33,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 4: [2023-04-29 11:37:33,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +14: [2023-04-29 11:37:33,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 4: [2023-04-29 11:37:33,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +25: [2023-04-29 11:37:33,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +37: [2023-04-29 11:37:33,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +37: [2023-04-29 11:37:33,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +37: [2023-04-29 11:37:33,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +37: [2023-04-29 11:37:33,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +50: [2023-04-29 11:37:33,442] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +50: [2023-04-29 11:37:33,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +53: [2023-04-29 11:37:33,442] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +25: [2023-04-29 11:37:33,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +25: [2023-04-29 11:37:33,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 5: [2023-04-29 11:37:33,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +16: [2023-04-29 11:37:33,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +16: [2023-04-29 11:37:33,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +53: [2023-04-29 11:37:33,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... + 5: [2023-04-29 11:37:33,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. +53: [2023-04-29 11:37:33,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +53: [2023-04-29 11:37:33,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +44: [2023-04-29 11:37:33,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +53: [2023-04-29 11:37:33,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... + 4: [2023-04-29 11:37:33,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +22: [2023-04-29 11:37:33,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +53: [2023-04-29 11:37:33,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +14: [2023-04-29 11:37:33,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +53: [2023-04-29 11:37:33,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +43: [2023-04-29 11:37:33,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +43: [2023-04-29 11:37:33,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +14: [2023-04-29 11:37:33,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +53: [2023-04-29 11:37:33,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +50: [2023-04-29 11:37:33,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 4: [2023-04-29 11:37:33,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 4: [2023-04-29 11:37:33,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +44: [2023-04-29 11:37:33,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 4: [2023-04-29 11:37:33,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +14: [2023-04-29 11:37:33,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +15: [2023-04-29 11:37:33,447] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +43: [2023-04-29 11:37:33,447] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +43: [2023-04-29 11:37:33,447] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +57: [2023-04-29 11:37:33,447] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +57: [2023-04-29 11:37:33,447] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +22: [2023-04-29 11:37:33,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,448] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +24: [2023-04-29 11:37:33,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +15: [2023-04-29 11:37:33,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +50: [2023-04-29 11:37:33,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 5: [2023-04-29 11:37:33,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 5: [2023-04-29 11:37:33,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_00-model_states.pt. + 1: [2023-04-29 11:37:33,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 8: [2023-04-29 11:37:33,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 5: [2023-04-29 11:37:33,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +57: [2023-04-29 11:37:33,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +57: [2023-04-29 11:37:33,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. + 8: [2023-04-29 11:37:33,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 4: [2023-04-29 11:37:33,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +43: [2023-04-29 11:37:33,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +16: [2023-04-29 11:37:33,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +43: [2023-04-29 11:37:33,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +43: [2023-04-29 11:37:33,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,453] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +43: [2023-04-29 11:37:33,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +15: [2023-04-29 11:37:33,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +37: [2023-04-29 11:37:33,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +37: [2023-04-29 11:37:33,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +37: [2023-04-29 11:37:33,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. + 5: [2023-04-29 11:37:33,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... + 5: [2023-04-29 11:37:33,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt... +15: [2023-04-29 11:37:33,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +37: [2023-04-29 11:37:33,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +18: [2023-04-29 11:37:33,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +37: [2023-04-29 11:37:33,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +18: [2023-04-29 11:37:33,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +19: [2023-04-29 11:37:33,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +58: [2023-04-29 11:37:33,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +58: [2023-04-29 11:37:33,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +58: [2023-04-29 11:37:33,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +58: [2023-04-29 11:37:33,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +18: [2023-04-29 11:37:33,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +16: [2023-04-29 11:37:33,463] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +19: [2023-04-29 11:37:33,464] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +19: [2023-04-29 11:37:33,464] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +27: [2023-04-29 11:37:33,464] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +37: [2023-04-29 11:37:33,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +37: [2023-04-29 11:37:33,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +37: [2023-04-29 11:37:33,466] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +19: [2023-04-29 11:37:33,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 1: [2023-04-29 11:37:33,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +37: [2023-04-29 11:37:33,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +20: [2023-04-29 11:37:33,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +20: [2023-04-29 11:37:33,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +27: [2023-04-29 11:37:33,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 1: [2023-04-29 11:37:33,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,470] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,470] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +27: [2023-04-29 11:37:33,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +11: [2023-04-29 11:37:33,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +11: [2023-04-29 11:37:33,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +20: [2023-04-29 11:37:33,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +27: [2023-04-29 11:37:33,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +20: [2023-04-29 11:37:33,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +11: [2023-04-29 11:37:33,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +11: [2023-04-29 11:37:33,473] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +37: [2023-04-29 11:37:33,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +43: [2023-04-29 11:37:33,473] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +43: [2023-04-29 11:37:33,473] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +57: [2023-04-29 11:37:33,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +57: [2023-04-29 11:37:33,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +37: [2023-04-29 11:37:33,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +16: [2023-04-29 11:37:33,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +20: [2023-04-29 11:37:33,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +27: [2023-04-29 11:37:33,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +27: [2023-04-29 11:37:33,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +43: [2023-04-29 11:37:33,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +43: [2023-04-29 11:37:33,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +20: [2023-04-29 11:37:33,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +20: [2023-04-29 11:37:33,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +20: [2023-04-29 11:37:33,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +27: [2023-04-29 11:37:33,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +11: [2023-04-29 11:37:33,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +11: [2023-04-29 11:37:33,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +11: [2023-04-29 11:37:33,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +57: [2023-04-29 11:37:33,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +15: [2023-04-29 11:37:33,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +11: [2023-04-29 11:37:33,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +16: [2023-04-29 11:37:33,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +37: [2023-04-29 11:37:33,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +15: [2023-04-29 11:37:33,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +27: [2023-04-29 11:37:33,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... + 1: [2023-04-29 11:37:33,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +43: [2023-04-29 11:37:33,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +43: [2023-04-29 11:37:33,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +43: [2023-04-29 11:37:33,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +43: [2023-04-29 11:37:33,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +57: [2023-04-29 11:37:33,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +15: [2023-04-29 11:37:33,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +15: [2023-04-29 11:37:33,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +26: [2023-04-29 11:37:33,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +16: [2023-04-29 11:37:33,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +19: [2023-04-29 11:37:33,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +26: [2023-04-29 11:37:33,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +58: [2023-04-29 11:37:33,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +58: [2023-04-29 11:37:33,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +58: [2023-04-29 11:37:33,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +58: [2023-04-29 11:37:33,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +26: [2023-04-29 11:37:33,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +26: [2023-04-29 11:37:33,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +30: [2023-04-29 11:37:33,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +19: [2023-04-29 11:37:33,493] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +30: [2023-04-29 11:37:33,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +30: [2023-04-29 11:37:33,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +30: [2023-04-29 11:37:33,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +30: [2023-04-29 11:37:33,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +19: [2023-04-29 11:37:33,493] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +30: [2023-04-29 11:37:33,495] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +30: [2023-04-29 11:37:33,495] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +19: [2023-04-29 11:37:33,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +23: [2023-04-29 11:37:33,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +50: [2023-04-29 11:37:33,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +30: [2023-04-29 11:37:33,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +30: [2023-04-29 11:37:33,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +30: [2023-04-29 11:37:33,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +25: [2023-04-29 11:37:33,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +30: [2023-04-29 11:37:33,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +30: [2023-04-29 11:37:33,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +30: [2023-04-29 11:37:33,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +30: [2023-04-29 11:37:33,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +30: [2023-04-29 11:37:33,502] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +53: [2023-04-29 11:37:33,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +40: [2023-04-29 11:37:33,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +40: [2023-04-29 11:37:33,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +40: [2023-04-29 11:37:33,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +53: [2023-04-29 11:37:33,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +40: [2023-04-29 11:37:33,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +23: [2023-04-29 11:37:33,505] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +25: [2023-04-29 11:37:33,505] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +50: [2023-04-29 11:37:33,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +25: [2023-04-29 11:37:33,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +25: [2023-04-29 11:37:33,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +40: [2023-04-29 11:37:33,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +23: [2023-04-29 11:37:33,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +23: [2023-04-29 11:37:33,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +30: [2023-04-29 11:37:33,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +40: [2023-04-29 11:37:33,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +40: [2023-04-29 11:37:33,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +50: [2023-04-29 11:37:33,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +50: [2023-04-29 11:37:33,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +40: [2023-04-29 11:37:33,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 4: [2023-04-29 11:37:33,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +21: [2023-04-29 11:37:33,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +21: [2023-04-29 11:37:33,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +21: [2023-04-29 11:37:33,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +21: [2023-04-29 11:37:33,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +26: [2023-04-29 11:37:33,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +26: [2023-04-29 11:37:33,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +11: [2023-04-29 11:37:33,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +11: [2023-04-29 11:37:33,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +11: [2023-04-29 11:37:33,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +11: [2023-04-29 11:37:33,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +43: [2023-04-29 11:37:33,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +50: [2023-04-29 11:37:33,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +50: [2023-04-29 11:37:33,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +37: [2023-04-29 11:37:33,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +49: [2023-04-29 11:37:33,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +49: [2023-04-29 11:37:33,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +23: [2023-04-29 11:37:33,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +49: [2023-04-29 11:37:33,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +49: [2023-04-29 11:37:33,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +26: [2023-04-29 11:37:33,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +39: [2023-04-29 11:37:33,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +39: [2023-04-29 11:37:33,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +43: [2023-04-29 11:37:33,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +26: [2023-04-29 11:37:33,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 4: [2023-04-29 11:37:33,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 4: [2023-04-29 11:37:33,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 9: [2023-04-29 11:37:33,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 9: [2023-04-29 11:37:33,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +62: [2023-04-29 11:37:33,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +62: [2023-04-29 11:37:33,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +62: [2023-04-29 11:37:33,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +27: [2023-04-29 11:37:33,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +27: [2023-04-29 11:37:33,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +62: [2023-04-29 11:37:33,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +39: [2023-04-29 11:37:33,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. +53: [2023-04-29 11:37:33,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +47: [2023-04-29 11:37:33,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +47: [2023-04-29 11:37:33,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +39: [2023-04-29 11:37:33,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_41-model_01-model_states.pt. + 9: [2023-04-29 11:37:33,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +53: [2023-04-29 11:37:33,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. + 9: [2023-04-29 11:37:33,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +25: [2023-04-29 11:37:33,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +10: [2023-04-29 11:37:33,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +10: [2023-04-29 11:37:33,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +27: [2023-04-29 11:37:33,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +53: [2023-04-29 11:37:33,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +27: [2023-04-29 11:37:33,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +43: [2023-04-29 11:37:33,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +47: [2023-04-29 11:37:33,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +43: [2023-04-29 11:37:33,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +47: [2023-04-29 11:37:33,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +50: [2023-04-29 11:37:33,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +27: [2023-04-29 11:37:33,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +27: [2023-04-29 11:37:33,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +10: [2023-04-29 11:37:33,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +25: [2023-04-29 11:37:33,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +10: [2023-04-29 11:37:33,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 1: [2023-04-29 11:37:33,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +20: [2023-04-29 11:37:33,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 9: [2023-04-29 11:37:33,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 9: [2023-04-29 11:37:33,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 9: [2023-04-29 11:37:33,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +53: [2023-04-29 11:37:33,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +27: [2023-04-29 11:37:33,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +27: [2023-04-29 11:37:33,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 9: [2023-04-29 11:37:33,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +10: [2023-04-29 11:37:33,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +10: [2023-04-29 11:37:33,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +50: [2023-04-29 11:37:33,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +23: [2023-04-29 11:37:33,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +10: [2023-04-29 11:37:33,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +10: [2023-04-29 11:37:33,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 1: [2023-04-29 11:37:33,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 4: [2023-04-29 11:37:33,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +43: [2023-04-29 11:37:33,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +37: [2023-04-29 11:37:33,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 6: [2023-04-29 11:37:33,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 1: [2023-04-29 11:37:33,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 6: [2023-04-29 11:37:33,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +13: [2023-04-29 11:37:33,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +13: [2023-04-29 11:37:33,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +13: [2023-04-29 11:37:33,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +25: [2023-04-29 11:37:33,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +37: [2023-04-29 11:37:33,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 4: [2023-04-29 11:37:33,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +25: [2023-04-29 11:37:33,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +13: [2023-04-29 11:37:33,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +23: [2023-04-29 11:37:33,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +23: [2023-04-29 11:37:33,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +21: [2023-04-29 11:37:33,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... + 1: [2023-04-29 11:37:33,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +37: [2023-04-29 11:37:33,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... + 1: [2023-04-29 11:37:33,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +21: [2023-04-29 11:37:33,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +11: [2023-04-29 11:37:33,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 7: [2023-04-29 11:37:33,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 7: [2023-04-29 11:37:33,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 7: [2023-04-29 11:37:33,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 7: [2023-04-29 11:37:33,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +49: [2023-04-29 11:37:33,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +11: [2023-04-29 11:37:33,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +11: [2023-04-29 11:37:33,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +20: [2023-04-29 11:37:33,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +49: [2023-04-29 11:37:33,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +49: [2023-04-29 11:37:33,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +21: [2023-04-29 11:37:33,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +21: [2023-04-29 11:37:33,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +49: [2023-04-29 11:37:33,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +20: [2023-04-29 11:37:33,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +10: [2023-04-29 11:37:33,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +10: [2023-04-29 11:37:33,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +10: [2023-04-29 11:37:33,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +10: [2023-04-29 11:37:33,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +11: [2023-04-29 11:37:33,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 7: [2023-04-29 11:37:33,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 2: [2023-04-29 11:37:33,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 2: [2023-04-29 11:37:33,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 2: [2023-04-29 11:37:33,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 2: [2023-04-29 11:37:33,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 7: [2023-04-29 11:37:33,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +18: [2023-04-29 11:37:33,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +18: [2023-04-29 11:37:33,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +18: [2023-04-29 11:37:33,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +18: [2023-04-29 11:37:33,551] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 7: [2023-04-29 11:37:33,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +28: [2023-04-29 11:37:33,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +28: [2023-04-29 11:37:33,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +11: [2023-04-29 11:37:33,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 7: [2023-04-29 11:37:33,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +47: [2023-04-29 11:37:33,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +47: [2023-04-29 11:37:33,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 4: [2023-04-29 11:37:33,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +28: [2023-04-29 11:37:33,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +47: [2023-04-29 11:37:33,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +28: [2023-04-29 11:37:33,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +47: [2023-04-29 11:37:33,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +12: [2023-04-29 11:37:33,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +12: [2023-04-29 11:37:33,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +12: [2023-04-29 11:37:33,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +12: [2023-04-29 11:37:33,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +19: [2023-04-29 11:37:33,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +19: [2023-04-29 11:37:33,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +53: [2023-04-29 11:37:33,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +43: [2023-04-29 11:37:33,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +62: [2023-04-29 11:37:33,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 4: [2023-04-29 11:37:33,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +39: [2023-04-29 11:37:33,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +39: [2023-04-29 11:37:33,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +19: [2023-04-29 11:37:33,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +43: [2023-04-29 11:37:33,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +43: [2023-04-29 11:37:33,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +20: [2023-04-29 11:37:33,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +19: [2023-04-29 11:37:33,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +11: [2023-04-29 11:37:33,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +28: [2023-04-29 11:37:33,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +28: [2023-04-29 11:37:33,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +53: [2023-04-29 11:37:33,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +55: [2023-04-29 11:37:33,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +55: [2023-04-29 11:37:33,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +55: [2023-04-29 11:37:33,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +62: [2023-04-29 11:37:33,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +55: [2023-04-29 11:37:33,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +12: [2023-04-29 11:37:33,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +62: [2023-04-29 11:37:33,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +39: [2023-04-29 11:37:33,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... +12: [2023-04-29 11:37:33,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +28: [2023-04-29 11:37:33,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +37: [2023-04-29 11:37:33,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +33: [2023-04-29 11:37:33,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +33: [2023-04-29 11:37:33,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +33: [2023-04-29 11:37:33,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +28: [2023-04-29 11:37:33,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +11: [2023-04-29 11:37:33,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +11: [2023-04-29 11:37:33,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +33: [2023-04-29 11:37:33,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +12: [2023-04-29 11:37:33,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +20: [2023-04-29 11:37:33,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +39: [2023-04-29 11:37:33,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt... + 5: [2023-04-29 11:37:33,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 5: [2023-04-29 11:37:33,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +12: [2023-04-29 11:37:33,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 5: [2023-04-29 11:37:33,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 5: [2023-04-29 11:37:33,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +62: [2023-04-29 11:37:33,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 2: [2023-04-29 11:37:33,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 2: [2023-04-29 11:37:33,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 2: [2023-04-29 11:37:33,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 2: [2023-04-29 11:37:33,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +13: [2023-04-29 11:37:33,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +30: [2023-04-29 11:37:33,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +30: [2023-04-29 11:37:33,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +37: [2023-04-29 11:37:33,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +37: [2023-04-29 11:37:33,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. + 4: [2023-04-29 11:37:33,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +37: [2023-04-29 11:37:33,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 2: [2023-04-29 11:37:33,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +37: [2023-04-29 11:37:33,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +30: [2023-04-29 11:37:33,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +30: [2023-04-29 11:37:33,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +40: [2023-04-29 11:37:33,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. + 2: [2023-04-29 11:37:33,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +11: [2023-04-29 11:37:33,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +40: [2023-04-29 11:37:33,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. + 5: [2023-04-29 11:37:33,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 5: [2023-04-29 11:37:33,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 5: [2023-04-29 11:37:33,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +20: [2023-04-29 11:37:33,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 2: [2023-04-29 11:37:33,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 5: [2023-04-29 11:37:33,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +20: [2023-04-29 11:37:33,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. + 2: [2023-04-29 11:37:33,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +20: [2023-04-29 11:37:33,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. + 6: [2023-04-29 11:37:33,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 6: [2023-04-29 11:37:33,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +20: [2023-04-29 11:37:33,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +10: [2023-04-29 11:37:33,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +13: [2023-04-29 11:37:33,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +13: [2023-04-29 11:37:33,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +20: [2023-04-29 11:37:33,574] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +13: [2023-04-29 11:37:33,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +13: [2023-04-29 11:37:33,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +13: [2023-04-29 11:37:33,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +55: [2023-04-29 11:37:33,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +55: [2023-04-29 11:37:33,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +55: [2023-04-29 11:37:33,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +18: [2023-04-29 11:37:33,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +55: [2023-04-29 11:37:33,577] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +18: [2023-04-29 11:37:33,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +20: [2023-04-29 11:37:33,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 2: [2023-04-29 11:37:33,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 2: [2023-04-29 11:37:33,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +55: [2023-04-29 11:37:33,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +31: [2023-04-29 11:37:33,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +31: [2023-04-29 11:37:33,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +10: [2023-04-29 11:37:33,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +31: [2023-04-29 11:37:33,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +13: [2023-04-29 11:37:33,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +13: [2023-04-29 11:37:33,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +10: [2023-04-29 11:37:33,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +10: [2023-04-29 11:37:33,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +31: [2023-04-29 11:37:33,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 2: [2023-04-29 11:37:33,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 2: [2023-04-29 11:37:33,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +18: [2023-04-29 11:37:33,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +18: [2023-04-29 11:37:33,584] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +55: [2023-04-29 11:37:33,584] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +55: [2023-04-29 11:37:33,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +31: [2023-04-29 11:37:33,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +19: [2023-04-29 11:37:33,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +14: [2023-04-29 11:37:33,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +14: [2023-04-29 11:37:33,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +55: [2023-04-29 11:37:33,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +37: [2023-04-29 11:37:33,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +31: [2023-04-29 11:37:33,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +31: [2023-04-29 11:37:33,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +14: [2023-04-29 11:37:33,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +14: [2023-04-29 11:37:33,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +19: [2023-04-29 11:37:33,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +11: [2023-04-29 11:37:33,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +31: [2023-04-29 11:37:33,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +19: [2023-04-29 11:37:33,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +13: [2023-04-29 11:37:33,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +13: [2023-04-29 11:37:33,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +33: [2023-04-29 11:37:33,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +29: [2023-04-29 11:37:33,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +29: [2023-04-29 11:37:33,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +29: [2023-04-29 11:37:33,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +55: [2023-04-29 11:37:33,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +29: [2023-04-29 11:37:33,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +40: [2023-04-29 11:37:33,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +40: [2023-04-29 11:37:33,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +33: [2023-04-29 11:37:33,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +55: [2023-04-29 11:37:33,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +33: [2023-04-29 11:37:33,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +55: [2023-04-29 11:37:33,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +33: [2023-04-29 11:37:33,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +55: [2023-04-29 11:37:33,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +37: [2023-04-29 11:37:33,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +17: [2023-04-29 11:37:33,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +17: [2023-04-29 11:37:33,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +40: [2023-04-29 11:37:33,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +17: [2023-04-29 11:37:33,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +17: [2023-04-29 11:37:33,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +19: [2023-04-29 11:37:33,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +14: [2023-04-29 11:37:33,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +14: [2023-04-29 11:37:33,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +14: [2023-04-29 11:37:33,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +14: [2023-04-29 11:37:33,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +13: [2023-04-29 11:37:33,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +20: [2023-04-29 11:37:33,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 9: [2023-04-29 11:37:33,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +13: [2023-04-29 11:37:33,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 3: [2023-04-29 11:37:33,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 3: [2023-04-29 11:37:33,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 3: [2023-04-29 11:37:33,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +37: [2023-04-29 11:37:33,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... + 3: [2023-04-29 11:37:33,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +11: [2023-04-29 11:37:33,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +11: [2023-04-29 11:37:33,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +27: [2023-04-29 11:37:33,597] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +27: [2023-04-29 11:37:33,597] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +49: [2023-04-29 11:37:33,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +49: [2023-04-29 11:37:33,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +49: [2023-04-29 11:37:33,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +49: [2023-04-29 11:37:33,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +30: [2023-04-29 11:37:33,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +37: [2023-04-29 11:37:33,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... + 3: [2023-04-29 11:37:33,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +27: [2023-04-29 11:37:33,601] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +27: [2023-04-29 11:37:33,601] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +30: [2023-04-29 11:37:33,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +30: [2023-04-29 11:37:33,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 3: [2023-04-29 11:37:33,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +20: [2023-04-29 11:37:33,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 9: [2023-04-29 11:37:33,601] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +38: [2023-04-29 11:37:33,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +38: [2023-04-29 11:37:33,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +38: [2023-04-29 11:37:33,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +38: [2023-04-29 11:37:33,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +21: [2023-04-29 11:37:33,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 3: [2023-04-29 11:37:33,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 9: [2023-04-29 11:37:33,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +20: [2023-04-29 11:37:33,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +49: [2023-04-29 11:37:33,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +40: [2023-04-29 11:37:33,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 3: [2023-04-29 11:37:33,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +20: [2023-04-29 11:37:33,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 9: [2023-04-29 11:37:33,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +37: [2023-04-29 11:37:33,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +30: [2023-04-29 11:37:33,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +20: [2023-04-29 11:37:33,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +49: [2023-04-29 11:37:33,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +49: [2023-04-29 11:37:33,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +49: [2023-04-29 11:37:33,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +21: [2023-04-29 11:37:33,608] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +37: [2023-04-29 11:37:33,608] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +37: [2023-04-29 11:37:33,608] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +21: [2023-04-29 11:37:33,610] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +11: [2023-04-29 11:37:33,611] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 4: [2023-04-29 11:37:33,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. + 4: [2023-04-29 11:37:33,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +49: [2023-04-29 11:37:33,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +32: [2023-04-29 11:37:33,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +32: [2023-04-29 11:37:33,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +32: [2023-04-29 11:37:33,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +32: [2023-04-29 11:37:33,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +21: [2023-04-29 11:37:33,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 7: [2023-04-29 11:37:33,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +49: [2023-04-29 11:37:33,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +17: [2023-04-29 11:37:33,614] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 4: [2023-04-29 11:37:33,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +21: [2023-04-29 11:37:33,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +29: [2023-04-29 11:37:33,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +11: [2023-04-29 11:37:33,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... + 4: [2023-04-29 11:37:33,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +10: [2023-04-29 11:37:33,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +10: [2023-04-29 11:37:33,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +10: [2023-04-29 11:37:33,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +21: [2023-04-29 11:37:33,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +29: [2023-04-29 11:37:33,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +49: [2023-04-29 11:37:33,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +23: [2023-04-29 11:37:33,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +23: [2023-04-29 11:37:33,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 6: [2023-04-29 11:37:33,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +49: [2023-04-29 11:37:33,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +49: [2023-04-29 11:37:33,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +10: [2023-04-29 11:37:33,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +49: [2023-04-29 11:37:33,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... + 7: [2023-04-29 11:37:33,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 7: [2023-04-29 11:37:33,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +29: [2023-04-29 11:37:33,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +21: [2023-04-29 11:37:33,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +17: [2023-04-29 11:37:33,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +29: [2023-04-29 11:37:33,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +17: [2023-04-29 11:37:33,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +23: [2023-04-29 11:37:33,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +23: [2023-04-29 11:37:33,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +40: [2023-04-29 11:37:33,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 7: [2023-04-29 11:37:33,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 9: [2023-04-29 11:37:33,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +39: [2023-04-29 11:37:33,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +17: [2023-04-29 11:37:33,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +11: [2023-04-29 11:37:33,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +21: [2023-04-29 11:37:33,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +39: [2023-04-29 11:37:33,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +27: [2023-04-29 11:37:33,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +27: [2023-04-29 11:37:33,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +28: [2023-04-29 11:37:33,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +40: [2023-04-29 11:37:33,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +46: [2023-04-29 11:37:33,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +46: [2023-04-29 11:37:33,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +49: [2023-04-29 11:37:33,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +49: [2023-04-29 11:37:33,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +27: [2023-04-29 11:37:33,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +46: [2023-04-29 11:37:33,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +46: [2023-04-29 11:37:33,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +12: [2023-04-29 11:37:33,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +12: [2023-04-29 11:37:33,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +13: [2023-04-29 11:37:33,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +28: [2023-04-29 11:37:33,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +39: [2023-04-29 11:37:33,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +25: [2023-04-29 11:37:33,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +25: [2023-04-29 11:37:33,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +25: [2023-04-29 11:37:33,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +25: [2023-04-29 11:37:33,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +11: [2023-04-29 11:37:33,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +39: [2023-04-29 11:37:33,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +27: [2023-04-29 11:37:33,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +12: [2023-04-29 11:37:33,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +38: [2023-04-29 11:37:33,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +39: [2023-04-29 11:37:33,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +11: [2023-04-29 11:37:33,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +48: [2023-04-29 11:37:33,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +48: [2023-04-29 11:37:33,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +48: [2023-04-29 11:37:33,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +28: [2023-04-29 11:37:33,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +28: [2023-04-29 11:37:33,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 0: [2023-04-29 11:37:33,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. + 0: [2023-04-29 11:37:33,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. + 0: [2023-04-29 11:37:33,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +48: [2023-04-29 11:37:33,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. + 0: [2023-04-29 11:37:33,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +12: [2023-04-29 11:37:33,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +38: [2023-04-29 11:37:33,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +13: [2023-04-29 11:37:33,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... + 9: [2023-04-29 11:37:33,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +41: [2023-04-29 11:37:33,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +41: [2023-04-29 11:37:33,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +11: [2023-04-29 11:37:33,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +39: [2023-04-29 11:37:33,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_00-model_states.pt. +55: [2023-04-29 11:37:33,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +38: [2023-04-29 11:37:33,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 4: [2023-04-29 11:37:33,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +41: [2023-04-29 11:37:33,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +11: [2023-04-29 11:37:33,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... + 9: [2023-04-29 11:37:33,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +41: [2023-04-29 11:37:33,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +39: [2023-04-29 11:37:33,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +38: [2023-04-29 11:37:33,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 6: [2023-04-29 11:37:33,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 2: [2023-04-29 11:37:33,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 2: [2023-04-29 11:37:33,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +18: [2023-04-29 11:37:33,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 9: [2023-04-29 11:37:33,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +31: [2023-04-29 11:37:33,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 7: [2023-04-29 11:37:33,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +32: [2023-04-29 11:37:33,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +11: [2023-04-29 11:37:33,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... + 4: [2023-04-29 11:37:33,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 4: [2023-04-29 11:37:33,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +32: [2023-04-29 11:37:33,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +10: [2023-04-29 11:37:33,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +39: [2023-04-29 11:37:33,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt... +18: [2023-04-29 11:37:33,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 2: [2023-04-29 11:37:33,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 4: [2023-04-29 11:37:33,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 7: [2023-04-29 11:37:33,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 6: [2023-04-29 11:37:33,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 7: [2023-04-29 11:37:33,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 7: [2023-04-29 11:37:33,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +32: [2023-04-29 11:37:33,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 6: [2023-04-29 11:37:33,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +13: [2023-04-29 11:37:33,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +13: [2023-04-29 11:37:33,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +32: [2023-04-29 11:37:33,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 5: [2023-04-29 11:37:33,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 5: [2023-04-29 11:37:33,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 5: [2023-04-29 11:37:33,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 5: [2023-04-29 11:37:33,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 2: [2023-04-29 11:37:33,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +18: [2023-04-29 11:37:33,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... + 6: [2023-04-29 11:37:33,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... + 6: [2023-04-29 11:37:33,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +21: [2023-04-29 11:37:33,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +21: [2023-04-29 11:37:33,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +18: [2023-04-29 11:37:33,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +23: [2023-04-29 11:37:33,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +10: [2023-04-29 11:37:33,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +21: [2023-04-29 11:37:33,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +23: [2023-04-29 11:37:33,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +47: [2023-04-29 11:37:33,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +47: [2023-04-29 11:37:33,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +21: [2023-04-29 11:37:33,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +10: [2023-04-29 11:37:33,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +47: [2023-04-29 11:37:33,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +47: [2023-04-29 11:37:33,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +47: [2023-04-29 11:37:33,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +47: [2023-04-29 11:37:33,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +47: [2023-04-29 11:37:33,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +42: [2023-04-29 11:37:33,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +42: [2023-04-29 11:37:33,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +47: [2023-04-29 11:37:33,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +46: [2023-04-29 11:37:33,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +46: [2023-04-29 11:37:33,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 6: [2023-04-29 11:37:33,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... + 7: [2023-04-29 11:37:33,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +10: [2023-04-29 11:37:33,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +10: [2023-04-29 11:37:33,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +34: [2023-04-29 11:37:33,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +34: [2023-04-29 11:37:33,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +42: [2023-04-29 11:37:33,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +42: [2023-04-29 11:37:33,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +18: [2023-04-29 11:37:33,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +18: [2023-04-29 11:37:33,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +46: [2023-04-29 11:37:33,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 7: [2023-04-29 11:37:33,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 6: [2023-04-29 11:37:33,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +47: [2023-04-29 11:37:33,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +21: [2023-04-29 11:37:33,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +21: [2023-04-29 11:37:33,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +46: [2023-04-29 11:37:33,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 2: [2023-04-29 11:37:33,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +10: [2023-04-29 11:37:33,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +48: [2023-04-29 11:37:33,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +21: [2023-04-29 11:37:33,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +23: [2023-04-29 11:37:33,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +47: [2023-04-29 11:37:33,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +14: [2023-04-29 11:37:33,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +48: [2023-04-29 11:37:33,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +48: [2023-04-29 11:37:33,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +10: [2023-04-29 11:37:33,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +21: [2023-04-29 11:37:33,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +25: [2023-04-29 11:37:33,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 2: [2023-04-29 11:37:33,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 2: [2023-04-29 11:37:33,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +47: [2023-04-29 11:37:33,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +19: [2023-04-29 11:37:33,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +19: [2023-04-29 11:37:33,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 7: [2023-04-29 11:37:33,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +62: [2023-04-29 11:37:33,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +47: [2023-04-29 11:37:33,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +62: [2023-04-29 11:37:33,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +62: [2023-04-29 11:37:33,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +52: [2023-04-29 11:37:33,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +52: [2023-04-29 11:37:33,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +28: [2023-04-29 11:37:33,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +28: [2023-04-29 11:37:33,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +62: [2023-04-29 11:37:33,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +62: [2023-04-29 11:37:33,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +62: [2023-04-29 11:37:33,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +62: [2023-04-29 11:37:33,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +47: [2023-04-29 11:37:33,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +20: [2023-04-29 11:37:33,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +62: [2023-04-29 11:37:33,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +47: [2023-04-29 11:37:33,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +34: [2023-04-29 11:37:33,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +34: [2023-04-29 11:37:33,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. + 2: [2023-04-29 11:37:33,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +23: [2023-04-29 11:37:33,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +19: [2023-04-29 11:37:33,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +52: [2023-04-29 11:37:33,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +47: [2023-04-29 11:37:33,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +52: [2023-04-29 11:37:33,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +12: [2023-04-29 11:37:33,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +47: [2023-04-29 11:37:33,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +48: [2023-04-29 11:37:33,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +55: [2023-04-29 11:37:33,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +10: [2023-04-29 11:37:33,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +12: [2023-04-29 11:37:33,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +18: [2023-04-29 11:37:33,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +18: [2023-04-29 11:37:33,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +55: [2023-04-29 11:37:33,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +55: [2023-04-29 11:37:33,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +55: [2023-04-29 11:37:33,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +48: [2023-04-29 11:37:33,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +25: [2023-04-29 11:37:33,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 7: [2023-04-29 11:37:33,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +48: [2023-04-29 11:37:33,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +31: [2023-04-29 11:37:33,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +31: [2023-04-29 11:37:33,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +31: [2023-04-29 11:37:33,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +25: [2023-04-29 11:37:33,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +20: [2023-04-29 11:37:33,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +25: [2023-04-29 11:37:33,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +62: [2023-04-29 11:37:33,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +12: [2023-04-29 11:37:33,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +52: [2023-04-29 11:37:33,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 2: [2023-04-29 11:37:33,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +62: [2023-04-29 11:37:33,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 2: [2023-04-29 11:37:33,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +52: [2023-04-29 11:37:33,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +45: [2023-04-29 11:37:33,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +45: [2023-04-29 11:37:33,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +45: [2023-04-29 11:37:33,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +28: [2023-04-29 11:37:33,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +45: [2023-04-29 11:37:33,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. + 3: [2023-04-29 11:37:33,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +48: [2023-04-29 11:37:33,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +19: [2023-04-29 11:37:33,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +19: [2023-04-29 11:37:33,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +41: [2023-04-29 11:37:33,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +52: [2023-04-29 11:37:33,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +35: [2023-04-29 11:37:33,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +35: [2023-04-29 11:37:33,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +35: [2023-04-29 11:37:33,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +35: [2023-04-29 11:37:33,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +19: [2023-04-29 11:37:33,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +55: [2023-04-29 11:37:33,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +55: [2023-04-29 11:37:33,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. + 0: [2023-04-29 11:37:33,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +13: [2023-04-29 11:37:33,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 0: [2023-04-29 11:37:33,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +41: [2023-04-29 11:37:33,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +40: [2023-04-29 11:37:33,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +40: [2023-04-29 11:37:33,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +48: [2023-04-29 11:37:33,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +40: [2023-04-29 11:37:33,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. + 8: [2023-04-29 11:37:33,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. + 8: [2023-04-29 11:37:33,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +13: [2023-04-29 11:37:33,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +13: [2023-04-29 11:37:33,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 0: [2023-04-29 11:37:33,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +52: [2023-04-29 11:37:33,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +62: [2023-04-29 11:37:33,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 8: [2023-04-29 11:37:33,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +28: [2023-04-29 11:37:33,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +12: [2023-04-29 11:37:33,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +14: [2023-04-29 11:37:33,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 8: [2023-04-29 11:37:33,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +48: [2023-04-29 11:37:33,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +48: [2023-04-29 11:37:33,667] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 7: [2023-04-29 11:37:33,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +40: [2023-04-29 11:37:33,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +10: [2023-04-29 11:37:33,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +49: [2023-04-29 11:37:33,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +10: [2023-04-29 11:37:33,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +41: [2023-04-29 11:37:33,667] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +62: [2023-04-29 11:37:33,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +62: [2023-04-29 11:37:33,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +55: [2023-04-29 11:37:33,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +55: [2023-04-29 11:37:33,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... + 0: [2023-04-29 11:37:33,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 0: [2023-04-29 11:37:33,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +62: [2023-04-29 11:37:33,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... + 0: [2023-04-29 11:37:33,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +19: [2023-04-29 11:37:33,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 0: [2023-04-29 11:37:33,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +17: [2023-04-29 11:37:33,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +62: [2023-04-29 11:37:33,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +62: [2023-04-29 11:37:33,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... + 2: [2023-04-29 11:37:33,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +48: [2023-04-29 11:37:33,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +31: [2023-04-29 11:37:33,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +13: [2023-04-29 11:37:33,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 0: [2023-04-29 11:37:33,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +20: [2023-04-29 11:37:33,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +13: [2023-04-29 11:37:33,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 2: [2023-04-29 11:37:33,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +41: [2023-04-29 11:37:33,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +14: [2023-04-29 11:37:33,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +13: [2023-04-29 11:37:33,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +55: [2023-04-29 11:37:33,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +17: [2023-04-29 11:37:33,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +13: [2023-04-29 11:37:33,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... + 2: [2023-04-29 11:37:33,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 3: [2023-04-29 11:37:33,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 3: [2023-04-29 11:37:33,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +13: [2023-04-29 11:37:33,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +10: [2023-04-29 11:37:33,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +10: [2023-04-29 11:37:33,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... + 7: [2023-04-29 11:37:33,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 7: [2023-04-29 11:37:33,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +20: [2023-04-29 11:37:33,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +13: [2023-04-29 11:37:33,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +12: [2023-04-29 11:37:33,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +12: [2023-04-29 11:37:33,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +12: [2023-04-29 11:37:33,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +12: [2023-04-29 11:37:33,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +49: [2023-04-29 11:37:33,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. + 3: [2023-04-29 11:37:33,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +19: [2023-04-29 11:37:33,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... + 0: [2023-04-29 11:37:33,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 0: [2023-04-29 11:37:33,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 0: [2023-04-29 11:37:33,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 2: [2023-04-29 11:37:33,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... + 0: [2023-04-29 11:37:33,677] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +20: [2023-04-29 11:37:33,677] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +20: [2023-04-29 11:37:33,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 5: [2023-04-29 11:37:33,677] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +14: [2023-04-29 11:37:33,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 5: [2023-04-29 11:37:33,678] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +55: [2023-04-29 11:37:33,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +34: [2023-04-29 11:37:33,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +42: [2023-04-29 11:37:33,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +34: [2023-04-29 11:37:33,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +20: [2023-04-29 11:37:33,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +48: [2023-04-29 11:37:33,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 5: [2023-04-29 11:37:33,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +55: [2023-04-29 11:37:33,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... + 5: [2023-04-29 11:37:33,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +14: [2023-04-29 11:37:33,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +49: [2023-04-29 11:37:33,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +13: [2023-04-29 11:37:33,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +42: [2023-04-29 11:37:33,683] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +20: [2023-04-29 11:37:33,683] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +42: [2023-04-29 11:37:33,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 7: [2023-04-29 11:37:33,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +29: [2023-04-29 11:37:33,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 2: [2023-04-29 11:37:33,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +45: [2023-04-29 11:37:33,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +55: [2023-04-29 11:37:33,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... + 6: [2023-04-29 11:37:33,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +35: [2023-04-29 11:37:33,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +40: [2023-04-29 11:37:33,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +24: [2023-04-29 11:37:33,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +24: [2023-04-29 11:37:33,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 2: [2023-04-29 11:37:33,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +34: [2023-04-29 11:37:33,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +34: [2023-04-29 11:37:33,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +31: [2023-04-29 11:37:33,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +29: [2023-04-29 11:37:33,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 3: [2023-04-29 11:37:33,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +31: [2023-04-29 11:37:33,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +29: [2023-04-29 11:37:33,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +49: [2023-04-29 11:37:33,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +45: [2023-04-29 11:37:33,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +42: [2023-04-29 11:37:33,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +31: [2023-04-29 11:37:33,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +29: [2023-04-29 11:37:33,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +40: [2023-04-29 11:37:33,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 3: [2023-04-29 11:37:33,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 3: [2023-04-29 11:37:33,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 8: [2023-04-29 11:37:33,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +17: [2023-04-29 11:37:33,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 3: [2023-04-29 11:37:33,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +35: [2023-04-29 11:37:33,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 3: [2023-04-29 11:37:33,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +45: [2023-04-29 11:37:33,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +24: [2023-04-29 11:37:33,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +24: [2023-04-29 11:37:33,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +51: [2023-04-29 11:37:33,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +51: [2023-04-29 11:37:33,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +51: [2023-04-29 11:37:33,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +51: [2023-04-29 11:37:33,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +45: [2023-04-29 11:37:33,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +49: [2023-04-29 11:37:33,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +17: [2023-04-29 11:37:33,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +14: [2023-04-29 11:37:33,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +55: [2023-04-29 11:37:33,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +35: [2023-04-29 11:37:33,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +55: [2023-04-29 11:37:33,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +55: [2023-04-29 11:37:33,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +44: [2023-04-29 11:37:33,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +44: [2023-04-29 11:37:33,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +35: [2023-04-29 11:37:33,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +40: [2023-04-29 11:37:33,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +17: [2023-04-29 11:37:33,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +29: [2023-04-29 11:37:33,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +29: [2023-04-29 11:37:33,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +44: [2023-04-29 11:37:33,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +22: [2023-04-29 11:37:33,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +22: [2023-04-29 11:37:33,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +40: [2023-04-29 11:37:33,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +44: [2023-04-29 11:37:33,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +17: [2023-04-29 11:37:33,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +16: [2023-04-29 11:37:33,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +16: [2023-04-29 11:37:33,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +12: [2023-04-29 11:37:33,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 9: [2023-04-29 11:37:33,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 9: [2023-04-29 11:37:33,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 9: [2023-04-29 11:37:33,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 9: [2023-04-29 11:37:33,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 3: [2023-04-29 11:37:33,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +16: [2023-04-29 11:37:33,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +17: [2023-04-29 11:37:33,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +29: [2023-04-29 11:37:33,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 3: [2023-04-29 11:37:33,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +44: [2023-04-29 11:37:33,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +44: [2023-04-29 11:37:33,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 8: [2023-04-29 11:37:33,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +22: [2023-04-29 11:37:33,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 4: [2023-04-29 11:37:33,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +44: [2023-04-29 11:37:33,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +22: [2023-04-29 11:37:33,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +44: [2023-04-29 11:37:33,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +58: [2023-04-29 11:37:33,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +58: [2023-04-29 11:37:33,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +58: [2023-04-29 11:37:33,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +58: [2023-04-29 11:37:33,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +12: [2023-04-29 11:37:33,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +58: [2023-04-29 11:37:33,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +58: [2023-04-29 11:37:33,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +58: [2023-04-29 11:37:33,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. + 8: [2023-04-29 11:37:33,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 8: [2023-04-29 11:37:33,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +58: [2023-04-29 11:37:33,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +17: [2023-04-29 11:37:33,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +49: [2023-04-29 11:37:33,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +16: [2023-04-29 11:37:33,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 3: [2023-04-29 11:37:33,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +16: [2023-04-29 11:37:33,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +13: [2023-04-29 11:37:33,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +16: [2023-04-29 11:37:33,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +14: [2023-04-29 11:37:33,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +29: [2023-04-29 11:37:33,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +14: [2023-04-29 11:37:33,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +15: [2023-04-29 11:37:33,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +15: [2023-04-29 11:37:33,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +15: [2023-04-29 11:37:33,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +12: [2023-04-29 11:37:33,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +12: [2023-04-29 11:37:33,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +15: [2023-04-29 11:37:33,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 4: [2023-04-29 11:37:33,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +28: [2023-04-29 11:37:33,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +28: [2023-04-29 11:37:33,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +28: [2023-04-29 11:37:33,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +25: [2023-04-29 11:37:33,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +58: [2023-04-29 11:37:33,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 4: [2023-04-29 11:37:33,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +58: [2023-04-29 11:37:33,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +58: [2023-04-29 11:37:33,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +28: [2023-04-29 11:37:33,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +58: [2023-04-29 11:37:33,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +58: [2023-04-29 11:37:33,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +58: [2023-04-29 11:37:33,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +58: [2023-04-29 11:37:33,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +58: [2023-04-29 11:37:33,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 6: [2023-04-29 11:37:33,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 6: [2023-04-29 11:37:33,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +13: [2023-04-29 11:37:33,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +47: [2023-04-29 11:37:33,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +25: [2023-04-29 11:37:33,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +15: [2023-04-29 11:37:33,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +23: [2023-04-29 11:37:33,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +21: [2023-04-29 11:37:33,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +49: [2023-04-29 11:37:33,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +15: [2023-04-29 11:37:33,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +15: [2023-04-29 11:37:33,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +15: [2023-04-29 11:37:33,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 4: [2023-04-29 11:37:33,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... + 4: [2023-04-29 11:37:33,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +16: [2023-04-29 11:37:33,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 4: [2023-04-29 11:37:33,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +23: [2023-04-29 11:37:33,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 6: [2023-04-29 11:37:33,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 6: [2023-04-29 11:37:33,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +23: [2023-04-29 11:37:33,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +51: [2023-04-29 11:37:33,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +47: [2023-04-29 11:37:33,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. + 4: [2023-04-29 11:37:33,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +62: [2023-04-29 11:37:33,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +24: [2023-04-29 11:37:33,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +24: [2023-04-29 11:37:33,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +24: [2023-04-29 11:37:33,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +21: [2023-04-29 11:37:33,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +21: [2023-04-29 11:37:33,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +25: [2023-04-29 11:37:33,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +21: [2023-04-29 11:37:33,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 4: [2023-04-29 11:37:33,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +16: [2023-04-29 11:37:33,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 3: [2023-04-29 11:37:33,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 3: [2023-04-29 11:37:33,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 3: [2023-04-29 11:37:33,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +23: [2023-04-29 11:37:33,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... + 3: [2023-04-29 11:37:33,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +38: [2023-04-29 11:37:33,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +38: [2023-04-29 11:37:33,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +38: [2023-04-29 11:37:33,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +38: [2023-04-29 11:37:33,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +38: [2023-04-29 11:37:33,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +38: [2023-04-29 11:37:33,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +38: [2023-04-29 11:37:33,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +38: [2023-04-29 11:37:33,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +51: [2023-04-29 11:37:33,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +22: [2023-04-29 11:37:33,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +49: [2023-04-29 11:37:33,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +22: [2023-04-29 11:37:33,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +52: [2023-04-29 11:37:33,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +22: [2023-04-29 11:37:33,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +48: [2023-04-29 11:37:33,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +47: [2023-04-29 11:37:33,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +25: [2023-04-29 11:37:33,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +62: [2023-04-29 11:37:33,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +62: [2023-04-29 11:37:33,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. + 0: [2023-04-29 11:37:33,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +24: [2023-04-29 11:37:33,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +47: [2023-04-29 11:37:33,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +38: [2023-04-29 11:37:33,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 9: [2023-04-29 11:37:33,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +23: [2023-04-29 11:37:33,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +48: [2023-04-29 11:37:33,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +48: [2023-04-29 11:37:33,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +22: [2023-04-29 11:37:33,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 9: [2023-04-29 11:37:33,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +38: [2023-04-29 11:37:33,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +38: [2023-04-29 11:37:33,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +38: [2023-04-29 11:37:33,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +25: [2023-04-29 11:37:33,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +51: [2023-04-29 11:37:33,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +51: [2023-04-29 11:37:33,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 9: [2023-04-29 11:37:33,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +23: [2023-04-29 11:37:33,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 9: [2023-04-29 11:37:33,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 0: [2023-04-29 11:37:33,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +38: [2023-04-29 11:37:33,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +38: [2023-04-29 11:37:33,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +38: [2023-04-29 11:37:33,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 7: [2023-04-29 11:37:33,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +38: [2023-04-29 11:37:33,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +52: [2023-04-29 11:37:33,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +52: [2023-04-29 11:37:33,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +23: [2023-04-29 11:37:33,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +52: [2023-04-29 11:37:33,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +25: [2023-04-29 11:37:33,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +54: [2023-04-29 11:37:33,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +25: [2023-04-29 11:37:33,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +54: [2023-04-29 11:37:33,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +54: [2023-04-29 11:37:33,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +32: [2023-04-29 11:37:33,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +32: [2023-04-29 11:37:33,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +32: [2023-04-29 11:37:33,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +32: [2023-04-29 11:37:33,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +32: [2023-04-29 11:37:33,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +32: [2023-04-29 11:37:33,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +32: [2023-04-29 11:37:33,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +54: [2023-04-29 11:37:33,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +32: [2023-04-29 11:37:33,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. + 7: [2023-04-29 11:37:33,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 7: [2023-04-29 11:37:33,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +23: [2023-04-29 11:37:33,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +28: [2023-04-29 11:37:33,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +15: [2023-04-29 11:37:33,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +15: [2023-04-29 11:37:33,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +15: [2023-04-29 11:37:33,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +28: [2023-04-29 11:37:33,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +28: [2023-04-29 11:37:33,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +15: [2023-04-29 11:37:33,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +47: [2023-04-29 11:37:33,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +54: [2023-04-29 11:37:33,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +28: [2023-04-29 11:37:33,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +54: [2023-04-29 11:37:33,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +25: [2023-04-29 11:37:33,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... + 7: [2023-04-29 11:37:33,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +54: [2023-04-29 11:37:33,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 0: [2023-04-29 11:37:33,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +32: [2023-04-29 11:37:33,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +32: [2023-04-29 11:37:33,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +16: [2023-04-29 11:37:33,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +16: [2023-04-29 11:37:33,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +54: [2023-04-29 11:37:33,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +48: [2023-04-29 11:37:33,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +21: [2023-04-29 11:37:33,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +59: [2023-04-29 11:37:33,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +59: [2023-04-29 11:37:33,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +59: [2023-04-29 11:37:33,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +32: [2023-04-29 11:37:33,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +59: [2023-04-29 11:37:33,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +32: [2023-04-29 11:37:33,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +52: [2023-04-29 11:37:33,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +52: [2023-04-29 11:37:33,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +32: [2023-04-29 11:37:33,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 0: [2023-04-29 11:37:33,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +32: [2023-04-29 11:37:33,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 5: [2023-04-29 11:37:33,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 5: [2023-04-29 11:37:33,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 5: [2023-04-29 11:37:33,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 5: [2023-04-29 11:37:33,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +32: [2023-04-29 11:37:33,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +62: [2023-04-29 11:37:33,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +32: [2023-04-29 11:37:33,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 7: [2023-04-29 11:37:33,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 0: [2023-04-29 11:37:33,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +52: [2023-04-29 11:37:33,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +52: [2023-04-29 11:37:33,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +47: [2023-04-29 11:37:33,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +48: [2023-04-29 11:37:33,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... + 0: [2023-04-29 11:37:33,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 0: [2023-04-29 11:37:33,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 0: [2023-04-29 11:37:33,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +52: [2023-04-29 11:37:33,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 0: [2023-04-29 11:37:33,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +40: [2023-04-29 11:37:33,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. + 0: [2023-04-29 11:37:33,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... + 7: [2023-04-29 11:37:33,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 7: [2023-04-29 11:37:33,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +48: [2023-04-29 11:37:33,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +62: [2023-04-29 11:37:33,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +62: [2023-04-29 11:37:33,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +62: [2023-04-29 11:37:33,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +21: [2023-04-29 11:37:33,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +40: [2023-04-29 11:37:33,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +48: [2023-04-29 11:37:33,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 0: [2023-04-29 11:37:33,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... + 7: [2023-04-29 11:37:33,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +47: [2023-04-29 11:37:33,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +21: [2023-04-29 11:37:33,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +48: [2023-04-29 11:37:33,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +48: [2023-04-29 11:37:33,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +48: [2023-04-29 11:37:33,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +48: [2023-04-29 11:37:33,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +16: [2023-04-29 11:37:33,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. +21: [2023-04-29 11:37:33,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +16: [2023-04-29 11:37:33,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_15-model_01-model_states.pt. + 8: [2023-04-29 11:37:33,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +50: [2023-04-29 11:37:33,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +12: [2023-04-29 11:37:33,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +50: [2023-04-29 11:37:33,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +50: [2023-04-29 11:37:33,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 0: [2023-04-29 11:37:33,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +50: [2023-04-29 11:37:33,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +47: [2023-04-29 11:37:33,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +50: [2023-04-29 11:37:33,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +12: [2023-04-29 11:37:33,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... + 8: [2023-04-29 11:37:33,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +44: [2023-04-29 11:37:33,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +40: [2023-04-29 11:37:33,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +40: [2023-04-29 11:37:33,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +52: [2023-04-29 11:37:33,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +44: [2023-04-29 11:37:33,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +52: [2023-04-29 11:37:33,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +48: [2023-04-29 11:37:33,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +50: [2023-04-29 11:37:33,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +48: [2023-04-29 11:37:33,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +16: [2023-04-29 11:37:33,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +16: [2023-04-29 11:37:33,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +36: [2023-04-29 11:37:33,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +36: [2023-04-29 11:37:33,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +36: [2023-04-29 11:37:33,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +36: [2023-04-29 11:37:33,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +48: [2023-04-29 11:37:33,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +12: [2023-04-29 11:37:33,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +50: [2023-04-29 11:37:33,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +52: [2023-04-29 11:37:33,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +31: [2023-04-29 11:37:33,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +31: [2023-04-29 11:37:33,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +31: [2023-04-29 11:37:33,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +31: [2023-04-29 11:37:33,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +40: [2023-04-29 11:37:33,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +40: [2023-04-29 11:37:33,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +50: [2023-04-29 11:37:33,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +44: [2023-04-29 11:37:33,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +44: [2023-04-29 11:37:33,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 5: [2023-04-29 11:37:33,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +59: [2023-04-29 11:37:33,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +15: [2023-04-29 11:37:33,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +63: [2023-04-29 11:37:33,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +63: [2023-04-29 11:37:33,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +63: [2023-04-29 11:37:33,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +48: [2023-04-29 11:37:33,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +12: [2023-04-29 11:37:33,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +63: [2023-04-29 11:37:33,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +15: [2023-04-29 11:37:33,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +15: [2023-04-29 11:37:33,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +12: [2023-04-29 11:37:33,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 8: [2023-04-29 11:37:33,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +59: [2023-04-29 11:37:33,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +59: [2023-04-29 11:37:33,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +59: [2023-04-29 11:37:33,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 5: [2023-04-29 11:37:33,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 8: [2023-04-29 11:37:33,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +58: [2023-04-29 11:37:33,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +62: [2023-04-29 11:37:33,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +58: [2023-04-29 11:37:33,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. + 5: [2023-04-29 11:37:33,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +15: [2023-04-29 11:37:33,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +12: [2023-04-29 11:37:33,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 8: [2023-04-29 11:37:33,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +53: [2023-04-29 11:37:33,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +53: [2023-04-29 11:37:33,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +53: [2023-04-29 11:37:33,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +53: [2023-04-29 11:37:33,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +52: [2023-04-29 11:37:33,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 5: [2023-04-29 11:37:33,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... + 0: [2023-04-29 11:37:33,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +33: [2023-04-29 11:37:33,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +40: [2023-04-29 11:37:33,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +33: [2023-04-29 11:37:33,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +33: [2023-04-29 11:37:33,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +33: [2023-04-29 11:37:33,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +33: [2023-04-29 11:37:33,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +33: [2023-04-29 11:37:33,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +33: [2023-04-29 11:37:33,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +33: [2023-04-29 11:37:33,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +17: [2023-04-29 11:37:33,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +17: [2023-04-29 11:37:33,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +17: [2023-04-29 11:37:33,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +52: [2023-04-29 11:37:33,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 0: [2023-04-29 11:37:33,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +12: [2023-04-29 11:37:33,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +17: [2023-04-29 11:37:33,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +52: [2023-04-29 11:37:33,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 0: [2023-04-29 11:37:33,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +26: [2023-04-29 11:37:33,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +26: [2023-04-29 11:37:33,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +58: [2023-04-29 11:37:33,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +58: [2023-04-29 11:37:33,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +26: [2023-04-29 11:37:33,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. + 8: [2023-04-29 11:37:33,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +26: [2023-04-29 11:37:33,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +53: [2023-04-29 11:37:33,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +12: [2023-04-29 11:37:33,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +24: [2023-04-29 11:37:33,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +46: [2023-04-29 11:37:33,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +46: [2023-04-29 11:37:33,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +46: [2023-04-29 11:37:33,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +46: [2023-04-29 11:37:33,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +46: [2023-04-29 11:37:33,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +46: [2023-04-29 11:37:33,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +46: [2023-04-29 11:37:33,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +45: [2023-04-29 11:37:33,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +45: [2023-04-29 11:37:33,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +45: [2023-04-29 11:37:33,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +45: [2023-04-29 11:37:33,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +45: [2023-04-29 11:37:33,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +45: [2023-04-29 11:37:33,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +45: [2023-04-29 11:37:33,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +45: [2023-04-29 11:37:33,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +46: [2023-04-29 11:37:33,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +54: [2023-04-29 11:37:33,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +54: [2023-04-29 11:37:33,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +54: [2023-04-29 11:37:33,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +54: [2023-04-29 11:37:33,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +53: [2023-04-29 11:37:33,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +22: [2023-04-29 11:37:33,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +53: [2023-04-29 11:37:33,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +53: [2023-04-29 11:37:33,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +33: [2023-04-29 11:37:33,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +40: [2023-04-29 11:37:33,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... + 8: [2023-04-29 11:37:33,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +33: [2023-04-29 11:37:33,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 8: [2023-04-29 11:37:33,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +17: [2023-04-29 11:37:33,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +17: [2023-04-29 11:37:33,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +52: [2023-04-29 11:37:33,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +33: [2023-04-29 11:37:33,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +33: [2023-04-29 11:37:33,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +17: [2023-04-29 11:37:33,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +17: [2023-04-29 11:37:33,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 3: [2023-04-29 11:37:33,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 3: [2023-04-29 11:37:33,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +33: [2023-04-29 11:37:33,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +46: [2023-04-29 11:37:33,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +33: [2023-04-29 11:37:33,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +60: [2023-04-29 11:37:33,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +60: [2023-04-29 11:37:33,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +60: [2023-04-29 11:37:33,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +24: [2023-04-29 11:37:33,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +33: [2023-04-29 11:37:33,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +33: [2023-04-29 11:37:33,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +46: [2023-04-29 11:37:33,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +60: [2023-04-29 11:37:33,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +46: [2023-04-29 11:37:33,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +46: [2023-04-29 11:37:33,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +45: [2023-04-29 11:37:33,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +45: [2023-04-29 11:37:33,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +45: [2023-04-29 11:37:33,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +38: [2023-04-29 11:37:33,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +45: [2023-04-29 11:37:33,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +46: [2023-04-29 11:37:33,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +45: [2023-04-29 11:37:33,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +46: [2023-04-29 11:37:33,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +15: [2023-04-29 11:37:33,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +22: [2023-04-29 11:37:33,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +45: [2023-04-29 11:37:33,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +24: [2023-04-29 11:37:33,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +46: [2023-04-29 11:37:33,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +36: [2023-04-29 11:37:33,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +46: [2023-04-29 11:37:33,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 3: [2023-04-29 11:37:33,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 3: [2023-04-29 11:37:33,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +22: [2023-04-29 11:37:33,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +22: [2023-04-29 11:37:33,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +45: [2023-04-29 11:37:33,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +45: [2023-04-29 11:37:33,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 0: [2023-04-29 11:37:33,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +16: [2023-04-29 11:37:33,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +36: [2023-04-29 11:37:33,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 3: [2023-04-29 11:37:33,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... + 3: [2023-04-29 11:37:33,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +44: [2023-04-29 11:37:33,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +36: [2023-04-29 11:37:33,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +28: [2023-04-29 11:37:33,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 9: [2023-04-29 11:37:33,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +16: [2023-04-29 11:37:33,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt... +24: [2023-04-29 11:37:33,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 9: [2023-04-29 11:37:33,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 3: [2023-04-29 11:37:33,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +44: [2023-04-29 11:37:33,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +22: [2023-04-29 11:37:33,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +24: [2023-04-29 11:37:33,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... + 3: [2023-04-29 11:37:33,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +44: [2023-04-29 11:37:33,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +61: [2023-04-29 11:37:33,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +61: [2023-04-29 11:37:33,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +36: [2023-04-29 11:37:33,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +24: [2023-04-29 11:37:33,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +37: [2023-04-29 11:37:33,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +37: [2023-04-29 11:37:33,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +22: [2023-04-29 11:37:33,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +37: [2023-04-29 11:37:33,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +37: [2023-04-29 11:37:33,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +22: [2023-04-29 11:37:33,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +31: [2023-04-29 11:37:33,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +15: [2023-04-29 11:37:33,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +44: [2023-04-29 11:37:33,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +32: [2023-04-29 11:37:33,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +61: [2023-04-29 11:37:33,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +63: [2023-04-29 11:37:33,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 9: [2023-04-29 11:37:33,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +28: [2023-04-29 11:37:33,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +31: [2023-04-29 11:37:33,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +48: [2023-04-29 11:37:33,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +15: [2023-04-29 11:37:33,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +61: [2023-04-29 11:37:33,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. + 9: [2023-04-29 11:37:33,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... + 9: [2023-04-29 11:37:33,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +24: [2023-04-29 11:37:33,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +38: [2023-04-29 11:37:33,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +63: [2023-04-29 11:37:33,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +38: [2023-04-29 11:37:33,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +22: [2023-04-29 11:37:33,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +31: [2023-04-29 11:37:33,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +31: [2023-04-29 11:37:33,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +24: [2023-04-29 11:37:33,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... + 9: [2023-04-29 11:37:33,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +37: [2023-04-29 11:37:33,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +58: [2023-04-29 11:37:33,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +37: [2023-04-29 11:37:33,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +37: [2023-04-29 11:37:33,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +63: [2023-04-29 11:37:33,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +63: [2023-04-29 11:37:33,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 9: [2023-04-29 11:37:33,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +58: [2023-04-29 11:37:33,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +37: [2023-04-29 11:37:33,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +16: [2023-04-29 11:37:33,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +15: [2023-04-29 11:37:33,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +38: [2023-04-29 11:37:33,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +26: [2023-04-29 11:37:33,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +26: [2023-04-29 11:37:33,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +26: [2023-04-29 11:37:33,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 9: [2023-04-29 11:37:33,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +26: [2023-04-29 11:37:33,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +43: [2023-04-29 11:37:33,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +43: [2023-04-29 11:37:33,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +43: [2023-04-29 11:37:33,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +28: [2023-04-29 11:37:33,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +43: [2023-04-29 11:37:33,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +38: [2023-04-29 11:37:33,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +32: [2023-04-29 11:37:33,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +32: [2023-04-29 11:37:33,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +58: [2023-04-29 11:37:33,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +58: [2023-04-29 11:37:33,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +54: [2023-04-29 11:37:33,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +54: [2023-04-29 11:37:33,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +54: [2023-04-29 11:37:33,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +28: [2023-04-29 11:37:33,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +44: [2023-04-29 11:37:33,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +44: [2023-04-29 11:37:33,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +44: [2023-04-29 11:37:33,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +44: [2023-04-29 11:37:33,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +44: [2023-04-29 11:37:33,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +44: [2023-04-29 11:37:33,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +44: [2023-04-29 11:37:33,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +44: [2023-04-29 11:37:33,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +16: [2023-04-29 11:37:33,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +16: [2023-04-29 11:37:33,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +16: [2023-04-29 11:37:33,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +44: [2023-04-29 11:37:33,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +44: [2023-04-29 11:37:33,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +28: [2023-04-29 11:37:33,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +44: [2023-04-29 11:37:33,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +44: [2023-04-29 11:37:33,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +60: [2023-04-29 11:37:33,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +22: [2023-04-29 11:37:33,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +28: [2023-04-29 11:37:33,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +22: [2023-04-29 11:37:33,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +22: [2023-04-29 11:37:33,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +54: [2023-04-29 11:37:33,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +22: [2023-04-29 11:37:33,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +54: [2023-04-29 11:37:33,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +57: [2023-04-29 11:37:33,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +57: [2023-04-29 11:37:33,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +57: [2023-04-29 11:37:33,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +60: [2023-04-29 11:37:33,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +54: [2023-04-29 11:37:33,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +57: [2023-04-29 11:37:33,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +28: [2023-04-29 11:37:33,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +60: [2023-04-29 11:37:33,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +28: [2023-04-29 11:37:33,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +56: [2023-04-29 11:37:33,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +56: [2023-04-29 11:37:33,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +56: [2023-04-29 11:37:33,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +56: [2023-04-29 11:37:33,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +22: [2023-04-29 11:37:33,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +60: [2023-04-29 11:37:33,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +22: [2023-04-29 11:37:33,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +32: [2023-04-29 11:37:33,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +22: [2023-04-29 11:37:33,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +22: [2023-04-29 11:37:33,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +15: [2023-04-29 11:37:33,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +61: [2023-04-29 11:37:33,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +61: [2023-04-29 11:37:33,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +50: [2023-04-29 11:37:33,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +14: [2023-04-29 11:37:33,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +14: [2023-04-29 11:37:33,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +14: [2023-04-29 11:37:33,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +14: [2023-04-29 11:37:33,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +54: [2023-04-29 11:37:33,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +54: [2023-04-29 11:37:33,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +61: [2023-04-29 11:37:33,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +63: [2023-04-29 11:37:33,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +63: [2023-04-29 11:37:33,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +63: [2023-04-29 11:37:33,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +63: [2023-04-29 11:37:33,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +50: [2023-04-29 11:37:33,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +32: [2023-04-29 11:37:33,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +61: [2023-04-29 11:37:33,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +38: [2023-04-29 11:37:33,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +38: [2023-04-29 11:37:33,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +63: [2023-04-29 11:37:33,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 5: [2023-04-29 11:37:33,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +16: [2023-04-29 11:37:33,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +16: [2023-04-29 11:37:33,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +63: [2023-04-29 11:37:33,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +38: [2023-04-29 11:37:33,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +63: [2023-04-29 11:37:33,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +63: [2023-04-29 11:37:33,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +15: [2023-04-29 11:37:33,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +15: [2023-04-29 11:37:33,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +34: [2023-04-29 11:37:33,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +34: [2023-04-29 11:37:33,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +34: [2023-04-29 11:37:33,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +34: [2023-04-29 11:37:33,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +34: [2023-04-29 11:37:33,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +34: [2023-04-29 11:37:33,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +34: [2023-04-29 11:37:33,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +34: [2023-04-29 11:37:33,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +35: [2023-04-29 11:37:33,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +35: [2023-04-29 11:37:33,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +35: [2023-04-29 11:37:33,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +24: [2023-04-29 11:37:33,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +24: [2023-04-29 11:37:33,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +35: [2023-04-29 11:37:33,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +35: [2023-04-29 11:37:33,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +35: [2023-04-29 11:37:33,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +35: [2023-04-29 11:37:33,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +35: [2023-04-29 11:37:33,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +54: [2023-04-29 11:37:33,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +32: [2023-04-29 11:37:33,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +16: [2023-04-29 11:37:33,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +32: [2023-04-29 11:37:33,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +15: [2023-04-29 11:37:33,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +16: [2023-04-29 11:37:33,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +33: [2023-04-29 11:37:33,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +24: [2023-04-29 11:37:33,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +24: [2023-04-29 11:37:33,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +34: [2023-04-29 11:37:33,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +24: [2023-04-29 11:37:33,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +35: [2023-04-29 11:37:33,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +34: [2023-04-29 11:37:33,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +16: [2023-04-29 11:37:33,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +43: [2023-04-29 11:37:33,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +24: [2023-04-29 11:37:33,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +43: [2023-04-29 11:37:33,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +34: [2023-04-29 11:37:33,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +34: [2023-04-29 11:37:33,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +35: [2023-04-29 11:37:33,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +35: [2023-04-29 11:37:33,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... + 5: [2023-04-29 11:37:33,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +53: [2023-04-29 11:37:33,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +54: [2023-04-29 11:37:33,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +52: [2023-04-29 11:37:33,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +34: [2023-04-29 11:37:33,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +54: [2023-04-29 11:37:33,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +54: [2023-04-29 11:37:33,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +54: [2023-04-29 11:37:33,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +54: [2023-04-29 11:37:33,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +24: [2023-04-29 11:37:33,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +54: [2023-04-29 11:37:33,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +43: [2023-04-29 11:37:33,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +43: [2023-04-29 11:37:33,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +54: [2023-04-29 11:37:33,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +24: [2023-04-29 11:37:33,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +35: [2023-04-29 11:37:33,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +35: [2023-04-29 11:37:33,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +34: [2023-04-29 11:37:33,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +57: [2023-04-29 11:37:33,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +50: [2023-04-29 11:37:33,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +17: [2023-04-29 11:37:33,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +34: [2023-04-29 11:37:33,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +40: [2023-04-29 11:37:33,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +40: [2023-04-29 11:37:33,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +40: [2023-04-29 11:37:33,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +34: [2023-04-29 11:37:33,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +46: [2023-04-29 11:37:33,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +40: [2023-04-29 11:37:33,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +57: [2023-04-29 11:37:33,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 5: [2023-04-29 11:37:33,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 5: [2023-04-29 11:37:33,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. + 5: [2023-04-29 11:37:33,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +50: [2023-04-29 11:37:33,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +56: [2023-04-29 11:37:33,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +57: [2023-04-29 11:37:33,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +17: [2023-04-29 11:37:33,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +57: [2023-04-29 11:37:33,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +35: [2023-04-29 11:37:33,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +35: [2023-04-29 11:37:33,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +56: [2023-04-29 11:37:33,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +56: [2023-04-29 11:37:33,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +35: [2023-04-29 11:37:33,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +56: [2023-04-29 11:37:33,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +16: [2023-04-29 11:37:33,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +50: [2023-04-29 11:37:33,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +52: [2023-04-29 11:37:33,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +40: [2023-04-29 11:37:33,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +52: [2023-04-29 11:37:33,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +45: [2023-04-29 11:37:33,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +29: [2023-04-29 11:37:33,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +29: [2023-04-29 11:37:33,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +29: [2023-04-29 11:37:33,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +14: [2023-04-29 11:37:33,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +46: [2023-04-29 11:37:33,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +29: [2023-04-29 11:37:33,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +16: [2023-04-29 11:37:33,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +40: [2023-04-29 11:37:33,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +40: [2023-04-29 11:37:33,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +40: [2023-04-29 11:37:33,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +32: [2023-04-29 11:37:33,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +16: [2023-04-29 11:37:33,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 5: [2023-04-29 11:37:33,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +53: [2023-04-29 11:37:33,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +53: [2023-04-29 11:37:33,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +53: [2023-04-29 11:37:33,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 5: [2023-04-29 11:37:33,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +33: [2023-04-29 11:37:33,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +33: [2023-04-29 11:37:33,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. + 5: [2023-04-29 11:37:33,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +15: [2023-04-29 11:37:33,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +33: [2023-04-29 11:37:33,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +45: [2023-04-29 11:37:33,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +50: [2023-04-29 11:37:33,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +50: [2023-04-29 11:37:33,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +51: [2023-04-29 11:37:33,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +51: [2023-04-29 11:37:33,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +51: [2023-04-29 11:37:33,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +51: [2023-04-29 11:37:33,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +51: [2023-04-29 11:37:33,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +51: [2023-04-29 11:37:33,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +51: [2023-04-29 11:37:33,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +51: [2023-04-29 11:37:33,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +50: [2023-04-29 11:37:33,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +45: [2023-04-29 11:37:33,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +45: [2023-04-29 11:37:33,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +14: [2023-04-29 11:37:33,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +15: [2023-04-29 11:37:33,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +15: [2023-04-29 11:37:33,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +29: [2023-04-29 11:37:33,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +29: [2023-04-29 11:37:33,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +29: [2023-04-29 11:37:33,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +52: [2023-04-29 11:37:33,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +29: [2023-04-29 11:37:33,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +54: [2023-04-29 11:37:33,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +17: [2023-04-29 11:37:33,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +54: [2023-04-29 11:37:33,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +54: [2023-04-29 11:37:33,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +50: [2023-04-29 11:37:33,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +14: [2023-04-29 11:37:33,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +54: [2023-04-29 11:37:33,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +54: [2023-04-29 11:37:33,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +50: [2023-04-29 11:37:33,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +52: [2023-04-29 11:37:33,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +50: [2023-04-29 11:37:33,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +14: [2023-04-29 11:37:33,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +54: [2023-04-29 11:37:33,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +54: [2023-04-29 11:37:33,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +50: [2023-04-29 11:37:33,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +44: [2023-04-29 11:37:33,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_51_mp_rank_02_optim_states.pt... +44: [2023-04-29 11:37:33,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_50_mp_rank_02_optim_states.pt... +44: [2023-04-29 11:37:33,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_48_mp_rank_02_optim_states.pt... +44: [2023-04-29 11:37:33,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_49_mp_rank_02_optim_states.pt... +54: [2023-04-29 11:37:33,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +15: [2023-04-29 11:37:33,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +51: [2023-04-29 11:37:33,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +51: [2023-04-29 11:37:33,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +15: [2023-04-29 11:37:33,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +52: [2023-04-29 11:37:33,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +46: [2023-04-29 11:37:33,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +37: [2023-04-29 11:37:33,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +59: [2023-04-29 11:37:33,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +59: [2023-04-29 11:37:33,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +53: [2023-04-29 11:37:33,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +15: [2023-04-29 11:37:33,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +15: [2023-04-29 11:37:33,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +17: [2023-04-29 11:37:33,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +41: [2023-04-29 11:37:33,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +41: [2023-04-29 11:37:33,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +41: [2023-04-29 11:37:33,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +41: [2023-04-29 11:37:33,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +41: [2023-04-29 11:37:33,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +41: [2023-04-29 11:37:33,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +41: [2023-04-29 11:37:33,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +41: [2023-04-29 11:37:33,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +51: [2023-04-29 11:37:33,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +59: [2023-04-29 11:37:33,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +59: [2023-04-29 11:37:33,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +51: [2023-04-29 11:37:33,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +15: [2023-04-29 11:37:33,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +59: [2023-04-29 11:37:33,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +59: [2023-04-29 11:37:33,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +59: [2023-04-29 11:37:33,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +51: [2023-04-29 11:37:33,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +51: [2023-04-29 11:37:33,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +59: [2023-04-29 11:37:33,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +52: [2023-04-29 11:37:33,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +46: [2023-04-29 11:37:33,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +31: [2023-04-29 11:37:33,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +51: [2023-04-29 11:37:33,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +51: [2023-04-29 11:37:33,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +31: [2023-04-29 11:37:33,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +59: [2023-04-29 11:37:33,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +59: [2023-04-29 11:37:33,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +63: [2023-04-29 11:37:33,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +26: [2023-04-29 11:37:33,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +26: [2023-04-29 11:37:33,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +33: [2023-04-29 11:37:33,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +53: [2023-04-29 11:37:33,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +52: [2023-04-29 11:37:33,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +53: [2023-04-29 11:37:33,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +59: [2023-04-29 11:37:33,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +53: [2023-04-29 11:37:33,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +41: [2023-04-29 11:37:33,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +59: [2023-04-29 11:37:33,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +31: [2023-04-29 11:37:33,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +31: [2023-04-29 11:37:33,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +41: [2023-04-29 11:37:33,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +41: [2023-04-29 11:37:33,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +59: [2023-04-29 11:37:33,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +59: [2023-04-29 11:37:33,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +59: [2023-04-29 11:37:33,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +41: [2023-04-29 11:37:33,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +63: [2023-04-29 11:37:33,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +46: [2023-04-29 11:37:33,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +50: [2023-04-29 11:37:33,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +26: [2023-04-29 11:37:33,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +26: [2023-04-29 11:37:33,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +41: [2023-04-29 11:37:33,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +50: [2023-04-29 11:37:33,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +36: [2023-04-29 11:37:33,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +31: [2023-04-29 11:37:33,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +50: [2023-04-29 11:37:33,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +36: [2023-04-29 11:37:33,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +31: [2023-04-29 11:37:33,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +36: [2023-04-29 11:37:33,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +36: [2023-04-29 11:37:33,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +36: [2023-04-29 11:37:33,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +59: [2023-04-29 11:37:33,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +36: [2023-04-29 11:37:33,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +36: [2023-04-29 11:37:33,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +50: [2023-04-29 11:37:33,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +36: [2023-04-29 11:37:33,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +41: [2023-04-29 11:37:33,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +39: [2023-04-29 11:37:33,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +39: [2023-04-29 11:37:33,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +39: [2023-04-29 11:37:33,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +26: [2023-04-29 11:37:33,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +56: [2023-04-29 11:37:33,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +56: [2023-04-29 11:37:33,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +39: [2023-04-29 11:37:33,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +26: [2023-04-29 11:37:33,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +56: [2023-04-29 11:37:33,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +45: [2023-04-29 11:37:33,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +63: [2023-04-29 11:37:33,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +17: [2023-04-29 11:37:33,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +41: [2023-04-29 11:37:33,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +46: [2023-04-29 11:37:33,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +56: [2023-04-29 11:37:33,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +41: [2023-04-29 11:37:33,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +31: [2023-04-29 11:37:33,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +31: [2023-04-29 11:37:33,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +50: [2023-04-29 11:37:33,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +36: [2023-04-29 11:37:33,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +50: [2023-04-29 11:37:33,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +50: [2023-04-29 11:37:33,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +63: [2023-04-29 11:37:33,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +50: [2023-04-29 11:37:33,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +60: [2023-04-29 11:37:33,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +60: [2023-04-29 11:37:33,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +26: [2023-04-29 11:37:33,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +26: [2023-04-29 11:37:33,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +17: [2023-04-29 11:37:33,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +57: [2023-04-29 11:37:33,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +57: [2023-04-29 11:37:33,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +53: [2023-04-29 11:37:33,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +39: [2023-04-29 11:37:33,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +61: [2023-04-29 11:37:33,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +61: [2023-04-29 11:37:33,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +53: [2023-04-29 11:37:33,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +36: [2023-04-29 11:37:33,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +53: [2023-04-29 11:37:33,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +61: [2023-04-29 11:37:33,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +61: [2023-04-29 11:37:33,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +36: [2023-04-29 11:37:33,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +22: [2023-04-29 11:37:33,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +53: [2023-04-29 11:37:33,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +36: [2023-04-29 11:37:33,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +60: [2023-04-29 11:37:33,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +60: [2023-04-29 11:37:33,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +60: [2023-04-29 11:37:33,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +56: [2023-04-29 11:37:33,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +56: [2023-04-29 11:37:33,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +56: [2023-04-29 11:37:33,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +39: [2023-04-29 11:37:33,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +63: [2023-04-29 11:37:33,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +57: [2023-04-29 11:37:33,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +57: [2023-04-29 11:37:33,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +39: [2023-04-29 11:37:33,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +39: [2023-04-29 11:37:33,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +56: [2023-04-29 11:37:33,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +33: [2023-04-29 11:37:33,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +45: [2023-04-29 11:37:33,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +42: [2023-04-29 11:37:33,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +42: [2023-04-29 11:37:33,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +55: [2023-04-29 11:37:33,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +55: [2023-04-29 11:37:33,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +36: [2023-04-29 11:37:33,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +33: [2023-04-29 11:37:33,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +33: [2023-04-29 11:37:33,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +36: [2023-04-29 11:37:33,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +60: [2023-04-29 11:37:33,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +57: [2023-04-29 11:37:33,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +54: [2023-04-29 11:37:33,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +57: [2023-04-29 11:37:33,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +36: [2023-04-29 11:37:33,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +60: [2023-04-29 11:37:33,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +36: [2023-04-29 11:37:33,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +61: [2023-04-29 11:37:33,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +60: [2023-04-29 11:37:33,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. + 8: [2023-04-29 11:37:33,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 8: [2023-04-29 11:37:33,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +63: [2023-04-29 11:37:33,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. + 8: [2023-04-29 11:37:33,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +16: [2023-04-29 11:37:33,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +55: [2023-04-29 11:37:33,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 8: [2023-04-29 11:37:33,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +61: [2023-04-29 11:37:33,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +55: [2023-04-29 11:37:33,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +53: [2023-04-29 11:37:33,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +37: [2023-04-29 11:37:33,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +53: [2023-04-29 11:37:33,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +53: [2023-04-29 11:37:33,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +61: [2023-04-29 11:37:33,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +60: [2023-04-29 11:37:33,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +37: [2023-04-29 11:37:33,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +53: [2023-04-29 11:37:33,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +60: [2023-04-29 11:37:33,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +37: [2023-04-29 11:37:33,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +37: [2023-04-29 11:37:33,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +42: [2023-04-29 11:37:33,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +42: [2023-04-29 11:37:33,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +42: [2023-04-29 11:37:33,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +42: [2023-04-29 11:37:33,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +42: [2023-04-29 11:37:33,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +60: [2023-04-29 11:37:33,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +42: [2023-04-29 11:37:33,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +54: [2023-04-29 11:37:33,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_88_mp_rank_02_optim_states.pt... +61: [2023-04-29 11:37:33,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +54: [2023-04-29 11:37:33,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_91_mp_rank_02_optim_states.pt... +54: [2023-04-29 11:37:33,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_90_mp_rank_02_optim_states.pt... +54: [2023-04-29 11:37:33,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_89_mp_rank_02_optim_states.pt... + 1: [2023-04-29 11:37:33,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +45: [2023-04-29 11:37:33,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 1: [2023-04-29 11:37:33,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +57: [2023-04-29 11:37:33,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +45: [2023-04-29 11:37:33,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +53: [2023-04-29 11:37:33,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +57: [2023-04-29 11:37:33,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +37: [2023-04-29 11:37:33,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +37: [2023-04-29 11:37:33,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +53: [2023-04-29 11:37:33,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +53: [2023-04-29 11:37:33,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +54: [2023-04-29 11:37:33,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +37: [2023-04-29 11:37:33,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +53: [2023-04-29 11:37:33,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +63: [2023-04-29 11:37:33,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +55: [2023-04-29 11:37:33,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +16: [2023-04-29 11:37:33,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_00-model_states.pt. +54: [2023-04-29 11:37:33,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +42: [2023-04-29 11:37:33,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +42: [2023-04-29 11:37:33,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +55: [2023-04-29 11:37:33,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +60: [2023-04-29 11:37:33,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +55: [2023-04-29 11:37:33,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +24: [2023-04-29 11:37:33,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 8: [2023-04-29 11:37:33,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 8: [2023-04-29 11:37:33,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +17: [2023-04-29 11:37:33,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 8: [2023-04-29 11:37:33,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +55: [2023-04-29 11:37:33,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +22: [2023-04-29 11:37:33,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +60: [2023-04-29 11:37:33,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +34: [2023-04-29 11:37:33,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. + 8: [2023-04-29 11:37:33,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +60: [2023-04-29 11:37:33,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +22: [2023-04-29 11:37:33,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +22: [2023-04-29 11:37:33,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +63: [2023-04-29 11:37:33,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +63: [2023-04-29 11:37:33,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +42: [2023-04-29 11:37:33,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +16: [2023-04-29 11:37:33,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +42: [2023-04-29 11:37:33,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +61: [2023-04-29 11:37:33,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +61: [2023-04-29 11:37:33,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +54: [2023-04-29 11:37:33,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +17: [2023-04-29 11:37:33,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +43: [2023-04-29 11:37:33,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +43: [2023-04-29 11:37:33,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +43: [2023-04-29 11:37:33,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +43: [2023-04-29 11:37:33,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +60: [2023-04-29 11:37:33,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +61: [2023-04-29 11:37:33,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +42: [2023-04-29 11:37:33,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +42: [2023-04-29 11:37:33,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +46: [2023-04-29 11:37:33,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +42: [2023-04-29 11:37:33,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +46: [2023-04-29 11:37:33,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +34: [2023-04-29 11:37:33,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +42: [2023-04-29 11:37:33,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +16: [2023-04-29 11:37:33,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt... +60: [2023-04-29 11:37:33,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +63: [2023-04-29 11:37:33,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +61: [2023-04-29 11:37:33,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +61: [2023-04-29 11:37:33,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +61: [2023-04-29 11:37:33,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +43: [2023-04-29 11:37:33,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +24: [2023-04-29 11:37:33,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +24: [2023-04-29 11:37:33,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +39: [2023-04-29 11:37:33,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +39: [2023-04-29 11:37:33,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +43: [2023-04-29 11:37:33,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +43: [2023-04-29 11:37:33,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +43: [2023-04-29 11:37:33,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +50: [2023-04-29 11:37:33,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_72_mp_rank_02_optim_states.pt... +50: [2023-04-29 11:37:33,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_74_mp_rank_02_optim_states.pt... +50: [2023-04-29 11:37:33,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_75_mp_rank_02_optim_states.pt... +50: [2023-04-29 11:37:33,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_73_mp_rank_02_optim_states.pt... +61: [2023-04-29 11:37:33,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +24: [2023-04-29 11:37:33,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +54: [2023-04-29 11:37:33,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +35: [2023-04-29 11:37:33,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +61: [2023-04-29 11:37:33,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +39: [2023-04-29 11:37:33,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +39: [2023-04-29 11:37:33,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_42-model_01-model_states.pt. +63: [2023-04-29 11:37:33,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +34: [2023-04-29 11:37:33,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +63: [2023-04-29 11:37:33,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +22: [2023-04-29 11:37:33,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +54: [2023-04-29 11:37:33,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +40: [2023-04-29 11:37:33,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +43: [2023-04-29 11:37:33,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +43: [2023-04-29 11:37:33,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +54: [2023-04-29 11:37:33,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +14: [2023-04-29 11:37:33,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +56: [2023-04-29 11:37:33,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +56: [2023-04-29 11:37:33,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +57: [2023-04-29 11:37:33,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +63: [2023-04-29 11:37:33,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +53: [2023-04-29 11:37:33,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_86_mp_rank_02_optim_states.pt... +53: [2023-04-29 11:37:33,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_84_mp_rank_02_optim_states.pt... +53: [2023-04-29 11:37:33,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_85_mp_rank_02_optim_states.pt... +53: [2023-04-29 11:37:33,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_87_mp_rank_02_optim_states.pt... +49: [2023-04-29 11:37:33,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +49: [2023-04-29 11:37:33,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +49: [2023-04-29 11:37:33,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +24: [2023-04-29 11:37:33,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +27: [2023-04-29 11:37:33,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +27: [2023-04-29 11:37:33,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +27: [2023-04-29 11:37:33,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +54: [2023-04-29 11:37:33,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +27: [2023-04-29 11:37:33,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +35: [2023-04-29 11:37:33,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +35: [2023-04-29 11:37:33,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +34: [2023-04-29 11:37:33,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +49: [2023-04-29 11:37:33,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +37: [2023-04-29 11:37:33,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +37: [2023-04-29 11:37:33,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +56: [2023-04-29 11:37:33,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +14: [2023-04-29 11:37:33,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +37: [2023-04-29 11:37:33,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +37: [2023-04-29 11:37:33,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +56: [2023-04-29 11:37:33,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +56: [2023-04-29 11:37:33,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +37: [2023-04-29 11:37:33,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +37: [2023-04-29 11:37:33,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +35: [2023-04-29 11:37:33,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +43: [2023-04-29 11:37:33,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +43: [2023-04-29 11:37:33,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +37: [2023-04-29 11:37:33,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +37: [2023-04-29 11:37:33,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +34: [2023-04-29 11:37:33,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +37: [2023-04-29 11:37:33,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +37: [2023-04-29 11:37:33,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +37: [2023-04-29 11:37:33,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +41: [2023-04-29 11:37:33,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +57: [2023-04-29 11:37:33,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +37: [2023-04-29 11:37:33,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +49: [2023-04-29 11:37:33,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +57: [2023-04-29 11:37:33,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +49: [2023-04-29 11:37:33,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +56: [2023-04-29 11:37:33,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +22: [2023-04-29 11:37:33,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +29: [2023-04-29 11:37:33,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +29: [2023-04-29 11:37:33,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +43: [2023-04-29 11:37:33,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +43: [2023-04-29 11:37:33,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +22: [2023-04-29 11:37:33,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +22: [2023-04-29 11:37:33,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +49: [2023-04-29 11:37:33,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +49: [2023-04-29 11:37:33,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +56: [2023-04-29 11:37:33,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +57: [2023-04-29 11:37:33,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +57: [2023-04-29 11:37:33,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +40: [2023-04-29 11:37:33,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +40: [2023-04-29 11:37:33,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +40: [2023-04-29 11:37:33,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +14: [2023-04-29 11:37:33,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +25: [2023-04-29 11:37:33,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +25: [2023-04-29 11:37:33,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +25: [2023-04-29 11:37:33,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +25: [2023-04-29 11:37:33,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +29: [2023-04-29 11:37:33,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +56: [2023-04-29 11:37:33,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +24: [2023-04-29 11:37:33,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +24: [2023-04-29 11:37:33,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +14: [2023-04-29 11:37:33,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +14: [2023-04-29 11:37:33,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +63: [2023-04-29 11:37:33,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +43: [2023-04-29 11:37:33,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +34: [2023-04-29 11:37:33,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +43: [2023-04-29 11:37:33,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +25: [2023-04-29 11:37:33,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +57: [2023-04-29 11:37:33,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +57: [2023-04-29 11:37:33,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +57: [2023-04-29 11:37:33,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +59: [2023-04-29 11:37:33,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +14: [2023-04-29 11:37:33,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +25: [2023-04-29 11:37:33,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +35: [2023-04-29 11:37:33,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +25: [2023-04-29 11:37:33,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +39: [2023-04-29 11:37:33,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +29: [2023-04-29 11:37:33,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +40: [2023-04-29 11:37:33,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +24: [2023-04-29 11:37:33,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +25: [2023-04-29 11:37:33,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +14: [2023-04-29 11:37:33,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +14: [2023-04-29 11:37:33,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +34: [2023-04-29 11:37:33,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +59: [2023-04-29 11:37:33,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +59: [2023-04-29 11:37:33,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +39: [2023-04-29 11:37:33,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +39: [2023-04-29 11:37:33,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +40: [2023-04-29 11:37:33,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +40: [2023-04-29 11:37:33,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +40: [2023-04-29 11:37:33,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +63: [2023-04-29 11:37:33,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +51: [2023-04-29 11:37:33,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +51: [2023-04-29 11:37:33,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +51: [2023-04-29 11:37:33,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +63: [2023-04-29 11:37:33,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +37: [2023-04-29 11:37:33,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_20_mp_rank_02_optim_states.pt... +37: [2023-04-29 11:37:33,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_21_mp_rank_02_optim_states.pt... +37: [2023-04-29 11:37:33,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_23_mp_rank_02_optim_states.pt... +37: [2023-04-29 11:37:33,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_22_mp_rank_02_optim_states.pt... +60: [2023-04-29 11:37:33,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +41: [2023-04-29 11:37:33,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +41: [2023-04-29 11:37:33,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +59: [2023-04-29 11:37:33,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +27: [2023-04-29 11:37:33,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +27: [2023-04-29 11:37:33,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +51: [2023-04-29 11:37:33,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +36: [2023-04-29 11:37:33,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +27: [2023-04-29 11:37:33,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +27: [2023-04-29 11:37:33,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +61: [2023-04-29 11:37:33,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +41: [2023-04-29 11:37:33,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +39: [2023-04-29 11:37:33,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt... +41: [2023-04-29 11:37:33,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +36: [2023-04-29 11:37:33,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +56: [2023-04-29 11:37:33,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +56: [2023-04-29 11:37:33,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +56: [2023-04-29 11:37:33,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +57: [2023-04-29 11:37:33,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +57: [2023-04-29 11:37:33,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +35: [2023-04-29 11:37:33,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +35: [2023-04-29 11:37:33,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +61: [2023-04-29 11:37:33,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. + 8: [2023-04-29 11:37:33,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +34: [2023-04-29 11:37:33,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +40: [2023-04-29 11:37:33,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +13: [2023-04-29 11:37:33,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +39: [2023-04-29 11:37:33,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +40: [2023-04-29 11:37:33,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +13: [2023-04-29 11:37:33,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +13: [2023-04-29 11:37:33,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +40: [2023-04-29 11:37:33,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +60: [2023-04-29 11:37:33,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +60: [2023-04-29 11:37:33,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +56: [2023-04-29 11:37:33,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +29: [2023-04-29 11:37:33,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +29: [2023-04-29 11:37:33,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +29: [2023-04-29 11:37:33,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +40: [2023-04-29 11:37:33,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +13: [2023-04-29 11:37:33,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +40: [2023-04-29 11:37:33,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +40: [2023-04-29 11:37:33,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +61: [2023-04-29 11:37:33,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +40: [2023-04-29 11:37:33,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +40: [2023-04-29 11:37:33,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +40: [2023-04-29 11:37:33,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +35: [2023-04-29 11:37:33,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +40: [2023-04-29 11:37:33,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +40: [2023-04-29 11:37:33,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +40: [2023-04-29 11:37:33,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +36: [2023-04-29 11:37:33,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +36: [2023-04-29 11:37:33,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +57: [2023-04-29 11:37:33,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. + 8: [2023-04-29 11:37:33,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 1: [2023-04-29 11:37:33,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. + 1: [2023-04-29 11:37:33,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. + 1: [2023-04-29 11:37:33,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. + 1: [2023-04-29 11:37:33,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +42: [2023-04-29 11:37:33,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +42: [2023-04-29 11:37:33,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +42: [2023-04-29 11:37:33,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +55: [2023-04-29 11:37:33,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +60: [2023-04-29 11:37:33,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. + 1: [2023-04-29 11:37:33,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 1: [2023-04-29 11:37:33,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +59: [2023-04-29 11:37:33,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +61: [2023-04-29 11:37:33,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +55: [2023-04-29 11:37:33,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 8: [2023-04-29 11:37:33,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 8: [2023-04-29 11:37:33,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +43: [2023-04-29 11:37:33,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +42: [2023-04-29 11:37:33,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +29: [2023-04-29 11:37:33,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +57: [2023-04-29 11:37:33,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +55: [2023-04-29 11:37:33,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +55: [2023-04-29 11:37:33,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +39: [2023-04-29 11:37:33,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +59: [2023-04-29 11:37:33,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +59: [2023-04-29 11:37:33,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +60: [2023-04-29 11:37:33,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +43: [2023-04-29 11:37:33,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. + 1: [2023-04-29 11:37:33,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +61: [2023-04-29 11:37:33,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +48: [2023-04-29 11:37:33,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +48: [2023-04-29 11:37:33,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +48: [2023-04-29 11:37:33,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +57: [2023-04-29 11:37:33,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +48: [2023-04-29 11:37:33,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +39: [2023-04-29 11:37:33,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +41: [2023-04-29 11:37:33,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +17: [2023-04-29 11:37:33,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +17: [2023-04-29 11:37:33,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +17: [2023-04-29 11:37:33,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +43: [2023-04-29 11:37:33,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +41: [2023-04-29 11:37:33,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +17: [2023-04-29 11:37:33,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +43: [2023-04-29 11:37:33,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +36: [2023-04-29 11:37:33,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +36: [2023-04-29 11:37:33,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +59: [2023-04-29 11:37:33,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +57: [2023-04-29 11:37:33,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +13: [2023-04-29 11:37:33,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +56: [2023-04-29 11:37:33,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +56: [2023-04-29 11:37:33,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +61: [2023-04-29 11:37:33,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +56: [2023-04-29 11:37:33,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +51: [2023-04-29 11:37:33,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +48: [2023-04-29 11:37:33,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 8: [2023-04-29 11:37:33,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +48: [2023-04-29 11:37:33,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +48: [2023-04-29 11:37:33,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +48: [2023-04-29 11:37:33,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +51: [2023-04-29 11:37:33,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +51: [2023-04-29 11:37:33,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +51: [2023-04-29 11:37:33,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +55: [2023-04-29 11:37:33,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +39: [2023-04-29 11:37:33,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +40: [2023-04-29 11:37:33,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_32_mp_rank_02_optim_states.pt... +40: [2023-04-29 11:37:33,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_33_mp_rank_02_optim_states.pt... +40: [2023-04-29 11:37:33,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_35_mp_rank_02_optim_states.pt... +40: [2023-04-29 11:37:33,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_34_mp_rank_02_optim_states.pt... + 1: [2023-04-29 11:37:33,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +41: [2023-04-29 11:37:33,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 8: [2023-04-29 11:37:33,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +39: [2023-04-29 11:37:33,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +57: [2023-04-29 11:37:33,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +13: [2023-04-29 11:37:33,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +13: [2023-04-29 11:37:33,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +60: [2023-04-29 11:37:33,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +60: [2023-04-29 11:37:33,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +61: [2023-04-29 11:37:33,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +13: [2023-04-29 11:37:33,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +43: [2023-04-29 11:37:33,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +25: [2023-04-29 11:37:33,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +55: [2023-04-29 11:37:33,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +42: [2023-04-29 11:37:33,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +55: [2023-04-29 11:37:33,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +56: [2023-04-29 11:37:33,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +55: [2023-04-29 11:37:33,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +42: [2023-04-29 11:37:33,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +42: [2023-04-29 11:37:33,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +36: [2023-04-29 11:37:33,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 4: [2023-04-29 11:37:33,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 4: [2023-04-29 11:37:33,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 1: [2023-04-29 11:37:33,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +49: [2023-04-29 11:37:33,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +36: [2023-04-29 11:37:33,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 4: [2023-04-29 11:37:33,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 4: [2023-04-29 11:37:33,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +49: [2023-04-29 11:37:33,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 1: [2023-04-29 11:37:33,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +55: [2023-04-29 11:37:33,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +55: [2023-04-29 11:37:33,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +55: [2023-04-29 11:37:33,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +61: [2023-04-29 11:37:33,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +60: [2023-04-29 11:37:33,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +55: [2023-04-29 11:37:33,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +55: [2023-04-29 11:37:33,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +55: [2023-04-29 11:37:33,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +42: [2023-04-29 11:37:33,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +55: [2023-04-29 11:37:33,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +55: [2023-04-29 11:37:33,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +55: [2023-04-29 11:37:33,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +57: [2023-04-29 11:37:33,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +55: [2023-04-29 11:37:33,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +55: [2023-04-29 11:37:33,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +55: [2023-04-29 11:37:33,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. + 8: [2023-04-29 11:37:33,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 8: [2023-04-29 11:37:33,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 1: [2023-04-29 11:37:33,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +47: [2023-04-29 11:37:33,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +47: [2023-04-29 11:37:33,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +39: [2023-04-29 11:37:34,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +17: [2023-04-29 11:37:34,001] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +43: [2023-04-29 11:37:34,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +25: [2023-04-29 11:37:34,003] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +47: [2023-04-29 11:37:34,003] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +49: [2023-04-29 11:37:34,003] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +49: [2023-04-29 11:37:34,003] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +47: [2023-04-29 11:37:34,003] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 1: [2023-04-29 11:37:34,004] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +18: [2023-04-29 11:37:34,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +18: [2023-04-29 11:37:34,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 1: [2023-04-29 11:37:34,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +21: [2023-04-29 11:37:34,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +21: [2023-04-29 11:37:34,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +21: [2023-04-29 11:37:34,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +21: [2023-04-29 11:37:34,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +43: [2023-04-29 11:37:34,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +43: [2023-04-29 11:37:34,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +23: [2023-04-29 11:37:34,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +23: [2023-04-29 11:37:34,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +39: [2023-04-29 11:37:34,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +47: [2023-04-29 11:37:34,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +47: [2023-04-29 11:37:34,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +18: [2023-04-29 11:37:34,006] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +18: [2023-04-29 11:37:34,006] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +47: [2023-04-29 11:37:34,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +17: [2023-04-29 11:37:34,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +23: [2023-04-29 11:37:34,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +23: [2023-04-29 11:37:34,009] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +47: [2023-04-29 11:37:34,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +25: [2023-04-29 11:37:34,009] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +25: [2023-04-29 11:37:34,010] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +17: [2023-04-29 11:37:34,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +25: [2023-04-29 11:37:34,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +17: [2023-04-29 11:37:34,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +18: [2023-04-29 11:37:34,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +18: [2023-04-29 11:37:34,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +23: [2023-04-29 11:37:34,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +23: [2023-04-29 11:37:34,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +23: [2023-04-29 11:37:34,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +18: [2023-04-29 11:37:34,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +20: [2023-04-29 11:37:34,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +20: [2023-04-29 11:37:34,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 4: [2023-04-29 11:37:34,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +23: [2023-04-29 11:37:34,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +18: [2023-04-29 11:37:34,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +39: [2023-04-29 11:37:34,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +27: [2023-04-29 11:37:34,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +20: [2023-04-29 11:37:34,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +20: [2023-04-29 11:37:34,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 4: [2023-04-29 11:37:34,016] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 4: [2023-04-29 11:37:34,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +39: [2023-04-29 11:37:34,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +49: [2023-04-29 11:37:34,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +27: [2023-04-29 11:37:34,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 4: [2023-04-29 11:37:34,019] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +49: [2023-04-29 11:37:34,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +27: [2023-04-29 11:37:34,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +27: [2023-04-29 11:37:34,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +49: [2023-04-29 11:37:34,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +39: [2023-04-29 11:37:34,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +49: [2023-04-29 11:37:34,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +49: [2023-04-29 11:37:34,022] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +49: [2023-04-29 11:37:34,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +49: [2023-04-29 11:37:34,022] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +49: [2023-04-29 11:37:34,022] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +27: [2023-04-29 11:37:34,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 0: [2023-04-29 11:37:34,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 0: [2023-04-29 11:37:34,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 0: [2023-04-29 11:37:34,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 0: [2023-04-29 11:37:34,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +27: [2023-04-29 11:37:34,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +27: [2023-04-29 11:37:34,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +39: [2023-04-29 11:37:34,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +21: [2023-04-29 11:37:34,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +21: [2023-04-29 11:37:34,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +27: [2023-04-29 11:37:34,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +25: [2023-04-29 11:37:34,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +39: [2023-04-29 11:37:34,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +39: [2023-04-29 11:37:34,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +39: [2023-04-29 11:37:34,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_00-model_states.pt. +55: [2023-04-29 11:37:34,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_92_mp_rank_02_optim_states.pt... +55: [2023-04-29 11:37:34,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_94_mp_rank_02_optim_states.pt... +55: [2023-04-29 11:37:34,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_95_mp_rank_02_optim_states.pt... +55: [2023-04-29 11:37:34,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_93_mp_rank_02_optim_states.pt... +49: [2023-04-29 11:37:34,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +49: [2023-04-29 11:37:34,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +49: [2023-04-29 11:37:34,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +49: [2023-04-29 11:37:34,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +49: [2023-04-29 11:37:34,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +49: [2023-04-29 11:37:34,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +49: [2023-04-29 11:37:34,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +49: [2023-04-29 11:37:34,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +20: [2023-04-29 11:37:34,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +21: [2023-04-29 11:37:34,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +20: [2023-04-29 11:37:34,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +52: [2023-04-29 11:37:34,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +52: [2023-04-29 11:37:34,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +20: [2023-04-29 11:37:34,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +21: [2023-04-29 11:37:34,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +52: [2023-04-29 11:37:34,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +52: [2023-04-29 11:37:34,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +20: [2023-04-29 11:37:34,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +25: [2023-04-29 11:37:34,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +39: [2023-04-29 11:37:34,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +20: [2023-04-29 11:37:34,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +48: [2023-04-29 11:37:34,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +39: [2023-04-29 11:37:34,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt... +52: [2023-04-29 11:37:34,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +13: [2023-04-29 11:37:34,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +25: [2023-04-29 11:37:34,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +52: [2023-04-29 11:37:34,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +52: [2023-04-29 11:37:34,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +20: [2023-04-29 11:37:34,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +20: [2023-04-29 11:37:34,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +20: [2023-04-29 11:37:34,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +20: [2023-04-29 11:37:34,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 6: [2023-04-29 11:37:34,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. + 6: [2023-04-29 11:37:34,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. + 6: [2023-04-29 11:37:34,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +52: [2023-04-29 11:37:34,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 6: [2023-04-29 11:37:34,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +20: [2023-04-29 11:37:34,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +11: [2023-04-29 11:37:34,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +11: [2023-04-29 11:37:34,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +11: [2023-04-29 11:37:34,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +20: [2023-04-29 11:37:34,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +13: [2023-04-29 11:37:34,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +11: [2023-04-29 11:37:34,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +13: [2023-04-29 11:37:34,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +20: [2023-04-29 11:37:34,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +48: [2023-04-29 11:37:34,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 1: [2023-04-29 11:37:34,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +48: [2023-04-29 11:37:34,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +48: [2023-04-29 11:37:34,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +19: [2023-04-29 11:37:34,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +19: [2023-04-29 11:37:34,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +19: [2023-04-29 11:37:34,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +19: [2023-04-29 11:37:34,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +13: [2023-04-29 11:37:34,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 0: [2023-04-29 11:37:34,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 0: [2023-04-29 11:37:34,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 0: [2023-04-29 11:37:34,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +62: [2023-04-29 11:37:34,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +62: [2023-04-29 11:37:34,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +62: [2023-04-29 11:37:34,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 1: [2023-04-29 11:37:34,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... + 9: [2023-04-29 11:37:34,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 9: [2023-04-29 11:37:34,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 9: [2023-04-29 11:37:34,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 0: [2023-04-29 11:37:34,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +13: [2023-04-29 11:37:34,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +62: [2023-04-29 11:37:34,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 9: [2023-04-29 11:37:34,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 8: [2023-04-29 11:37:34,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 8: [2023-04-29 11:37:34,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +13: [2023-04-29 11:37:34,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 8: [2023-04-29 11:37:34,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +13: [2023-04-29 11:37:34,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 8: [2023-04-29 11:37:34,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 1: [2023-04-29 11:37:34,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +62: [2023-04-29 11:37:34,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +62: [2023-04-29 11:37:34,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +62: [2023-04-29 11:37:34,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +62: [2023-04-29 11:37:34,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 9: [2023-04-29 11:37:34,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 1: [2023-04-29 11:37:34,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +13: [2023-04-29 11:37:34,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +38: [2023-04-29 11:37:34,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +38: [2023-04-29 11:37:34,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 1: [2023-04-29 11:37:34,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 9: [2023-04-29 11:37:34,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +38: [2023-04-29 11:37:34,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 9: [2023-04-29 11:37:34,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +38: [2023-04-29 11:37:34,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 9: [2023-04-29 11:37:34,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +17: [2023-04-29 11:37:34,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 1: [2023-04-29 11:37:34,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +38: [2023-04-29 11:37:34,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +53: [2023-04-29 11:37:34,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +53: [2023-04-29 11:37:34,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +49: [2023-04-29 11:37:34,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_70_mp_rank_02_optim_states.pt... +49: [2023-04-29 11:37:34,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_68_mp_rank_02_optim_states.pt... +49: [2023-04-29 11:37:34,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_71_mp_rank_02_optim_states.pt... +49: [2023-04-29 11:37:34,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_69_mp_rank_02_optim_states.pt... + 1: [2023-04-29 11:37:34,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +38: [2023-04-29 11:37:34,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +50: [2023-04-29 11:37:34,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +50: [2023-04-29 11:37:34,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +53: [2023-04-29 11:37:34,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +48: [2023-04-29 11:37:34,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +50: [2023-04-29 11:37:34,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +38: [2023-04-29 11:37:34,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +53: [2023-04-29 11:37:34,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +50: [2023-04-29 11:37:34,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. + 1: [2023-04-29 11:37:34,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +38: [2023-04-29 11:37:34,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +47: [2023-04-29 11:37:34,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +47: [2023-04-29 11:37:34,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +25: [2023-04-29 11:37:34,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +25: [2023-04-29 11:37:34,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +17: [2023-04-29 11:37:34,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +18: [2023-04-29 11:37:34,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +25: [2023-04-29 11:37:34,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +25: [2023-04-29 11:37:34,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. + 4: [2023-04-29 11:37:34,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +47: [2023-04-29 11:37:34,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +23: [2023-04-29 11:37:34,075] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +47: [2023-04-29 11:37:34,075] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +19: [2023-04-29 11:37:34,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +11: [2023-04-29 11:37:34,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 4: [2023-04-29 11:37:34,076] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +48: [2023-04-29 11:37:34,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 6: [2023-04-29 11:37:34,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 6: [2023-04-29 11:37:34,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 6: [2023-04-29 11:37:34,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 4: [2023-04-29 11:37:34,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +23: [2023-04-29 11:37:34,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +48: [2023-04-29 11:37:34,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +48: [2023-04-29 11:37:34,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +48: [2023-04-29 11:37:34,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +48: [2023-04-29 11:37:34,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +48: [2023-04-29 11:37:34,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +48: [2023-04-29 11:37:34,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +11: [2023-04-29 11:37:34,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +17: [2023-04-29 11:37:34,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +17: [2023-04-29 11:37:34,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +48: [2023-04-29 11:37:34,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 6: [2023-04-29 11:37:34,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +48: [2023-04-29 11:37:34,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +48: [2023-04-29 11:37:34,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 4: [2023-04-29 11:37:34,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +48: [2023-04-29 11:37:34,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +23: [2023-04-29 11:37:34,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +23: [2023-04-29 11:37:34,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 4: [2023-04-29 11:37:34,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +11: [2023-04-29 11:37:34,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +11: [2023-04-29 11:37:34,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +18: [2023-04-29 11:37:34,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +18: [2023-04-29 11:37:34,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +48: [2023-04-29 11:37:34,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +17: [2023-04-29 11:37:34,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +17: [2023-04-29 11:37:34,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +19: [2023-04-29 11:37:34,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +19: [2023-04-29 11:37:34,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 4: [2023-04-29 11:37:34,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +19: [2023-04-29 11:37:34,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +48: [2023-04-29 11:37:34,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +48: [2023-04-29 11:37:34,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +17: [2023-04-29 11:37:34,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +18: [2023-04-29 11:37:34,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +48: [2023-04-29 11:37:34,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. + 4: [2023-04-29 11:37:34,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +30: [2023-04-29 11:37:34,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +30: [2023-04-29 11:37:34,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +30: [2023-04-29 11:37:34,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +11: [2023-04-29 11:37:34,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +30: [2023-04-29 11:37:34,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +11: [2023-04-29 11:37:34,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +11: [2023-04-29 11:37:34,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +11: [2023-04-29 11:37:34,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +21: [2023-04-29 11:37:34,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 4: [2023-04-29 11:37:34,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 8: [2023-04-29 11:37:34,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +26: [2023-04-29 11:37:34,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +26: [2023-04-29 11:37:34,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +17: [2023-04-29 11:37:34,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 8: [2023-04-29 11:37:34,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +11: [2023-04-29 11:37:34,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +18: [2023-04-29 11:37:34,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +21: [2023-04-29 11:37:34,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +21: [2023-04-29 11:37:34,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +26: [2023-04-29 11:37:34,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +11: [2023-04-29 11:37:34,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +26: [2023-04-29 11:37:34,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +11: [2023-04-29 11:37:34,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +11: [2023-04-29 11:37:34,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +50: [2023-04-29 11:37:34,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +44: [2023-04-29 11:37:34,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +44: [2023-04-29 11:37:34,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +44: [2023-04-29 11:37:34,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +58: [2023-04-29 11:37:34,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +58: [2023-04-29 11:37:34,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +58: [2023-04-29 11:37:34,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +47: [2023-04-29 11:37:34,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +21: [2023-04-29 11:37:34,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +47: [2023-04-29 11:37:34,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +58: [2023-04-29 11:37:34,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +44: [2023-04-29 11:37:34,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. + 8: [2023-04-29 11:37:34,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +25: [2023-04-29 11:37:34,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 8: [2023-04-29 11:37:34,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +50: [2023-04-29 11:37:34,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +25: [2023-04-29 11:37:34,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +47: [2023-04-29 11:37:34,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +47: [2023-04-29 11:37:34,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +25: [2023-04-29 11:37:34,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +47: [2023-04-29 11:37:34,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +23: [2023-04-29 11:37:34,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +50: [2023-04-29 11:37:34,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +47: [2023-04-29 11:37:34,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +47: [2023-04-29 11:37:34,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +47: [2023-04-29 11:37:34,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +47: [2023-04-29 11:37:34,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +47: [2023-04-29 11:37:34,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +58: [2023-04-29 11:37:34,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +47: [2023-04-29 11:37:34,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +21: [2023-04-29 11:37:34,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +47: [2023-04-29 11:37:34,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +58: [2023-04-29 11:37:34,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +53: [2023-04-29 11:37:34,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +53: [2023-04-29 11:37:34,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +58: [2023-04-29 11:37:34,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +53: [2023-04-29 11:37:34,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +53: [2023-04-29 11:37:34,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +58: [2023-04-29 11:37:34,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +25: [2023-04-29 11:37:34,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +23: [2023-04-29 11:37:34,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +21: [2023-04-29 11:37:34,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +47: [2023-04-29 11:37:34,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +50: [2023-04-29 11:37:34,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +52: [2023-04-29 11:37:34,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +47: [2023-04-29 11:37:34,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +47: [2023-04-29 11:37:34,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +47: [2023-04-29 11:37:34,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +20: [2023-04-29 11:37:34,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +23: [2023-04-29 11:37:34,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +23: [2023-04-29 11:37:34,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +21: [2023-04-29 11:37:34,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... + 0: [2023-04-29 11:37:34,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +52: [2023-04-29 11:37:34,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +52: [2023-04-29 11:37:34,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +52: [2023-04-29 11:37:34,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +21: [2023-04-29 11:37:34,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +30: [2023-04-29 11:37:34,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +20: [2023-04-29 11:37:34,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +20: [2023-04-29 11:37:34,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +30: [2023-04-29 11:37:34,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +18: [2023-04-29 11:37:34,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 0: [2023-04-29 11:37:34,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 0: [2023-04-29 11:37:34,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +30: [2023-04-29 11:37:34,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +37: [2023-04-29 11:37:34,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +37: [2023-04-29 11:37:34,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +30: [2023-04-29 11:37:34,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 0: [2023-04-29 11:37:34,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +37: [2023-04-29 11:37:34,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +20: [2023-04-29 11:37:34,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +37: [2023-04-29 11:37:34,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +30: [2023-04-29 11:37:34,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 9: [2023-04-29 11:37:34,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +30: [2023-04-29 11:37:34,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +26: [2023-04-29 11:37:34,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +26: [2023-04-29 11:37:34,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +26: [2023-04-29 11:37:34,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +18: [2023-04-29 11:37:34,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +48: [2023-04-29 11:37:34,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_64_mp_rank_02_optim_states.pt... +48: [2023-04-29 11:37:34,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_65_mp_rank_02_optim_states.pt... +48: [2023-04-29 11:37:34,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_66_mp_rank_02_optim_states.pt... +48: [2023-04-29 11:37:34,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_67_mp_rank_02_optim_states.pt... +30: [2023-04-29 11:37:34,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +30: [2023-04-29 11:37:34,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +20: [2023-04-29 11:37:34,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 0: [2023-04-29 11:37:34,123] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 0: [2023-04-29 11:37:34,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +26: [2023-04-29 11:37:34,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +30: [2023-04-29 11:37:34,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +18: [2023-04-29 11:37:34,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +38: [2023-04-29 11:37:34,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +30: [2023-04-29 11:37:34,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +20: [2023-04-29 11:37:34,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +20: [2023-04-29 11:37:34,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +62: [2023-04-29 11:37:34,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +44: [2023-04-29 11:37:34,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +62: [2023-04-29 11:37:34,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +44: [2023-04-29 11:37:34,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 7: [2023-04-29 11:37:34,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +20: [2023-04-29 11:37:34,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +30: [2023-04-29 11:37:34,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +30: [2023-04-29 11:37:34,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +52: [2023-04-29 11:37:34,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 0: [2023-04-29 11:37:34,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +38: [2023-04-29 11:37:34,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +20: [2023-04-29 11:37:34,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +44: [2023-04-29 11:37:34,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +44: [2023-04-29 11:37:34,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +38: [2023-04-29 11:37:34,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +38: [2023-04-29 11:37:34,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 9: [2023-04-29 11:37:34,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 9: [2023-04-29 11:37:34,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +20: [2023-04-29 11:37:34,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 9: [2023-04-29 11:37:34,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +52: [2023-04-29 11:37:34,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +52: [2023-04-29 11:37:34,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 0: [2023-04-29 11:37:34,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +20: [2023-04-29 11:37:34,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +52: [2023-04-29 11:37:34,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +20: [2023-04-29 11:37:34,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 7: [2023-04-29 11:37:34,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +62: [2023-04-29 11:37:34,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +55: [2023-04-29 11:37:34,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +55: [2023-04-29 11:37:34,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +55: [2023-04-29 11:37:34,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +55: [2023-04-29 11:37:34,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +62: [2023-04-29 11:37:34,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 7: [2023-04-29 11:37:34,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +52: [2023-04-29 11:37:34,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +20: [2023-04-29 11:37:34,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +52: [2023-04-29 11:37:34,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +52: [2023-04-29 11:37:34,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +19: [2023-04-29 11:37:34,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +52: [2023-04-29 11:37:34,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. + 6: [2023-04-29 11:37:34,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +27: [2023-04-29 11:37:34,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +27: [2023-04-29 11:37:34,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +27: [2023-04-29 11:37:34,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +52: [2023-04-29 11:37:34,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +47: [2023-04-29 11:37:34,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_61_mp_rank_02_optim_states.pt... +47: [2023-04-29 11:37:34,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_63_mp_rank_02_optim_states.pt... +47: [2023-04-29 11:37:34,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_62_mp_rank_02_optim_states.pt... +47: [2023-04-29 11:37:34,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_60_mp_rank_02_optim_states.pt... +20: [2023-04-29 11:37:34,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +52: [2023-04-29 11:37:34,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +52: [2023-04-29 11:37:34,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +52: [2023-04-29 11:37:34,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +52: [2023-04-29 11:37:34,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +27: [2023-04-29 11:37:34,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +62: [2023-04-29 11:37:34,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +52: [2023-04-29 11:37:34,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +52: [2023-04-29 11:37:34,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +62: [2023-04-29 11:37:34,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +62: [2023-04-29 11:37:34,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +37: [2023-04-29 11:37:34,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +52: [2023-04-29 11:37:34,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +11: [2023-04-29 11:37:34,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +62: [2023-04-29 11:37:34,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +19: [2023-04-29 11:37:34,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... + 2: [2023-04-29 11:37:34,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. + 2: [2023-04-29 11:37:34,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. + 2: [2023-04-29 11:37:34,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. + 2: [2023-04-29 11:37:34,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +31: [2023-04-29 11:37:34,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +31: [2023-04-29 11:37:34,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +23: [2023-04-29 11:37:34,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +23: [2023-04-29 11:37:34,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +20: [2023-04-29 11:37:34,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +27: [2023-04-29 11:37:34,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 6: [2023-04-29 11:37:34,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +31: [2023-04-29 11:37:34,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +31: [2023-04-29 11:37:34,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +23: [2023-04-29 11:37:34,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +23: [2023-04-29 11:37:34,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +27: [2023-04-29 11:37:34,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 9: [2023-04-29 11:37:34,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +27: [2023-04-29 11:37:34,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +38: [2023-04-29 11:37:34,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 6: [2023-04-29 11:37:34,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 6: [2023-04-29 11:37:34,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +62: [2023-04-29 11:37:34,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +27: [2023-04-29 11:37:34,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +62: [2023-04-29 11:37:34,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 8: [2023-04-29 11:37:34,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +11: [2023-04-29 11:37:34,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +11: [2023-04-29 11:37:34,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +37: [2023-04-29 11:37:34,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +10: [2023-04-29 11:37:34,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +10: [2023-04-29 11:37:34,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +10: [2023-04-29 11:37:34,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +10: [2023-04-29 11:37:34,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +19: [2023-04-29 11:37:34,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +19: [2023-04-29 11:37:34,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +37: [2023-04-29 11:37:34,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +19: [2023-04-29 11:37:34,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +38: [2023-04-29 11:37:34,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +37: [2023-04-29 11:37:34,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +38: [2023-04-29 11:37:34,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +38: [2023-04-29 11:37:34,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 6: [2023-04-29 11:37:34,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +38: [2023-04-29 11:37:34,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +38: [2023-04-29 11:37:34,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +38: [2023-04-29 11:37:34,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +38: [2023-04-29 11:37:34,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. + 6: [2023-04-29 11:37:34,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +62: [2023-04-29 11:37:34,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +38: [2023-04-29 11:37:34,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +62: [2023-04-29 11:37:34,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +62: [2023-04-29 11:37:34,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. + 6: [2023-04-29 11:37:34,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +62: [2023-04-29 11:37:34,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +38: [2023-04-29 11:37:34,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +38: [2023-04-29 11:37:34,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +62: [2023-04-29 11:37:34,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. + 5: [2023-04-29 11:37:34,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 5: [2023-04-29 11:37:34,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 5: [2023-04-29 11:37:34,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +62: [2023-04-29 11:37:34,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +38: [2023-04-29 11:37:34,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +11: [2023-04-29 11:37:34,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +11: [2023-04-29 11:37:34,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 5: [2023-04-29 11:37:34,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 8: [2023-04-29 11:37:34,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +58: [2023-04-29 11:37:34,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +58: [2023-04-29 11:37:34,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +58: [2023-04-29 11:37:34,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +58: [2023-04-29 11:37:34,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +10: [2023-04-29 11:37:34,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +11: [2023-04-29 11:37:34,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 8: [2023-04-29 11:37:34,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +10: [2023-04-29 11:37:34,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +10: [2023-04-29 11:37:34,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +38: [2023-04-29 11:37:34,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +10: [2023-04-29 11:37:34,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +38: [2023-04-29 11:37:34,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +38: [2023-04-29 11:37:34,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +25: [2023-04-29 11:37:34,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +38: [2023-04-29 11:37:34,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +49: [2023-04-29 11:37:34,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +49: [2023-04-29 11:37:34,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +49: [2023-04-29 11:37:34,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +58: [2023-04-29 11:37:34,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +12: [2023-04-29 11:37:34,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +12: [2023-04-29 11:37:34,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +20: [2023-04-29 11:37:34,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +49: [2023-04-29 11:37:34,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +32: [2023-04-29 11:37:34,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +25: [2023-04-29 11:37:34,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +33: [2023-04-29 11:37:34,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +33: [2023-04-29 11:37:34,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +32: [2023-04-29 11:37:34,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +33: [2023-04-29 11:37:34,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +33: [2023-04-29 11:37:34,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 6: [2023-04-29 11:37:34,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +32: [2023-04-29 11:37:34,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +32: [2023-04-29 11:37:34,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +25: [2023-04-29 11:37:34,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +19: [2023-04-29 11:37:34,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +19: [2023-04-29 11:37:34,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +19: [2023-04-29 11:37:34,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... + 5: [2023-04-29 11:37:34,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 5: [2023-04-29 11:37:34,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 5: [2023-04-29 11:37:34,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 8: [2023-04-29 11:37:34,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +11: [2023-04-29 11:37:34,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +11: [2023-04-29 11:37:34,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +12: [2023-04-29 11:37:34,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 4: [2023-04-29 11:37:34,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 4: [2023-04-29 11:37:34,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 4: [2023-04-29 11:37:34,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 5: [2023-04-29 11:37:34,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 4: [2023-04-29 11:37:34,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +25: [2023-04-29 11:37:34,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +11: [2023-04-29 11:37:34,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +50: [2023-04-29 11:37:34,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 9: [2023-04-29 11:37:34,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +11: [2023-04-29 11:37:34,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +32: [2023-04-29 11:37:34,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +12: [2023-04-29 11:37:34,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +25: [2023-04-29 11:37:34,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +28: [2023-04-29 11:37:34,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +28: [2023-04-29 11:37:34,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +25: [2023-04-29 11:37:34,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +25: [2023-04-29 11:37:34,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +26: [2023-04-29 11:37:34,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +26: [2023-04-29 11:37:34,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 9: [2023-04-29 11:37:34,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +53: [2023-04-29 11:37:34,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +12: [2023-04-29 11:37:34,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +33: [2023-04-29 11:37:34,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +33: [2023-04-29 11:37:34,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +32: [2023-04-29 11:37:34,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +62: [2023-04-29 11:37:34,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +26: [2023-04-29 11:37:34,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +33: [2023-04-29 11:37:34,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +12: [2023-04-29 11:37:34,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +33: [2023-04-29 11:37:34,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +62: [2023-04-29 11:37:34,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +26: [2023-04-29 11:37:34,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +62: [2023-04-29 11:37:34,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 2: [2023-04-29 11:37:34,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +62: [2023-04-29 11:37:34,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +32: [2023-04-29 11:37:34,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +12: [2023-04-29 11:37:34,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +32: [2023-04-29 11:37:34,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +50: [2023-04-29 11:37:34,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +28: [2023-04-29 11:37:34,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +28: [2023-04-29 11:37:34,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 9: [2023-04-29 11:37:34,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +52: [2023-04-29 11:37:34,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_81_mp_rank_02_optim_states.pt... +52: [2023-04-29 11:37:34,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_83_mp_rank_02_optim_states.pt... +52: [2023-04-29 11:37:34,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_80_mp_rank_02_optim_states.pt... +52: [2023-04-29 11:37:34,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_82_mp_rank_02_optim_states.pt... + 4: [2023-04-29 11:37:34,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +25: [2023-04-29 11:37:34,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +55: [2023-04-29 11:37:34,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +55: [2023-04-29 11:37:34,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 4: [2023-04-29 11:37:34,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +55: [2023-04-29 11:37:34,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 4: [2023-04-29 11:37:34,175] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 4: [2023-04-29 11:37:34,175] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +28: [2023-04-29 11:37:34,175] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +28: [2023-04-29 11:37:34,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +12: [2023-04-29 11:37:34,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 2: [2023-04-29 11:37:34,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +50: [2023-04-29 11:37:34,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... + 2: [2023-04-29 11:37:34,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +29: [2023-04-29 11:37:34,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +29: [2023-04-29 11:37:34,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +26: [2023-04-29 11:37:34,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +29: [2023-04-29 11:37:34,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +26: [2023-04-29 11:37:34,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +29: [2023-04-29 11:37:34,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. + 8: [2023-04-29 11:37:34,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +11: [2023-04-29 11:37:34,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +26: [2023-04-29 11:37:34,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +50: [2023-04-29 11:37:34,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 2: [2023-04-29 11:37:34,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +26: [2023-04-29 11:37:34,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +50: [2023-04-29 11:37:34,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +23: [2023-04-29 11:37:34,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +55: [2023-04-29 11:37:34,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +46: [2023-04-29 11:37:34,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +46: [2023-04-29 11:37:34,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +46: [2023-04-29 11:37:34,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +53: [2023-04-29 11:37:34,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +53: [2023-04-29 11:37:34,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +53: [2023-04-29 11:37:34,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +46: [2023-04-29 11:37:34,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +50: [2023-04-29 11:37:34,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +31: [2023-04-29 11:37:34,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +28: [2023-04-29 11:37:34,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +14: [2023-04-29 11:37:34,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +14: [2023-04-29 11:37:34,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +23: [2023-04-29 11:37:34,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +31: [2023-04-29 11:37:34,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +31: [2023-04-29 11:37:34,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 8: [2023-04-29 11:37:34,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +11: [2023-04-29 11:37:34,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +62: [2023-04-29 11:37:34,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +62: [2023-04-29 11:37:34,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +62: [2023-04-29 11:37:34,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +46: [2023-04-29 11:37:34,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +23: [2023-04-29 11:37:34,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +53: [2023-04-29 11:37:34,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +28: [2023-04-29 11:37:34,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +62: [2023-04-29 11:37:34,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +31: [2023-04-29 11:37:34,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +26: [2023-04-29 11:37:34,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +11: [2023-04-29 11:37:34,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 3: [2023-04-29 11:37:34,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 3: [2023-04-29 11:37:34,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 3: [2023-04-29 11:37:34,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +30: [2023-04-29 11:37:34,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +46: [2023-04-29 11:37:34,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +19: [2023-04-29 11:37:34,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +19: [2023-04-29 11:37:34,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +19: [2023-04-29 11:37:34,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 3: [2023-04-29 11:37:34,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +14: [2023-04-29 11:37:34,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +23: [2023-04-29 11:37:34,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 8: [2023-04-29 11:37:34,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +14: [2023-04-29 11:37:34,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +46: [2023-04-29 11:37:34,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +50: [2023-04-29 11:37:34,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +14: [2023-04-29 11:37:34,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +46: [2023-04-29 11:37:34,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +53: [2023-04-29 11:37:34,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +53: [2023-04-29 11:37:34,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +62: [2023-04-29 11:37:34,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +62: [2023-04-29 11:37:34,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +53: [2023-04-29 11:37:34,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +58: [2023-04-29 11:37:34,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +58: [2023-04-29 11:37:34,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 3: [2023-04-29 11:37:34,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +49: [2023-04-29 11:37:34,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +50: [2023-04-29 11:37:34,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +30: [2023-04-29 11:37:34,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 8: [2023-04-29 11:37:34,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +26: [2023-04-29 11:37:34,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +26: [2023-04-29 11:37:34,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 3: [2023-04-29 11:37:34,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +30: [2023-04-29 11:37:34,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +14: [2023-04-29 11:37:34,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +19: [2023-04-29 11:37:34,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +19: [2023-04-29 11:37:34,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +30: [2023-04-29 11:37:34,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 3: [2023-04-29 11:37:34,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +19: [2023-04-29 11:37:34,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +19: [2023-04-29 11:37:34,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +62: [2023-04-29 11:37:34,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +14: [2023-04-29 11:37:34,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +62: [2023-04-29 11:37:34,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +14: [2023-04-29 11:37:34,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +14: [2023-04-29 11:37:34,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 3: [2023-04-29 11:37:34,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +14: [2023-04-29 11:37:34,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +14: [2023-04-29 11:37:34,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +14: [2023-04-29 11:37:34,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +26: [2023-04-29 11:37:34,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +49: [2023-04-29 11:37:34,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +26: [2023-04-29 11:37:34,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +30: [2023-04-29 11:37:34,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +49: [2023-04-29 11:37:34,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +58: [2023-04-29 11:37:34,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +49: [2023-04-29 11:37:34,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +58: [2023-04-29 11:37:34,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +58: [2023-04-29 11:37:34,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +58: [2023-04-29 11:37:34,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +58: [2023-04-29 11:37:34,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +19: [2023-04-29 11:37:34,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +44: [2023-04-29 11:37:34,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +30: [2023-04-29 11:37:34,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +11: [2023-04-29 11:37:34,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +44: [2023-04-29 11:37:34,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +21: [2023-04-29 11:37:34,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +21: [2023-04-29 11:37:34,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +21: [2023-04-29 11:37:34,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +26: [2023-04-29 11:37:34,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +44: [2023-04-29 11:37:34,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +58: [2023-04-29 11:37:34,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +21: [2023-04-29 11:37:34,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 2: [2023-04-29 11:37:34,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 2: [2023-04-29 11:37:34,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +58: [2023-04-29 11:37:34,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +58: [2023-04-29 11:37:34,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +10: [2023-04-29 11:37:34,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +10: [2023-04-29 11:37:34,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +10: [2023-04-29 11:37:34,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +58: [2023-04-29 11:37:34,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +10: [2023-04-29 11:37:34,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +26: [2023-04-29 11:37:34,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +30: [2023-04-29 11:37:34,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +30: [2023-04-29 11:37:34,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +29: [2023-04-29 11:37:34,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 2: [2023-04-29 11:37:34,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 2: [2023-04-29 11:37:34,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +44: [2023-04-29 11:37:34,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +29: [2023-04-29 11:37:34,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +44: [2023-04-29 11:37:34,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +44: [2023-04-29 11:37:34,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +29: [2023-04-29 11:37:34,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +44: [2023-04-29 11:37:34,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +21: [2023-04-29 11:37:34,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 7: [2023-04-29 11:37:34,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 2: [2023-04-29 11:37:34,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +21: [2023-04-29 11:37:34,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +21: [2023-04-29 11:37:34,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +29: [2023-04-29 11:37:34,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +21: [2023-04-29 11:37:34,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +30: [2023-04-29 11:37:34,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +30: [2023-04-29 11:37:34,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +38: [2023-04-29 11:37:34,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_25_mp_rank_02_optim_states.pt... +38: [2023-04-29 11:37:34,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_24_mp_rank_02_optim_states.pt... +38: [2023-04-29 11:37:34,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_26_mp_rank_02_optim_states.pt... +38: [2023-04-29 11:37:34,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_27_mp_rank_02_optim_states.pt... + 2: [2023-04-29 11:37:34,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +44: [2023-04-29 11:37:34,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +30: [2023-04-29 11:37:34,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... + 2: [2023-04-29 11:37:34,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 2: [2023-04-29 11:37:34,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +30: [2023-04-29 11:37:34,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +26: [2023-04-29 11:37:34,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +11: [2023-04-29 11:37:34,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +11: [2023-04-29 11:37:34,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +62: [2023-04-29 11:37:34,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_123_mp_rank_02_optim_states.pt... +62: [2023-04-29 11:37:34,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_121_mp_rank_02_optim_states.pt... +62: [2023-04-29 11:37:34,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_120_mp_rank_02_optim_states.pt... +62: [2023-04-29 11:37:34,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_122_mp_rank_02_optim_states.pt... +27: [2023-04-29 11:37:34,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +14: [2023-04-29 11:37:34,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +30: [2023-04-29 11:37:34,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +32: [2023-04-29 11:37:34,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +32: [2023-04-29 11:37:34,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +32: [2023-04-29 11:37:34,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +32: [2023-04-29 11:37:34,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +15: [2023-04-29 11:37:34,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +15: [2023-04-29 11:37:34,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +15: [2023-04-29 11:37:34,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +15: [2023-04-29 11:37:34,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +22: [2023-04-29 11:37:34,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +22: [2023-04-29 11:37:34,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +22: [2023-04-29 11:37:34,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +22: [2023-04-29 11:37:34,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 7: [2023-04-29 11:37:34,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +37: [2023-04-29 11:37:34,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +27: [2023-04-29 11:37:34,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +58: [2023-04-29 11:37:34,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +58: [2023-04-29 11:37:34,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +58: [2023-04-29 11:37:34,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +58: [2023-04-29 11:37:34,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +46: [2023-04-29 11:37:34,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +46: [2023-04-29 11:37:34,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +46: [2023-04-29 11:37:34,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +58: [2023-04-29 11:37:34,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +58: [2023-04-29 11:37:34,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +46: [2023-04-29 11:37:34,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +15: [2023-04-29 11:37:34,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +58: [2023-04-29 11:37:34,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +37: [2023-04-29 11:37:34,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +14: [2023-04-29 11:37:34,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +58: [2023-04-29 11:37:34,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +15: [2023-04-29 11:37:34,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +22: [2023-04-29 11:37:34,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +27: [2023-04-29 11:37:34,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +27: [2023-04-29 11:37:34,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +22: [2023-04-29 11:37:34,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +22: [2023-04-29 11:37:34,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +15: [2023-04-29 11:37:34,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +14: [2023-04-29 11:37:34,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +14: [2023-04-29 11:37:34,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +15: [2023-04-29 11:37:34,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +22: [2023-04-29 11:37:34,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +10: [2023-04-29 11:37:34,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +58: [2023-04-29 11:37:34,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +12: [2023-04-29 11:37:34,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +30: [2023-04-29 11:37:34,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +37: [2023-04-29 11:37:34,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +58: [2023-04-29 11:37:34,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +58: [2023-04-29 11:37:34,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +58: [2023-04-29 11:37:34,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +37: [2023-04-29 11:37:34,229] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +54: [2023-04-29 11:37:34,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +54: [2023-04-29 11:37:34,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +45: [2023-04-29 11:37:34,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +45: [2023-04-29 11:37:34,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 4: [2023-04-29 11:37:34,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +54: [2023-04-29 11:37:34,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +32: [2023-04-29 11:37:34,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +54: [2023-04-29 11:37:34,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +10: [2023-04-29 11:37:34,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +10: [2023-04-29 11:37:34,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +10: [2023-04-29 11:37:34,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +37: [2023-04-29 11:37:34,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +63: [2023-04-29 11:37:34,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +63: [2023-04-29 11:37:34,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 7: [2023-04-29 11:37:34,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +63: [2023-04-29 11:37:34,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 2: [2023-04-29 11:37:34,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +63: [2023-04-29 11:37:34,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +45: [2023-04-29 11:37:34,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +45: [2023-04-29 11:37:34,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +27: [2023-04-29 11:37:34,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +37: [2023-04-29 11:37:34,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 7: [2023-04-29 11:37:34,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 3: [2023-04-29 11:37:34,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +30: [2023-04-29 11:37:34,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +30: [2023-04-29 11:37:34,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +33: [2023-04-29 11:37:34,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +33: [2023-04-29 11:37:34,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +33: [2023-04-29 11:37:34,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +12: [2023-04-29 11:37:34,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +35: [2023-04-29 11:37:34,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +10: [2023-04-29 11:37:34,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +47: [2023-04-29 11:37:34,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +47: [2023-04-29 11:37:34,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +47: [2023-04-29 11:37:34,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +35: [2023-04-29 11:37:34,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +35: [2023-04-29 11:37:34,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. + 5: [2023-04-29 11:37:34,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 5: [2023-04-29 11:37:34,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 5: [2023-04-29 11:37:34,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 5: [2023-04-29 11:37:34,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +35: [2023-04-29 11:37:34,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +26: [2023-04-29 11:37:34,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +45: [2023-04-29 11:37:34,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +33: [2023-04-29 11:37:34,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 2: [2023-04-29 11:37:34,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +55: [2023-04-29 11:37:34,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +26: [2023-04-29 11:37:34,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +45: [2023-04-29 11:37:34,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +63: [2023-04-29 11:37:34,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +37: [2023-04-29 11:37:34,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +45: [2023-04-29 11:37:34,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +47: [2023-04-29 11:37:34,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +63: [2023-04-29 11:37:34,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +32: [2023-04-29 11:37:34,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +31: [2023-04-29 11:37:34,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +45: [2023-04-29 11:37:34,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 4: [2023-04-29 11:37:34,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 4: [2023-04-29 11:37:34,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 4: [2023-04-29 11:37:34,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +63: [2023-04-29 11:37:34,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +63: [2023-04-29 11:37:34,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +46: [2023-04-29 11:37:34,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +37: [2023-04-29 11:37:34,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +12: [2023-04-29 11:37:34,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +32: [2023-04-29 11:37:34,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +31: [2023-04-29 11:37:34,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +23: [2023-04-29 11:37:34,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +10: [2023-04-29 11:37:34,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +10: [2023-04-29 11:37:34,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +10: [2023-04-29 11:37:34,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +55: [2023-04-29 11:37:34,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +28: [2023-04-29 11:37:34,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +28: [2023-04-29 11:37:34,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +12: [2023-04-29 11:37:34,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 2: [2023-04-29 11:37:34,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +17: [2023-04-29 11:37:34,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +55: [2023-04-29 11:37:34,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +17: [2023-04-29 11:37:34,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +17: [2023-04-29 11:37:34,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +17: [2023-04-29 11:37:34,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +26: [2023-04-29 11:37:34,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +26: [2023-04-29 11:37:34,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +32: [2023-04-29 11:37:34,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +31: [2023-04-29 11:37:34,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +32: [2023-04-29 11:37:34,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +27: [2023-04-29 11:37:34,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +28: [2023-04-29 11:37:34,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +28: [2023-04-29 11:37:34,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +31: [2023-04-29 11:37:34,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +46: [2023-04-29 11:37:34,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +55: [2023-04-29 11:37:34,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +55: [2023-04-29 11:37:34,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +14: [2023-04-29 11:37:34,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +55: [2023-04-29 11:37:34,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... + 2: [2023-04-29 11:37:34,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 3: [2023-04-29 11:37:34,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +46: [2023-04-29 11:37:34,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +46: [2023-04-29 11:37:34,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +32: [2023-04-29 11:37:34,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +28: [2023-04-29 11:37:34,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +28: [2023-04-29 11:37:34,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +28: [2023-04-29 11:37:34,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +27: [2023-04-29 11:37:34,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +27: [2023-04-29 11:37:34,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +23: [2023-04-29 11:37:34,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +23: [2023-04-29 11:37:34,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +28: [2023-04-29 11:37:34,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +12: [2023-04-29 11:37:34,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 2: [2023-04-29 11:37:34,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +17: [2023-04-29 11:37:34,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +17: [2023-04-29 11:37:34,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +19: [2023-04-29 11:37:34,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +19: [2023-04-29 11:37:34,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +17: [2023-04-29 11:37:34,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 3: [2023-04-29 11:37:34,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +49: [2023-04-29 11:37:34,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +17: [2023-04-29 11:37:34,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +46: [2023-04-29 11:37:34,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +58: [2023-04-29 11:37:34,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_107_mp_rank_02_optim_states.pt... +58: [2023-04-29 11:37:34,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_105_mp_rank_02_optim_states.pt... +58: [2023-04-29 11:37:34,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_104_mp_rank_02_optim_states.pt... +58: [2023-04-29 11:37:34,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_106_mp_rank_02_optim_states.pt... +55: [2023-04-29 11:37:34,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +22: [2023-04-29 11:37:34,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. + 3: [2023-04-29 11:37:34,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +23: [2023-04-29 11:37:34,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +22: [2023-04-29 11:37:34,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +22: [2023-04-29 11:37:34,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +55: [2023-04-29 11:37:34,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... + 3: [2023-04-29 11:37:34,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. + 2: [2023-04-29 11:37:34,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +22: [2023-04-29 11:37:34,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +31: [2023-04-29 11:37:34,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 3: [2023-04-29 11:37:34,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. + 3: [2023-04-29 11:37:34,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +31: [2023-04-29 11:37:34,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +23: [2023-04-29 11:37:34,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +18: [2023-04-29 11:37:34,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +18: [2023-04-29 11:37:34,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +18: [2023-04-29 11:37:34,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +18: [2023-04-29 11:37:34,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +23: [2023-04-29 11:37:34,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +23: [2023-04-29 11:37:34,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +46: [2023-04-29 11:37:34,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +19: [2023-04-29 11:37:34,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +19: [2023-04-29 11:37:34,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +32: [2023-04-29 11:37:34,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +12: [2023-04-29 11:37:34,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. + 7: [2023-04-29 11:37:34,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. + 7: [2023-04-29 11:37:34,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. + 2: [2023-04-29 11:37:34,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 3: [2023-04-29 11:37:34,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 7: [2023-04-29 11:37:34,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +32: [2023-04-29 11:37:34,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +12: [2023-04-29 11:37:34,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. + 4: [2023-04-29 11:37:34,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +31: [2023-04-29 11:37:34,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +31: [2023-04-29 11:37:34,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +31: [2023-04-29 11:37:34,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +31: [2023-04-29 11:37:34,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +12: [2023-04-29 11:37:34,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +12: [2023-04-29 11:37:34,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +23: [2023-04-29 11:37:34,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +31: [2023-04-29 11:37:34,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 3: [2023-04-29 11:37:34,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +32: [2023-04-29 11:37:34,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +49: [2023-04-29 11:37:34,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +62: [2023-04-29 11:37:34,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +62: [2023-04-29 11:37:34,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +31: [2023-04-29 11:37:34,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +62: [2023-04-29 11:37:34,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +16: [2023-04-29 11:37:34,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +16: [2023-04-29 11:37:34,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +54: [2023-04-29 11:37:34,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +49: [2023-04-29 11:37:34,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +54: [2023-04-29 11:37:34,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +54: [2023-04-29 11:37:34,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +31: [2023-04-29 11:37:34,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +54: [2023-04-29 11:37:34,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +14: [2023-04-29 11:37:34,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +16: [2023-04-29 11:37:34,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +54: [2023-04-29 11:37:34,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +29: [2023-04-29 11:37:34,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +47: [2023-04-29 11:37:34,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +33: [2023-04-29 11:37:34,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +33: [2023-04-29 11:37:34,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +31: [2023-04-29 11:37:34,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +54: [2023-04-29 11:37:34,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +54: [2023-04-29 11:37:34,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +47: [2023-04-29 11:37:34,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 2: [2023-04-29 11:37:34,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +16: [2023-04-29 11:37:34,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +54: [2023-04-29 11:37:34,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +31: [2023-04-29 11:37:34,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +54: [2023-04-29 11:37:34,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +54: [2023-04-29 11:37:34,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +48: [2023-04-29 11:37:34,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +48: [2023-04-29 11:37:34,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +48: [2023-04-29 11:37:34,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +26: [2023-04-29 11:37:34,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +48: [2023-04-29 11:37:34,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +31: [2023-04-29 11:37:34,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +49: [2023-04-29 11:37:34,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +54: [2023-04-29 11:37:34,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +54: [2023-04-29 11:37:34,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +32: [2023-04-29 11:37:34,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +32: [2023-04-29 11:37:34,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +46: [2023-04-29 11:37:34,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +12: [2023-04-29 11:37:34,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +33: [2023-04-29 11:37:34,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +24: [2023-04-29 11:37:34,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +24: [2023-04-29 11:37:34,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +35: [2023-04-29 11:37:34,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +32: [2023-04-29 11:37:34,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +41: [2023-04-29 11:37:34,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +41: [2023-04-29 11:37:34,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +41: [2023-04-29 11:37:34,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 5: [2023-04-29 11:37:34,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +36: [2023-04-29 11:37:34,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +41: [2023-04-29 11:37:34,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +35: [2023-04-29 11:37:34,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +36: [2023-04-29 11:37:34,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +36: [2023-04-29 11:37:34,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +10: [2023-04-29 11:37:34,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +36: [2023-04-29 11:37:34,272] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +26: [2023-04-29 11:37:34,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +49: [2023-04-29 11:37:34,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... + 5: [2023-04-29 11:37:34,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +21: [2023-04-29 11:37:34,272] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +35: [2023-04-29 11:37:34,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +47: [2023-04-29 11:37:34,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +47: [2023-04-29 11:37:34,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +33: [2023-04-29 11:37:34,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +29: [2023-04-29 11:37:34,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... + 2: [2023-04-29 11:37:34,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +24: [2023-04-29 11:37:34,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +12: [2023-04-29 11:37:34,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +28: [2023-04-29 11:37:34,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +24: [2023-04-29 11:37:34,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +49: [2023-04-29 11:37:34,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +33: [2023-04-29 11:37:34,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +33: [2023-04-29 11:37:34,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +33: [2023-04-29 11:37:34,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +46: [2023-04-29 11:37:34,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +35: [2023-04-29 11:37:34,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +46: [2023-04-29 11:37:34,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +35: [2023-04-29 11:37:34,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +33: [2023-04-29 11:37:34,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. + 4: [2023-04-29 11:37:34,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +33: [2023-04-29 11:37:34,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +62: [2023-04-29 11:37:34,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +62: [2023-04-29 11:37:34,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +62: [2023-04-29 11:37:34,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +33: [2023-04-29 11:37:34,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +33: [2023-04-29 11:37:34,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +35: [2023-04-29 11:37:34,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +35: [2023-04-29 11:37:34,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +35: [2023-04-29 11:37:34,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +35: [2023-04-29 11:37:34,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +46: [2023-04-29 11:37:34,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +33: [2023-04-29 11:37:34,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +33: [2023-04-29 11:37:34,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +33: [2023-04-29 11:37:34,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +33: [2023-04-29 11:37:34,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +33: [2023-04-29 11:37:34,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 5: [2023-04-29 11:37:34,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +15: [2023-04-29 11:37:34,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +15: [2023-04-29 11:37:34,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. + 5: [2023-04-29 11:37:34,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +33: [2023-04-29 11:37:34,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +14: [2023-04-29 11:37:34,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +33: [2023-04-29 11:37:34,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +33: [2023-04-29 11:37:34,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +33: [2023-04-29 11:37:34,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +28: [2023-04-29 11:37:34,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 4: [2023-04-29 11:37:34,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 4: [2023-04-29 11:37:34,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +15: [2023-04-29 11:37:34,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +62: [2023-04-29 11:37:34,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +46: [2023-04-29 11:37:34,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +46: [2023-04-29 11:37:34,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +29: [2023-04-29 11:37:34,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 5: [2023-04-29 11:37:34,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +15: [2023-04-29 11:37:34,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +58: [2023-04-29 11:37:34,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +58: [2023-04-29 11:37:34,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 5: [2023-04-29 11:37:34,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. + 5: [2023-04-29 11:37:34,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +49: [2023-04-29 11:37:34,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +54: [2023-04-29 11:37:34,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +54: [2023-04-29 11:37:34,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +54: [2023-04-29 11:37:34,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +54: [2023-04-29 11:37:34,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +34: [2023-04-29 11:37:34,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +34: [2023-04-29 11:37:34,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +41: [2023-04-29 11:37:34,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +41: [2023-04-29 11:37:34,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 5: [2023-04-29 11:37:34,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +34: [2023-04-29 11:37:34,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +10: [2023-04-29 11:37:34,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +34: [2023-04-29 11:37:34,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +10: [2023-04-29 11:37:34,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +32: [2023-04-29 11:37:34,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +10: [2023-04-29 11:37:34,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +29: [2023-04-29 11:37:34,278] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +32: [2023-04-29 11:37:34,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +32: [2023-04-29 11:37:34,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +32: [2023-04-29 11:37:34,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +14: [2023-04-29 11:37:34,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +41: [2023-04-29 11:37:34,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 2: [2023-04-29 11:37:34,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +41: [2023-04-29 11:37:34,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +26: [2023-04-29 11:37:34,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +14: [2023-04-29 11:37:34,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +58: [2023-04-29 11:37:34,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +49: [2023-04-29 11:37:34,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +26: [2023-04-29 11:37:34,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +28: [2023-04-29 11:37:34,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +28: [2023-04-29 11:37:34,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +29: [2023-04-29 11:37:34,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +19: [2023-04-29 11:37:34,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +19: [2023-04-29 11:37:34,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +12: [2023-04-29 11:37:34,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +14: [2023-04-29 11:37:34,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +29: [2023-04-29 11:37:34,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +22: [2023-04-29 11:37:34,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +21: [2023-04-29 11:37:34,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +21: [2023-04-29 11:37:34,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +28: [2023-04-29 11:37:34,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +28: [2023-04-29 11:37:34,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +21: [2023-04-29 11:37:34,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +34: [2023-04-29 11:37:34,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +34: [2023-04-29 11:37:34,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +28: [2023-04-29 11:37:34,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +18: [2023-04-29 11:37:34,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +58: [2023-04-29 11:37:34,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +58: [2023-04-29 11:37:34,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... + 3: [2023-04-29 11:37:34,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +28: [2023-04-29 11:37:34,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +34: [2023-04-29 11:37:34,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +62: [2023-04-29 11:37:34,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +18: [2023-04-29 11:37:34,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +35: [2023-04-29 11:37:34,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +35: [2023-04-29 11:37:34,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +29: [2023-04-29 11:37:34,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +27: [2023-04-29 11:37:34,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +27: [2023-04-29 11:37:34,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +27: [2023-04-29 11:37:34,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +27: [2023-04-29 11:37:34,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +34: [2023-04-29 11:37:34,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +35: [2023-04-29 11:37:34,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +58: [2023-04-29 11:37:34,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +12: [2023-04-29 11:37:34,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +22: [2023-04-29 11:37:34,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +19: [2023-04-29 11:37:34,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +22: [2023-04-29 11:37:34,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +10: [2023-04-29 11:37:34,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 3: [2023-04-29 11:37:34,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 3: [2023-04-29 11:37:34,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +29: [2023-04-29 11:37:34,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +58: [2023-04-29 11:37:34,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... + 2: [2023-04-29 11:37:34,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +22: [2023-04-29 11:37:34,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +63: [2023-04-29 11:37:34,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +63: [2023-04-29 11:37:34,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +14: [2023-04-29 11:37:34,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +63: [2023-04-29 11:37:34,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +63: [2023-04-29 11:37:34,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. + 7: [2023-04-29 11:37:34,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +44: [2023-04-29 11:37:34,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_51_mp_rank_02_optim_states.pt. +44: [2023-04-29 11:37:34,290] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 358 +46: [2023-04-29 11:37:34,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 3: [2023-04-29 11:37:34,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 3: [2023-04-29 11:37:34,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +46: [2023-04-29 11:37:34,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +12: [2023-04-29 11:37:34,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +46: [2023-04-29 11:37:34,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +10: [2023-04-29 11:37:34,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +46: [2023-04-29 11:37:34,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +32: [2023-04-29 11:37:34,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +58: [2023-04-29 11:37:34,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +16: [2023-04-29 11:37:34,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +19: [2023-04-29 11:37:34,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +32: [2023-04-29 11:37:34,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +32: [2023-04-29 11:37:34,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +32: [2023-04-29 11:37:34,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. + 3: [2023-04-29 11:37:34,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +18: [2023-04-29 11:37:34,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +18: [2023-04-29 11:37:34,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 3: [2023-04-29 11:37:34,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 2: [2023-04-29 11:37:34,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +12: [2023-04-29 11:37:34,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +59: [2023-04-29 11:37:34,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +59: [2023-04-29 11:37:34,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +59: [2023-04-29 11:37:34,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +59: [2023-04-29 11:37:34,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +16: [2023-04-29 11:37:34,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +22: [2023-04-29 11:37:34,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +22: [2023-04-29 11:37:34,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +33: [2023-04-29 11:37:34,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +21: [2023-04-29 11:37:34,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +36: [2023-04-29 11:37:34,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +12: [2023-04-29 11:37:34,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 1: [2023-04-29 11:37:34,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 1: [2023-04-29 11:37:34,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 1: [2023-04-29 11:37:34,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 1: [2023-04-29 11:37:34,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +32: [2023-04-29 11:37:34,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +24: [2023-04-29 11:37:34,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +36: [2023-04-29 11:37:34,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +16: [2023-04-29 11:37:34,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +32: [2023-04-29 11:37:34,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +32: [2023-04-29 11:37:34,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +32: [2023-04-29 11:37:34,301] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +24: [2023-04-29 11:37:34,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +15: [2023-04-29 11:37:34,301] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +59: [2023-04-29 11:37:34,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +59: [2023-04-29 11:37:34,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +14: [2023-04-29 11:37:34,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +24: [2023-04-29 11:37:34,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +59: [2023-04-29 11:37:34,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 2: [2023-04-29 11:37:34,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +24: [2023-04-29 11:37:34,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +59: [2023-04-29 11:37:34,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +16: [2023-04-29 11:37:34,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +33: [2023-04-29 11:37:34,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +36: [2023-04-29 11:37:34,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +36: [2023-04-29 11:37:34,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +48: [2023-04-29 11:37:34,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +33: [2023-04-29 11:37:34,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +48: [2023-04-29 11:37:34,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +22: [2023-04-29 11:37:34,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +33: [2023-04-29 11:37:34,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 5: [2023-04-29 11:37:34,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +10: [2023-04-29 11:37:34,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 0: [2023-04-29 11:37:34,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 0: [2023-04-29 11:37:34,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 0: [2023-04-29 11:37:34,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +15: [2023-04-29 11:37:34,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +15: [2023-04-29 11:37:34,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +46: [2023-04-29 11:37:34,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 0: [2023-04-29 11:37:34,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +46: [2023-04-29 11:37:34,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +14: [2023-04-29 11:37:34,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +15: [2023-04-29 11:37:34,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +46: [2023-04-29 11:37:34,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +46: [2023-04-29 11:37:34,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +46: [2023-04-29 11:37:34,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +46: [2023-04-29 11:37:34,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 5: [2023-04-29 11:37:34,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +14: [2023-04-29 11:37:34,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +14: [2023-04-29 11:37:34,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +48: [2023-04-29 11:37:34,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +46: [2023-04-29 11:37:34,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +46: [2023-04-29 11:37:34,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +14: [2023-04-29 11:37:34,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +48: [2023-04-29 11:37:34,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 5: [2023-04-29 11:37:34,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 5: [2023-04-29 11:37:34,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +45: [2023-04-29 11:37:34,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +15: [2023-04-29 11:37:34,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +15: [2023-04-29 11:37:34,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +15: [2023-04-29 11:37:34,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +15: [2023-04-29 11:37:34,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 2: [2023-04-29 11:37:34,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +10: [2023-04-29 11:37:34,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +45: [2023-04-29 11:37:34,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +45: [2023-04-29 11:37:34,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 0: [2023-04-29 11:37:34,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +21: [2023-04-29 11:37:34,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +21: [2023-04-29 11:37:34,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 0: [2023-04-29 11:37:34,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +21: [2023-04-29 11:37:34,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +32: [2023-04-29 11:37:34,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +63: [2023-04-29 11:37:34,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 0: [2023-04-29 11:37:34,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 0: [2023-04-29 11:37:34,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +54: [2023-04-29 11:37:34,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_91_mp_rank_02_optim_states.pt. +54: [2023-04-29 11:37:34,313] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 438 +14: [2023-04-29 11:37:34,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +42: [2023-04-29 11:37:34,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +42: [2023-04-29 11:37:34,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +42: [2023-04-29 11:37:34,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +42: [2023-04-29 11:37:34,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +27: [2023-04-29 11:37:34,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +27: [2023-04-29 11:37:34,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +14: [2023-04-29 11:37:34,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +14: [2023-04-29 11:37:34,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 8: [2023-04-29 11:37:34,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 8: [2023-04-29 11:37:34,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 8: [2023-04-29 11:37:34,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +14: [2023-04-29 11:37:34,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 8: [2023-04-29 11:37:34,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +10: [2023-04-29 11:37:34,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +32: [2023-04-29 11:37:34,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +63: [2023-04-29 11:37:34,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +61: [2023-04-29 11:37:34,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +61: [2023-04-29 11:37:34,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +61: [2023-04-29 11:37:34,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +63: [2023-04-29 11:37:34,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +61: [2023-04-29 11:37:34,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 2: [2023-04-29 11:37:34,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +46: [2023-04-29 11:37:34,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +46: [2023-04-29 11:37:34,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +63: [2023-04-29 11:37:34,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +27: [2023-04-29 11:37:34,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +17: [2023-04-29 11:37:34,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +17: [2023-04-29 11:37:34,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +17: [2023-04-29 11:37:34,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +27: [2023-04-29 11:37:34,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 8: [2023-04-29 11:37:34,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 8: [2023-04-29 11:37:34,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +63: [2023-04-29 11:37:34,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +45: [2023-04-29 11:37:34,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +10: [2023-04-29 11:37:34,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +17: [2023-04-29 11:37:34,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 8: [2023-04-29 11:37:34,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +46: [2023-04-29 11:37:34,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_58_mp_rank_02_optim_states.pt... +46: [2023-04-29 11:37:34,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_56_mp_rank_02_optim_states.pt... +46: [2023-04-29 11:37:34,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_59_mp_rank_02_optim_states.pt... +46: [2023-04-29 11:37:34,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_57_mp_rank_02_optim_states.pt... +61: [2023-04-29 11:37:34,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 8: [2023-04-29 11:37:34,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 2: [2023-04-29 11:37:34,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +61: [2023-04-29 11:37:34,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +46: [2023-04-29 11:37:34,326] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +10: [2023-04-29 11:37:34,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +46: [2023-04-29 11:37:34,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +46: [2023-04-29 11:37:34,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +32: [2023-04-29 11:37:34,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +63: [2023-04-29 11:37:34,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +31: [2023-04-29 11:37:34,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +61: [2023-04-29 11:37:34,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 1: [2023-04-29 11:37:34,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +32: [2023-04-29 11:37:34,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_2_mp_rank_02_optim_states.pt... +32: [2023-04-29 11:37:34,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_3_mp_rank_02_optim_states.pt... +32: [2023-04-29 11:37:34,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_0_mp_rank_02_optim_states.pt... +32: [2023-04-29 11:37:34,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_1_mp_rank_02_optim_states.pt... +61: [2023-04-29 11:37:34,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +22: [2023-04-29 11:37:34,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +22: [2023-04-29 11:37:34,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +47: [2023-04-29 11:37:34,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 1: [2023-04-29 11:37:34,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +22: [2023-04-29 11:37:34,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 1: [2023-04-29 11:37:34,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +45: [2023-04-29 11:37:34,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +45: [2023-04-29 11:37:34,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +45: [2023-04-29 11:37:34,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +45: [2023-04-29 11:37:34,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +35: [2023-04-29 11:37:34,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +46: [2023-04-29 11:37:34,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +44: [2023-04-29 11:37:34,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_49_mp_rank_02_optim_states.pt. +44: [2023-04-29 11:37:34,333] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 354 + 1: [2023-04-29 11:37:34,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +10: [2023-04-29 11:37:34,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +32: [2023-04-29 11:37:34,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... + 1: [2023-04-29 11:37:34,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 1: [2023-04-29 11:37:34,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 1: [2023-04-29 11:37:34,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +47: [2023-04-29 11:37:34,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +22: [2023-04-29 11:37:34,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 1: [2023-04-29 11:37:34,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +63: [2023-04-29 11:37:34,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +63: [2023-04-29 11:37:34,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +63: [2023-04-29 11:37:34,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +15: [2023-04-29 11:37:34,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +33: [2023-04-29 11:37:34,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_4_mp_rank_02_optim_states.pt... +33: [2023-04-29 11:37:34,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_6_mp_rank_02_optim_states.pt... +33: [2023-04-29 11:37:34,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_7_mp_rank_02_optim_states.pt... +41: [2023-04-29 11:37:34,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +45: [2023-04-29 11:37:34,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +47: [2023-04-29 11:37:34,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +32: [2023-04-29 11:37:34,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +32: [2023-04-29 11:37:34,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +15: [2023-04-29 11:37:34,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 1: [2023-04-29 11:37:34,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +63: [2023-04-29 11:37:34,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +63: [2023-04-29 11:37:34,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +57: [2023-04-29 11:37:34,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +57: [2023-04-29 11:37:34,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +57: [2023-04-29 11:37:34,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. + 1: [2023-04-29 11:37:34,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +15: [2023-04-29 11:37:34,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +63: [2023-04-29 11:37:34,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +15: [2023-04-29 11:37:34,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +42: [2023-04-29 11:37:34,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +45: [2023-04-29 11:37:34,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +45: [2023-04-29 11:37:34,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +35: [2023-04-29 11:37:34,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +57: [2023-04-29 11:37:34,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +31: [2023-04-29 11:37:34,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +31: [2023-04-29 11:37:34,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 6: [2023-04-29 11:37:34,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 6: [2023-04-29 11:37:34,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +31: [2023-04-29 11:37:34,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 1: [2023-04-29 11:37:34,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 6: [2023-04-29 11:37:34,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 1: [2023-04-29 11:37:34,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +47: [2023-04-29 11:37:34,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... + 6: [2023-04-29 11:37:34,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +28: [2023-04-29 11:37:34,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +50: [2023-04-29 11:37:34,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_74_mp_rank_02_optim_states.pt. +45: [2023-04-29 11:37:34,345] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +18: [2023-04-29 11:37:34,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +45: [2023-04-29 11:37:34,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +45: [2023-04-29 11:37:34,345] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +45: [2023-04-29 11:37:34,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +41: [2023-04-29 11:37:34,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +35: [2023-04-29 11:37:34,345] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +50: [2023-04-29 11:37:34,344] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 404 +45: [2023-04-29 11:37:34,345] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +45: [2023-04-29 11:37:34,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +32: [2023-04-29 11:37:34,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +45: [2023-04-29 11:37:34,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +46: [2023-04-29 11:37:34,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +45: [2023-04-29 11:37:34,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +45: [2023-04-29 11:37:34,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +32: [2023-04-29 11:37:34,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +35: [2023-04-29 11:37:34,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +34: [2023-04-29 11:37:34,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +34: [2023-04-29 11:37:34,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +24: [2023-04-29 11:37:34,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +24: [2023-04-29 11:37:34,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +41: [2023-04-29 11:37:34,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +41: [2023-04-29 11:37:34,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +47: [2023-04-29 11:37:34,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +47: [2023-04-29 11:37:34,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +18: [2023-04-29 11:37:34,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +44: [2023-04-29 11:37:34,349] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_48_mp_rank_02_optim_states.pt. +54: [2023-04-29 11:37:34,349] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_89_mp_rank_02_optim_states.pt. +44: [2023-04-29 11:37:34,350] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 352 +54: [2023-04-29 11:37:34,350] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 434 +18: [2023-04-29 11:37:34,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +28: [2023-04-29 11:37:34,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +42: [2023-04-29 11:37:34,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +42: [2023-04-29 11:37:34,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +24: [2023-04-29 11:37:34,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +39: [2023-04-29 11:37:34,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +39: [2023-04-29 11:37:34,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +39: [2023-04-29 11:37:34,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +17: [2023-04-29 11:37:34,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +28: [2023-04-29 11:37:34,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +35: [2023-04-29 11:37:34,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +24: [2023-04-29 11:37:34,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +28: [2023-04-29 11:37:34,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 7: [2023-04-29 11:37:34,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +41: [2023-04-29 11:37:34,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +12: [2023-04-29 11:37:34,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +41: [2023-04-29 11:37:34,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +22: [2023-04-29 11:37:34,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +24: [2023-04-29 11:37:34,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +39: [2023-04-29 11:37:34,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +24: [2023-04-29 11:37:34,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +46: [2023-04-29 11:37:34,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +60: [2023-04-29 11:37:34,354] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +60: [2023-04-29 11:37:34,354] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +47: [2023-04-29 11:37:34,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +47: [2023-04-29 11:37:34,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +17: [2023-04-29 11:37:34,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +21: [2023-04-29 11:37:34,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +18: [2023-04-29 11:37:34,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +42: [2023-04-29 11:37:34,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +21: [2023-04-29 11:37:34,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +21: [2023-04-29 11:37:34,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +17: [2023-04-29 11:37:34,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +21: [2023-04-29 11:37:34,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +24: [2023-04-29 11:37:34,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +34: [2023-04-29 11:37:34,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 3: [2023-04-29 11:37:34,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 3: [2023-04-29 11:37:34,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +35: [2023-04-29 11:37:34,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +28: [2023-04-29 11:37:34,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +39: [2023-04-29 11:37:34,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +12: [2023-04-29 11:37:34,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... + 7: [2023-04-29 11:37:34,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +31: [2023-04-29 11:37:34,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +28: [2023-04-29 11:37:34,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +50: [2023-04-29 11:37:34,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_72_mp_rank_02_optim_states.pt. +50: [2023-04-29 11:37:34,358] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 400 +39: [2023-04-29 11:37:34,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +41: [2023-04-29 11:37:34,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +28: [2023-04-29 11:37:34,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +60: [2023-04-29 11:37:34,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +39: [2023-04-29 11:37:34,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +60: [2023-04-29 11:37:34,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +17: [2023-04-29 11:37:34,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +60: [2023-04-29 11:37:34,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +24: [2023-04-29 11:37:34,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +63: [2023-04-29 11:37:34,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +63: [2023-04-29 11:37:34,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +63: [2023-04-29 11:37:34,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +22: [2023-04-29 11:37:34,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +12: [2023-04-29 11:37:34,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +35: [2023-04-29 11:37:34,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +35: [2023-04-29 11:37:34,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +63: [2023-04-29 11:37:34,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +45: [2023-04-29 11:37:34,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +56: [2023-04-29 11:37:34,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +56: [2023-04-29 11:37:34,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +56: [2023-04-29 11:37:34,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +51: [2023-04-29 11:37:34,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +51: [2023-04-29 11:37:34,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +60: [2023-04-29 11:37:34,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +39: [2023-04-29 11:37:34,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +51: [2023-04-29 11:37:34,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +56: [2023-04-29 11:37:34,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +45: [2023-04-29 11:37:34,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +41: [2023-04-29 11:37:34,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +35: [2023-04-29 11:37:34,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +22: [2023-04-29 11:37:34,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +28: [2023-04-29 11:37:34,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +45: [2023-04-29 11:37:34,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +45: [2023-04-29 11:37:34,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +45: [2023-04-29 11:37:34,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +16: [2023-04-29 11:37:34,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +34: [2023-04-29 11:37:34,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 3: [2023-04-29 11:37:34,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 3: [2023-04-29 11:37:34,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... + 3: [2023-04-29 11:37:34,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +35: [2023-04-29 11:37:34,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +45: [2023-04-29 11:37:34,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +51: [2023-04-29 11:37:34,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +18: [2023-04-29 11:37:34,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +18: [2023-04-29 11:37:34,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +45: [2023-04-29 11:37:34,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +45: [2023-04-29 11:37:34,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 3: [2023-04-29 11:37:34,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 7: [2023-04-29 11:37:34,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +12: [2023-04-29 11:37:34,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +18: [2023-04-29 11:37:34,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +18: [2023-04-29 11:37:34,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +57: [2023-04-29 11:37:34,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +60: [2023-04-29 11:37:34,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +56: [2023-04-29 11:37:34,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +16: [2023-04-29 11:37:34,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +59: [2023-04-29 11:37:34,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +59: [2023-04-29 11:37:34,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +59: [2023-04-29 11:37:34,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. + 6: [2023-04-29 11:37:34,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +59: [2023-04-29 11:37:34,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. + 7: [2023-04-29 11:37:34,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +12: [2023-04-29 11:37:34,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +56: [2023-04-29 11:37:34,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +56: [2023-04-29 11:37:34,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +56: [2023-04-29 11:37:34,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +35: [2023-04-29 11:37:34,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +57: [2023-04-29 11:37:34,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +63: [2023-04-29 11:37:34,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +18: [2023-04-29 11:37:34,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +63: [2023-04-29 11:37:34,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +18: [2023-04-29 11:37:34,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +60: [2023-04-29 11:37:34,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +63: [2023-04-29 11:37:34,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +63: [2023-04-29 11:37:34,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +63: [2023-04-29 11:37:34,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +63: [2023-04-29 11:37:34,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +63: [2023-04-29 11:37:34,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +63: [2023-04-29 11:37:34,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +57: [2023-04-29 11:37:34,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +24: [2023-04-29 11:37:34,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 3: [2023-04-29 11:37:34,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +22: [2023-04-29 11:37:34,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +22: [2023-04-29 11:37:34,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +51: [2023-04-29 11:37:34,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +35: [2023-04-29 11:37:34,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +35: [2023-04-29 11:37:34,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 0: [2023-04-29 11:37:34,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 3: [2023-04-29 11:37:34,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +51: [2023-04-29 11:37:34,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +35: [2023-04-29 11:37:34,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +35: [2023-04-29 11:37:34,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +51: [2023-04-29 11:37:34,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +57: [2023-04-29 11:37:34,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +16: [2023-04-29 11:37:34,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +18: [2023-04-29 11:37:34,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +41: [2023-04-29 11:37:34,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +31: [2023-04-29 11:37:34,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +16: [2023-04-29 11:37:34,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +12: [2023-04-29 11:37:34,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +12: [2023-04-29 11:37:34,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... + 6: [2023-04-29 11:37:34,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +51: [2023-04-29 11:37:34,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +34: [2023-04-29 11:37:34,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +34: [2023-04-29 11:37:34,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +41: [2023-04-29 11:37:34,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +18: [2023-04-29 11:37:34,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +18: [2023-04-29 11:37:34,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +31: [2023-04-29 11:37:34,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +59: [2023-04-29 11:37:34,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +24: [2023-04-29 11:37:34,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +34: [2023-04-29 11:37:34,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +34: [2023-04-29 11:37:34,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +31: [2023-04-29 11:37:34,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +54: [2023-04-29 11:37:34,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_89_mp_rank_03_optim_states.pt... +54: [2023-04-29 11:37:34,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_90_mp_rank_03_optim_states.pt... +54: [2023-04-29 11:37:34,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_88_mp_rank_03_optim_states.pt... +54: [2023-04-29 11:37:34,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_91_mp_rank_03_optim_states.pt... +18: [2023-04-29 11:37:34,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +54: [2023-04-29 11:37:34,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_90_mp_rank_02_optim_states.pt. +54: [2023-04-29 11:37:34,376] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 436 +35: [2023-04-29 11:37:34,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... + 5: [2023-04-29 11:37:34,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +18: [2023-04-29 11:37:34,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +16: [2023-04-29 11:37:34,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +22: [2023-04-29 11:37:34,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +22: [2023-04-29 11:37:34,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +22: [2023-04-29 11:37:34,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... + 6: [2023-04-29 11:37:34,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 6: [2023-04-29 11:37:34,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +60: [2023-04-29 11:37:34,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +60: [2023-04-29 11:37:34,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +24: [2023-04-29 11:37:34,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 5: [2023-04-29 11:37:34,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 5: [2023-04-29 11:37:34,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +29: [2023-04-29 11:37:34,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +29: [2023-04-29 11:37:34,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +29: [2023-04-29 11:37:34,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +18: [2023-04-29 11:37:34,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +29: [2023-04-29 11:37:34,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +12: [2023-04-29 11:37:34,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +34: [2023-04-29 11:37:34,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +41: [2023-04-29 11:37:34,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +34: [2023-04-29 11:37:34,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +33: [2023-04-29 11:37:34,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_5_mp_rank_02_optim_states.pt... +33: [2023-04-29 11:37:34,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +33: [2023-04-29 11:37:34,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +41: [2023-04-29 11:37:34,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +33: [2023-04-29 11:37:34,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +33: [2023-04-29 11:37:34,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +33: [2023-04-29 11:37:34,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +34: [2023-04-29 11:37:34,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +34: [2023-04-29 11:37:34,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +34: [2023-04-29 11:37:34,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +15: [2023-04-29 11:37:34,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +43: [2023-04-29 11:37:34,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +43: [2023-04-29 11:37:34,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +34: [2023-04-29 11:37:34,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. + 5: [2023-04-29 11:37:34,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +16: [2023-04-29 11:37:34,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 9: [2023-04-29 11:37:34,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. + 9: [2023-04-29 11:37:34,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +59: [2023-04-29 11:37:34,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +19: [2023-04-29 11:37:34,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +19: [2023-04-29 11:37:34,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +24: [2023-04-29 11:37:34,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +21: [2023-04-29 11:37:34,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +24: [2023-04-29 11:37:34,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. + 9: [2023-04-29 11:37:34,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. + 9: [2023-04-29 11:37:34,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_16-model_01-model_states.pt. +59: [2023-04-29 11:37:34,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +48: [2023-04-29 11:37:34,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +22: [2023-04-29 11:37:34,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... + 5: [2023-04-29 11:37:34,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +27: [2023-04-29 11:37:34,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +29: [2023-04-29 11:37:34,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +34: [2023-04-29 11:37:34,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +60: [2023-04-29 11:37:34,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. + 0: [2023-04-29 11:37:34,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 0: [2023-04-29 11:37:34,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +34: [2023-04-29 11:37:34,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +29: [2023-04-29 11:37:34,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +29: [2023-04-29 11:37:34,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +60: [2023-04-29 11:37:34,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +16: [2023-04-29 11:37:34,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... + 8: [2023-04-29 11:37:34,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +29: [2023-04-29 11:37:34,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 5: [2023-04-29 11:37:34,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... + 5: [2023-04-29 11:37:34,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +24: [2023-04-29 11:37:34,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +43: [2023-04-29 11:37:34,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +41: [2023-04-29 11:37:34,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +19: [2023-04-29 11:37:34,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +41: [2023-04-29 11:37:34,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +19: [2023-04-29 11:37:34,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +43: [2023-04-29 11:37:34,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +63: [2023-04-29 11:37:34,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_125_mp_rank_02_optim_states.pt... +41: [2023-04-29 11:37:34,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +63: [2023-04-29 11:37:34,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_127_mp_rank_02_optim_states.pt... +63: [2023-04-29 11:37:34,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_124_mp_rank_02_optim_states.pt... +63: [2023-04-29 11:37:34,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_126_mp_rank_02_optim_states.pt... +41: [2023-04-29 11:37:34,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +48: [2023-04-29 11:37:34,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +48: [2023-04-29 11:37:34,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +41: [2023-04-29 11:37:34,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 5: [2023-04-29 11:37:34,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +43: [2023-04-29 11:37:34,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 0: [2023-04-29 11:37:34,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +27: [2023-04-29 11:37:34,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +41: [2023-04-29 11:37:34,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +59: [2023-04-29 11:37:34,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +43: [2023-04-29 11:37:34,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 6: [2023-04-29 11:37:34,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 6: [2023-04-29 11:37:34,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +15: [2023-04-29 11:37:34,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +16: [2023-04-29 11:37:34,389] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +24: [2023-04-29 11:37:34,389] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... + 6: [2023-04-29 11:37:34,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 6: [2023-04-29 11:37:34,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +40: [2023-04-29 11:37:34,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_34_mp_rank_02_optim_states.pt. +24: [2023-04-29 11:37:34,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +40: [2023-04-29 11:37:34,390] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 324 +21: [2023-04-29 11:37:34,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +27: [2023-04-29 11:37:34,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +41: [2023-04-29 11:37:34,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +21: [2023-04-29 11:37:34,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +48: [2023-04-29 11:37:34,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +15: [2023-04-29 11:37:34,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... + 8: [2023-04-29 11:37:34,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +43: [2023-04-29 11:37:34,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +42: [2023-04-29 11:37:34,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +42: [2023-04-29 11:37:34,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +42: [2023-04-29 11:37:34,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +59: [2023-04-29 11:37:34,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +41: [2023-04-29 11:37:34,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +61: [2023-04-29 11:37:34,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +61: [2023-04-29 11:37:34,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +38: [2023-04-29 11:37:34,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +38: [2023-04-29 11:37:34,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +42: [2023-04-29 11:37:34,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +43: [2023-04-29 11:37:34,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +34: [2023-04-29 11:37:34,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +27: [2023-04-29 11:37:34,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +21: [2023-04-29 11:37:34,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +48: [2023-04-29 11:37:34,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +34: [2023-04-29 11:37:34,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +27: [2023-04-29 11:37:34,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +48: [2023-04-29 11:37:34,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +34: [2023-04-29 11:37:34,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 6: [2023-04-29 11:37:34,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 6: [2023-04-29 11:37:34,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +61: [2023-04-29 11:37:34,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +61: [2023-04-29 11:37:34,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +48: [2023-04-29 11:37:34,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +34: [2023-04-29 11:37:34,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +59: [2023-04-29 11:37:34,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +38: [2023-04-29 11:37:34,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +52: [2023-04-29 11:37:34,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +52: [2023-04-29 11:37:34,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +52: [2023-04-29 11:37:34,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +38: [2023-04-29 11:37:34,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. + 6: [2023-04-29 11:37:34,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 6: [2023-04-29 11:37:34,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +40: [2023-04-29 11:37:34,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +40: [2023-04-29 11:37:34,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +40: [2023-04-29 11:37:34,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +52: [2023-04-29 11:37:34,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +40: [2023-04-29 11:37:34,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. + 8: [2023-04-29 11:37:34,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 8: [2023-04-29 11:37:34,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +27: [2023-04-29 11:37:34,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +41: [2023-04-29 11:37:34,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +59: [2023-04-29 11:37:34,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +41: [2023-04-29 11:37:34,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +41: [2023-04-29 11:37:34,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +45: [2023-04-29 11:37:34,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_52_mp_rank_02_optim_states.pt... +45: [2023-04-29 11:37:34,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_54_mp_rank_02_optim_states.pt... +45: [2023-04-29 11:37:34,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_53_mp_rank_02_optim_states.pt... +45: [2023-04-29 11:37:34,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_55_mp_rank_02_optim_states.pt... +41: [2023-04-29 11:37:34,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +15: [2023-04-29 11:37:34,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +15: [2023-04-29 11:37:34,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +15: [2023-04-29 11:37:34,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +61: [2023-04-29 11:37:34,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +61: [2023-04-29 11:37:34,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. + 0: [2023-04-29 11:37:34,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +61: [2023-04-29 11:37:34,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +42: [2023-04-29 11:37:34,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +42: [2023-04-29 11:37:34,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +34: [2023-04-29 11:37:34,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +42: [2023-04-29 11:37:34,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +34: [2023-04-29 11:37:34,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +34: [2023-04-29 11:37:34,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +34: [2023-04-29 11:37:34,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +27: [2023-04-29 11:37:34,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 1: [2023-04-29 11:37:34,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +48: [2023-04-29 11:37:34,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +57: [2023-04-29 11:37:34,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +57: [2023-04-29 11:37:34,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +41: [2023-04-29 11:37:34,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 1: [2023-04-29 11:37:34,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +42: [2023-04-29 11:37:34,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +59: [2023-04-29 11:37:34,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 1: [2023-04-29 11:37:34,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +41: [2023-04-29 11:37:34,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +41: [2023-04-29 11:37:34,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +41: [2023-04-29 11:37:34,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +27: [2023-04-29 11:37:34,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +15: [2023-04-29 11:37:34,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +63: [2023-04-29 11:37:34,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +57: [2023-04-29 11:37:34,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +57: [2023-04-29 11:37:34,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +11: [2023-04-29 11:37:34,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +11: [2023-04-29 11:37:34,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +15: [2023-04-29 11:37:34,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +11: [2023-04-29 11:37:34,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +37: [2023-04-29 11:37:34,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_20_mp_rank_02_optim_states.pt. +36: [2023-04-29 11:37:34,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +36: [2023-04-29 11:37:34,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +11: [2023-04-29 11:37:34,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +37: [2023-04-29 11:37:34,404] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 296 +34: [2023-04-29 11:37:34,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +34: [2023-04-29 11:37:34,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +61: [2023-04-29 11:37:34,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +35: [2023-04-29 11:37:34,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +35: [2023-04-29 11:37:34,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +35: [2023-04-29 11:37:34,405] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +35: [2023-04-29 11:37:34,405] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +35: [2023-04-29 11:37:34,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +35: [2023-04-29 11:37:34,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +60: [2023-04-29 11:37:34,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +35: [2023-04-29 11:37:34,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +35: [2023-04-29 11:37:34,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +35: [2023-04-29 11:37:34,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +35: [2023-04-29 11:37:34,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +36: [2023-04-29 11:37:34,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +35: [2023-04-29 11:37:34,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +36: [2023-04-29 11:37:34,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +57: [2023-04-29 11:37:34,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +36: [2023-04-29 11:37:34,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +36: [2023-04-29 11:37:34,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +35: [2023-04-29 11:37:34,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +36: [2023-04-29 11:37:34,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +57: [2023-04-29 11:37:34,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +36: [2023-04-29 11:37:34,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 1: [2023-04-29 11:37:34,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +42: [2023-04-29 11:37:34,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +25: [2023-04-29 11:37:34,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +25: [2023-04-29 11:37:34,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +60: [2023-04-29 11:37:34,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +25: [2023-04-29 11:37:34,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +13: [2023-04-29 11:37:34,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +63: [2023-04-29 11:37:34,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +25: [2023-04-29 11:37:34,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +57: [2023-04-29 11:37:34,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +36: [2023-04-29 11:37:34,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +13: [2023-04-29 11:37:34,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +13: [2023-04-29 11:37:34,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +63: [2023-04-29 11:37:34,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +57: [2023-04-29 11:37:34,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 8: [2023-04-29 11:37:34,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +63: [2023-04-29 11:37:34,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +59: [2023-04-29 11:37:34,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +51: [2023-04-29 11:37:34,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +51: [2023-04-29 11:37:34,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +36: [2023-04-29 11:37:34,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +16: [2023-04-29 11:37:34,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 1: [2023-04-29 11:37:34,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +50: [2023-04-29 11:37:34,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_75_mp_rank_02_optim_states.pt. +16: [2023-04-29 11:37:34,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +16: [2023-04-29 11:37:34,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 1: [2023-04-29 11:37:34,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 1: [2023-04-29 11:37:34,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +50: [2023-04-29 11:37:34,408] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 406 +16: [2023-04-29 11:37:34,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 1: [2023-04-29 11:37:34,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 1: [2023-04-29 11:37:34,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +23: [2023-04-29 11:37:34,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 9: [2023-04-29 11:37:34,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +23: [2023-04-29 11:37:34,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +23: [2023-04-29 11:37:34,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +23: [2023-04-29 11:37:34,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +36: [2023-04-29 11:37:34,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +59: [2023-04-29 11:37:34,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +42: [2023-04-29 11:37:34,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +36: [2023-04-29 11:37:34,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +13: [2023-04-29 11:37:34,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +63: [2023-04-29 11:37:34,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +59: [2023-04-29 11:37:34,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +59: [2023-04-29 11:37:34,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +59: [2023-04-29 11:37:34,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +59: [2023-04-29 11:37:34,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +59: [2023-04-29 11:37:34,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +13: [2023-04-29 11:37:34,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +59: [2023-04-29 11:37:34,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +59: [2023-04-29 11:37:34,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. + 1: [2023-04-29 11:37:34,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +13: [2023-04-29 11:37:34,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +59: [2023-04-29 11:37:34,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +59: [2023-04-29 11:37:34,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +63: [2023-04-29 11:37:34,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +63: [2023-04-29 11:37:34,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +59: [2023-04-29 11:37:34,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +36: [2023-04-29 11:37:34,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +51: [2023-04-29 11:37:34,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +19: [2023-04-29 11:37:34,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +51: [2023-04-29 11:37:34,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +19: [2023-04-29 11:37:34,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +60: [2023-04-29 11:37:34,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 9: [2023-04-29 11:37:34,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... + 9: [2023-04-29 11:37:34,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +36: [2023-04-29 11:37:34,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +60: [2023-04-29 11:37:34,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 9: [2023-04-29 11:37:34,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt... +23: [2023-04-29 11:37:34,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 0: [2023-04-29 11:37:34,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 0: [2023-04-29 11:37:34,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +13: [2023-04-29 11:37:34,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 1: [2023-04-29 11:37:34,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +35: [2023-04-29 11:37:34,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_13_mp_rank_02_optim_states.pt... +35: [2023-04-29 11:37:34,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_12_mp_rank_02_optim_states.pt... +35: [2023-04-29 11:37:34,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_15_mp_rank_02_optim_states.pt... +36: [2023-04-29 11:37:34,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +36: [2023-04-29 11:37:34,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +34: [2023-04-29 11:37:34,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 0: [2023-04-29 11:37:34,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +16: [2023-04-29 11:37:34,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +16: [2023-04-29 11:37:34,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +23: [2023-04-29 11:37:34,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 8: [2023-04-29 11:37:34,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +16: [2023-04-29 11:37:34,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +39: [2023-04-29 11:37:34,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +59: [2023-04-29 11:37:34,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +35: [2023-04-29 11:37:34,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_14_mp_rank_02_optim_states.pt... +59: [2023-04-29 11:37:34,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +59: [2023-04-29 11:37:34,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +23: [2023-04-29 11:37:34,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +34: [2023-04-29 11:37:34,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +19: [2023-04-29 11:37:34,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +59: [2023-04-29 11:37:34,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +24: [2023-04-29 11:37:34,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +50: [2023-04-29 11:37:34,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_73_mp_rank_02_optim_states.pt. +23: [2023-04-29 11:37:34,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +50: [2023-04-29 11:37:34,419] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 402 +16: [2023-04-29 11:37:34,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +63: [2023-04-29 11:37:34,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +38: [2023-04-29 11:37:34,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +38: [2023-04-29 11:37:34,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +24: [2023-04-29 11:37:34,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +19: [2023-04-29 11:37:34,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +13: [2023-04-29 11:37:34,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +52: [2023-04-29 11:37:34,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +33: [2023-04-29 11:37:34,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +33: [2023-04-29 11:37:34,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +33: [2023-04-29 11:37:34,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... + 1: [2023-04-29 11:37:34,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 8: [2023-04-29 11:37:34,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +40: [2023-04-29 11:37:34,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +40: [2023-04-29 11:37:34,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +24: [2023-04-29 11:37:34,425] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +38: [2023-04-29 11:37:34,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +40: [2023-04-29 11:37:34,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +52: [2023-04-29 11:37:34,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +40: [2023-04-29 11:37:34,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +61: [2023-04-29 11:37:34,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +51: [2023-04-29 11:37:34,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +53: [2023-04-29 11:37:34,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_87_mp_rank_02_optim_states.pt. +57: [2023-04-29 11:37:34,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +60: [2023-04-29 11:37:34,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 8: [2023-04-29 11:37:34,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +56: [2023-04-29 11:37:34,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +18: [2023-04-29 11:37:34,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +24: [2023-04-29 11:37:34,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +34: [2023-04-29 11:37:34,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_11_mp_rank_02_optim_states.pt... +34: [2023-04-29 11:37:34,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_9_mp_rank_02_optim_states.pt... +25: [2023-04-29 11:37:34,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +29: [2023-04-29 11:37:34,448] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +29: [2023-04-29 11:37:34,448] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +43: [2023-04-29 11:37:34,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +43: [2023-04-29 11:37:34,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +41: [2023-04-29 11:37:34,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_39_mp_rank_02_optim_states.pt... +41: [2023-04-29 11:37:34,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_36_mp_rank_02_optim_states.pt... +41: [2023-04-29 11:37:34,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_37_mp_rank_02_optim_states.pt... +41: [2023-04-29 11:37:34,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_38_mp_rank_02_optim_states.pt... +42: [2023-04-29 11:37:34,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 1: [2023-04-29 11:37:34,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +38: [2023-04-29 11:37:34,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +21: [2023-04-29 11:37:34,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +52: [2023-04-29 11:37:34,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 6: [2023-04-29 11:37:34,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +39: [2023-04-29 11:37:34,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +39: [2023-04-29 11:37:34,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +11: [2023-04-29 11:37:34,432] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +45: [2023-04-29 11:37:34,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +61: [2023-04-29 11:37:34,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +51: [2023-04-29 11:37:34,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +53: [2023-04-29 11:37:34,438] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 430 +57: [2023-04-29 11:37:34,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +60: [2023-04-29 11:37:34,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +56: [2023-04-29 11:37:34,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +24: [2023-04-29 11:37:34,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +34: [2023-04-29 11:37:34,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_8_mp_rank_02_optim_states.pt... +34: [2023-04-29 11:37:34,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_10_mp_rank_02_optim_states.pt... +25: [2023-04-29 11:37:34,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +43: [2023-04-29 11:37:34,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +42: [2023-04-29 11:37:34,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +52: [2023-04-29 11:37:34,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +39: [2023-04-29 11:37:34,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +61: [2023-04-29 11:37:34,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +57: [2023-04-29 11:37:34,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +57: [2023-04-29 11:37:34,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +60: [2023-04-29 11:37:34,447] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +56: [2023-04-29 11:37:34,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +24: [2023-04-29 11:37:34,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +25: [2023-04-29 11:37:34,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +25: [2023-04-29 11:37:34,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +43: [2023-04-29 11:37:34,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +42: [2023-04-29 11:37:34,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 1: [2023-04-29 11:37:34,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +21: [2023-04-29 11:37:34,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +39: [2023-04-29 11:37:34,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +11: [2023-04-29 11:37:34,432] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +45: [2023-04-29 11:37:34,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +61: [2023-04-29 11:37:34,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +56: [2023-04-29 11:37:34,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +56: [2023-04-29 11:37:34,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +24: [2023-04-29 11:37:34,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +42: [2023-04-29 11:37:34,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... + 1: [2023-04-29 11:37:34,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +11: [2023-04-29 11:37:34,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +45: [2023-04-29 11:37:34,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +61: [2023-04-29 11:37:34,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +56: [2023-04-29 11:37:34,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +11: [2023-04-29 11:37:34,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +45: [2023-04-29 11:37:34,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +61: [2023-04-29 11:37:34,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +56: [2023-04-29 11:37:34,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +45: [2023-04-29 11:37:34,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +61: [2023-04-29 11:37:34,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +56: [2023-04-29 11:37:34,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +45: [2023-04-29 11:37:34,442] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +61: [2023-04-29 11:37:34,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +45: [2023-04-29 11:37:34,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +61: [2023-04-29 11:37:34,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +61: [2023-04-29 11:37:34,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +41: [2023-04-29 11:37:34,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 6: [2023-04-29 11:37:34,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +45: [2023-04-29 11:37:34,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +61: [2023-04-29 11:37:34,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +61: [2023-04-29 11:37:34,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +61: [2023-04-29 11:37:34,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +53: [2023-04-29 11:37:34,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_85_mp_rank_02_optim_states.pt. +60: [2023-04-29 11:37:34,447] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 6: [2023-04-29 11:37:34,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +61: [2023-04-29 11:37:34,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 6: [2023-04-29 11:37:34,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +61: [2023-04-29 11:37:34,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +53: [2023-04-29 11:37:34,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_84_mp_rank_02_optim_states.pt. + 6: [2023-04-29 11:37:34,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +61: [2023-04-29 11:37:34,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +61: [2023-04-29 11:37:34,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +61: [2023-04-29 11:37:34,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +61: [2023-04-29 11:37:34,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +61: [2023-04-29 11:37:34,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +53: [2023-04-29 11:37:34,451] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 426 +42: [2023-04-29 11:37:34,442] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +53: [2023-04-29 11:37:34,451] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 424 +42: [2023-04-29 11:37:34,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... + 6: [2023-04-29 11:37:34,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +57: [2023-04-29 11:37:34,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +57: [2023-04-29 11:37:34,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +51: [2023-04-29 11:37:34,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +57: [2023-04-29 11:37:34,453] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +18: [2023-04-29 11:37:34,453] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +29: [2023-04-29 11:37:34,453] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +29: [2023-04-29 11:37:34,453] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +53: [2023-04-29 11:37:34,453] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_86_mp_rank_02_optim_states.pt. +41: [2023-04-29 11:37:34,453] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +59: [2023-04-29 11:37:34,453] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +53: [2023-04-29 11:37:34,454] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 428 +51: [2023-04-29 11:37:34,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 1: [2023-04-29 11:37:34,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +59: [2023-04-29 11:37:34,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_110_mp_rank_02_optim_states.pt... +59: [2023-04-29 11:37:34,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_111_mp_rank_02_optim_states.pt... +59: [2023-04-29 11:37:34,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_109_mp_rank_02_optim_states.pt... +59: [2023-04-29 11:37:34,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_108_mp_rank_02_optim_states.pt... + 6: [2023-04-29 11:37:34,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +18: [2023-04-29 11:37:34,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +56: [2023-04-29 11:37:34,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +18: [2023-04-29 11:37:34,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +41: [2023-04-29 11:37:34,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +60: [2023-04-29 11:37:34,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +39: [2023-04-29 11:37:34,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +18: [2023-04-29 11:37:34,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +39: [2023-04-29 11:37:34,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +59: [2023-04-29 11:37:34,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +55: [2023-04-29 11:37:34,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_95_mp_rank_02_optim_states.pt. +39: [2023-04-29 11:37:34,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +55: [2023-04-29 11:37:34,459] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 446 +41: [2023-04-29 11:37:34,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... + 6: [2023-04-29 11:37:34,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 6: [2023-04-29 11:37:34,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 6: [2023-04-29 11:37:34,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +57: [2023-04-29 11:37:34,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +39: [2023-04-29 11:37:34,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +39: [2023-04-29 11:37:34,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +39: [2023-04-29 11:37:34,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +39: [2023-04-29 11:37:34,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +39: [2023-04-29 11:37:34,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +39: [2023-04-29 11:37:34,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +39: [2023-04-29 11:37:34,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +39: [2023-04-29 11:37:34,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +39: [2023-04-29 11:37:34,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +37: [2023-04-29 11:37:34,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_23_mp_rank_02_optim_states.pt. +39: [2023-04-29 11:37:34,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +39: [2023-04-29 11:37:34,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +39: [2023-04-29 11:37:34,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +21: [2023-04-29 11:37:34,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +37: [2023-04-29 11:37:34,462] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 302 +36: [2023-04-29 11:37:34,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +21: [2023-04-29 11:37:34,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +43: [2023-04-29 11:37:34,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +24: [2023-04-29 11:37:34,463] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +43: [2023-04-29 11:37:34,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +43: [2023-04-29 11:37:34,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +60: [2023-04-29 11:37:34,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +60: [2023-04-29 11:37:34,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +43: [2023-04-29 11:37:34,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +59: [2023-04-29 11:37:34,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +60: [2023-04-29 11:37:34,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +60: [2023-04-29 11:37:34,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +60: [2023-04-29 11:37:34,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +60: [2023-04-29 11:37:34,466] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +37: [2023-04-29 11:37:34,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_22_mp_rank_02_optim_states.pt. +60: [2023-04-29 11:37:34,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +37: [2023-04-29 11:37:34,466] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 300 +42: [2023-04-29 11:37:34,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +42: [2023-04-29 11:37:34,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +42: [2023-04-29 11:37:34,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +21: [2023-04-29 11:37:34,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 6: [2023-04-29 11:37:34,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 6: [2023-04-29 11:37:34,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +41: [2023-04-29 11:37:34,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +40: [2023-04-29 11:37:34,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_32_mp_rank_02_optim_states.pt. +40: [2023-04-29 11:37:34,468] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 320 +43: [2023-04-29 11:37:34,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +59: [2023-04-29 11:37:34,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +21: [2023-04-29 11:37:34,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +57: [2023-04-29 11:37:34,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +57: [2023-04-29 11:37:34,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +59: [2023-04-29 11:37:34,470] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +56: [2023-04-29 11:37:34,470] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +30: [2023-04-29 11:37:34,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +30: [2023-04-29 11:37:34,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +30: [2023-04-29 11:37:34,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +56: [2023-04-29 11:37:34,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +30: [2023-04-29 11:37:34,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +56: [2023-04-29 11:37:34,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +41: [2023-04-29 11:37:34,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +21: [2023-04-29 11:37:34,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +34: [2023-04-29 11:37:34,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +34: [2023-04-29 11:37:34,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +56: [2023-04-29 11:37:34,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +49: [2023-04-29 11:37:34,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_68_mp_rank_02_optim_states.pt. +49: [2023-04-29 11:37:34,472] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 392 +43: [2023-04-29 11:37:34,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +43: [2023-04-29 11:37:34,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +43: [2023-04-29 11:37:34,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +59: [2023-04-29 11:37:34,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +56: [2023-04-29 11:37:34,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +56: [2023-04-29 11:37:34,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +56: [2023-04-29 11:37:34,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +51: [2023-04-29 11:37:34,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +51: [2023-04-29 11:37:34,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +51: [2023-04-29 11:37:34,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +59: [2023-04-29 11:37:34,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +56: [2023-04-29 11:37:34,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +41: [2023-04-29 11:37:34,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +56: [2023-04-29 11:37:34,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +60: [2023-04-29 11:37:34,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +60: [2023-04-29 11:37:34,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +60: [2023-04-29 11:37:34,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +34: [2023-04-29 11:37:34,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +34: [2023-04-29 11:37:34,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +60: [2023-04-29 11:37:34,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +21: [2023-04-29 11:37:34,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +29: [2023-04-29 11:37:34,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +42: [2023-04-29 11:37:34,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +29: [2023-04-29 11:37:34,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 2: [2023-04-29 11:37:34,479] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 2: [2023-04-29 11:37:34,479] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +56: [2023-04-29 11:37:34,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +57: [2023-04-29 11:37:34,479] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +38: [2023-04-29 11:37:34,479] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +60: [2023-04-29 11:37:34,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +23: [2023-04-29 11:37:34,479] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +41: [2023-04-29 11:37:34,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +56: [2023-04-29 11:37:34,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +60: [2023-04-29 11:37:34,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +56: [2023-04-29 11:37:34,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +56: [2023-04-29 11:37:34,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +60: [2023-04-29 11:37:34,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +56: [2023-04-29 11:37:34,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +56: [2023-04-29 11:37:34,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +56: [2023-04-29 11:37:34,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +56: [2023-04-29 11:37:34,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +60: [2023-04-29 11:37:34,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +56: [2023-04-29 11:37:34,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +56: [2023-04-29 11:37:34,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +13: [2023-04-29 11:37:34,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +34: [2023-04-29 11:37:34,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +25: [2023-04-29 11:37:34,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +25: [2023-04-29 11:37:34,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +34: [2023-04-29 11:37:34,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +59: [2023-04-29 11:37:34,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +29: [2023-04-29 11:37:34,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 2: [2023-04-29 11:37:34,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 2: [2023-04-29 11:37:34,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +29: [2023-04-29 11:37:34,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +25: [2023-04-29 11:37:34,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +57: [2023-04-29 11:37:34,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +25: [2023-04-29 11:37:34,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +23: [2023-04-29 11:37:34,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 6: [2023-04-29 11:37:34,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 6: [2023-04-29 11:37:34,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +36: [2023-04-29 11:37:34,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +38: [2023-04-29 11:37:34,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +61: [2023-04-29 11:37:34,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_116_mp_rank_02_optim_states.pt... +61: [2023-04-29 11:37:34,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_119_mp_rank_02_optim_states.pt... +61: [2023-04-29 11:37:34,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_118_mp_rank_02_optim_states.pt... +61: [2023-04-29 11:37:34,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_117_mp_rank_02_optim_states.pt... + 9: [2023-04-29 11:37:34,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +43: [2023-04-29 11:37:34,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +13: [2023-04-29 11:37:34,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +19: [2023-04-29 11:37:34,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +18: [2023-04-29 11:37:34,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +39: [2023-04-29 11:37:34,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +39: [2023-04-29 11:37:34,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +60: [2023-04-29 11:37:34,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +34: [2023-04-29 11:37:34,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +25: [2023-04-29 11:37:34,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +18: [2023-04-29 11:37:34,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +52: [2023-04-29 11:37:34,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +23: [2023-04-29 11:37:34,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +23: [2023-04-29 11:37:34,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +19: [2023-04-29 11:37:34,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +10: [2023-04-29 11:37:34,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +10: [2023-04-29 11:37:34,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +25: [2023-04-29 11:37:34,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +34: [2023-04-29 11:37:34,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +43: [2023-04-29 11:37:34,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +55: [2023-04-29 11:37:34,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_94_mp_rank_02_optim_states.pt. +43: [2023-04-29 11:37:34,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +55: [2023-04-29 11:37:34,489] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 444 +25: [2023-04-29 11:37:34,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +39: [2023-04-29 11:37:34,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +39: [2023-04-29 11:37:34,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_43-model_01-model_states.pt. +36: [2023-04-29 11:37:34,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +25: [2023-04-29 11:37:34,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +36: [2023-04-29 11:37:34,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +43: [2023-04-29 11:37:34,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +60: [2023-04-29 11:37:34,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +10: [2023-04-29 11:37:34,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +10: [2023-04-29 11:37:34,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +36: [2023-04-29 11:37:34,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 9: [2023-04-29 11:37:34,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +38: [2023-04-29 11:37:34,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 9: [2023-04-29 11:37:34,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +13: [2023-04-29 11:37:34,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +13: [2023-04-29 11:37:34,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +11: [2023-04-29 11:37:34,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +20: [2023-04-29 11:37:34,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +20: [2023-04-29 11:37:34,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +20: [2023-04-29 11:37:34,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +20: [2023-04-29 11:37:34,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +18: [2023-04-29 11:37:34,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +25: [2023-04-29 11:37:34,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +19: [2023-04-29 11:37:34,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 9: [2023-04-29 11:37:34,493] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... + 9: [2023-04-29 11:37:34,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_00-model_states.pt. +60: [2023-04-29 11:37:34,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +25: [2023-04-29 11:37:34,493] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +40: [2023-04-29 11:37:34,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +52: [2023-04-29 11:37:34,493] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +36: [2023-04-29 11:37:34,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +19: [2023-04-29 11:37:34,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +36: [2023-04-29 11:37:34,493] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +60: [2023-04-29 11:37:34,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +36: [2023-04-29 11:37:34,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +16: [2023-04-29 11:37:34,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +11: [2023-04-29 11:37:34,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +38: [2023-04-29 11:37:34,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +52: [2023-04-29 11:37:34,495] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +10: [2023-04-29 11:37:34,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 9: [2023-04-29 11:37:34,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 9: [2023-04-29 11:37:34,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +42: [2023-04-29 11:37:34,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +57: [2023-04-29 11:37:34,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +57: [2023-04-29 11:37:34,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +10: [2023-04-29 11:37:34,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +20: [2023-04-29 11:37:34,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +16: [2023-04-29 11:37:34,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +16: [2023-04-29 11:37:34,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +16: [2023-04-29 11:37:34,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +42: [2023-04-29 11:37:34,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +42: [2023-04-29 11:37:34,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +10: [2023-04-29 11:37:34,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +61: [2023-04-29 11:37:34,497] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +19: [2023-04-29 11:37:34,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +60: [2023-04-29 11:37:34,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... + 9: [2023-04-29 11:37:34,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +10: [2023-04-29 11:37:34,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +30: [2023-04-29 11:37:34,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 9: [2023-04-29 11:37:34,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +40: [2023-04-29 11:37:34,497] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +40: [2023-04-29 11:37:34,497] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 6: [2023-04-29 11:37:34,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +61: [2023-04-29 11:37:34,497] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +20: [2023-04-29 11:37:34,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 6: [2023-04-29 11:37:34,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +20: [2023-04-29 11:37:34,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +19: [2023-04-29 11:37:34,499] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +20: [2023-04-29 11:37:34,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +30: [2023-04-29 11:37:34,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 9: [2023-04-29 11:37:34,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt... +40: [2023-04-29 11:37:34,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +30: [2023-04-29 11:37:34,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +30: [2023-04-29 11:37:34,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +40: [2023-04-29 11:37:34,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +39: [2023-04-29 11:37:34,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_29_mp_rank_02_optim_states.pt... +39: [2023-04-29 11:37:34,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_31_mp_rank_02_optim_states.pt... +39: [2023-04-29 11:37:34,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_28_mp_rank_02_optim_states.pt... +39: [2023-04-29 11:37:34,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_30_mp_rank_02_optim_states.pt... +25: [2023-04-29 11:37:34,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +52: [2023-04-29 11:37:34,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... + 9: [2023-04-29 11:37:34,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 9: [2023-04-29 11:37:34,502] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +19: [2023-04-29 11:37:34,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +60: [2023-04-29 11:37:34,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +60: [2023-04-29 11:37:34,502] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +61: [2023-04-29 11:37:34,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +11: [2023-04-29 11:37:34,502] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +11: [2023-04-29 11:37:34,502] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +61: [2023-04-29 11:37:34,502] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +43: [2023-04-29 11:37:34,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +43: [2023-04-29 11:37:34,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +43: [2023-04-29 11:37:34,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +51: [2023-04-29 11:37:34,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +40: [2023-04-29 11:37:34,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... + 9: [2023-04-29 11:37:34,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +43: [2023-04-29 11:37:34,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +40: [2023-04-29 11:37:34,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +57: [2023-04-29 11:37:34,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +57: [2023-04-29 11:37:34,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +38: [2023-04-29 11:37:34,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 9: [2023-04-29 11:37:34,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +42: [2023-04-29 11:37:34,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +42: [2023-04-29 11:37:34,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +52: [2023-04-29 11:37:34,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +52: [2023-04-29 11:37:34,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +42: [2023-04-29 11:37:34,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +42: [2023-04-29 11:37:34,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +42: [2023-04-29 11:37:34,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +42: [2023-04-29 11:37:34,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +61: [2023-04-29 11:37:34,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +40: [2023-04-29 11:37:34,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +42: [2023-04-29 11:37:34,505] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +38: [2023-04-29 11:37:34,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +42: [2023-04-29 11:37:34,505] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +42: [2023-04-29 11:37:34,505] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +23: [2023-04-29 11:37:34,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 2: [2023-04-29 11:37:34,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +57: [2023-04-29 11:37:34,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +57: [2023-04-29 11:37:34,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +57: [2023-04-29 11:37:34,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +57: [2023-04-29 11:37:34,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +57: [2023-04-29 11:37:34,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +57: [2023-04-29 11:37:34,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +57: [2023-04-29 11:37:34,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 2: [2023-04-29 11:37:34,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +43: [2023-04-29 11:37:34,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +43: [2023-04-29 11:37:34,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +13: [2023-04-29 11:37:34,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +57: [2023-04-29 11:37:34,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +25: [2023-04-29 11:37:34,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 2: [2023-04-29 11:37:34,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +11: [2023-04-29 11:37:34,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +43: [2023-04-29 11:37:34,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +43: [2023-04-29 11:37:34,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +43: [2023-04-29 11:37:34,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +43: [2023-04-29 11:37:34,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 9: [2023-04-29 11:37:34,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +60: [2023-04-29 11:37:34,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +43: [2023-04-29 11:37:34,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +43: [2023-04-29 11:37:34,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +19: [2023-04-29 11:37:34,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +61: [2023-04-29 11:37:34,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +60: [2023-04-29 11:37:34,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_112_mp_rank_02_optim_states.pt... +60: [2023-04-29 11:37:34,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_113_mp_rank_02_optim_states.pt... +60: [2023-04-29 11:37:34,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_114_mp_rank_02_optim_states.pt... +60: [2023-04-29 11:37:34,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_115_mp_rank_02_optim_states.pt... +61: [2023-04-29 11:37:34,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... + 2: [2023-04-29 11:37:34,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 9: [2023-04-29 11:37:34,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +11: [2023-04-29 11:37:34,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +11: [2023-04-29 11:37:34,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +51: [2023-04-29 11:37:34,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +51: [2023-04-29 11:37:34,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +52: [2023-04-29 11:37:34,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +25: [2023-04-29 11:37:34,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +25: [2023-04-29 11:37:34,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +23: [2023-04-29 11:37:34,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +52: [2023-04-29 11:37:34,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +38: [2023-04-29 11:37:34,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +13: [2023-04-29 11:37:34,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +42: [2023-04-29 11:37:34,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +42: [2023-04-29 11:37:34,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +42: [2023-04-29 11:37:34,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +42: [2023-04-29 11:37:34,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +38: [2023-04-29 11:37:34,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +11: [2023-04-29 11:37:34,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +36: [2023-04-29 11:37:34,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 7: [2023-04-29 11:37:34,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +36: [2023-04-29 11:37:34,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +36: [2023-04-29 11:37:34,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +57: [2023-04-29 11:37:34,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +36: [2023-04-29 11:37:34,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +61: [2023-04-29 11:37:34,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +57: [2023-04-29 11:37:34,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +57: [2023-04-29 11:37:34,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +57: [2023-04-29 11:37:34,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +56: [2023-04-29 11:37:34,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_96_mp_rank_02_optim_states.pt... +56: [2023-04-29 11:37:34,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_97_mp_rank_02_optim_states.pt... +56: [2023-04-29 11:37:34,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_98_mp_rank_02_optim_states.pt... +56: [2023-04-29 11:37:34,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_99_mp_rank_02_optim_states.pt... +51: [2023-04-29 11:37:34,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +13: [2023-04-29 11:37:34,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +51: [2023-04-29 11:37:34,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +23: [2023-04-29 11:37:34,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +51: [2023-04-29 11:37:34,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +51: [2023-04-29 11:37:34,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +51: [2023-04-29 11:37:34,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +25: [2023-04-29 11:37:34,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 7: [2023-04-29 11:37:34,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 7: [2023-04-29 11:37:34,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +25: [2023-04-29 11:37:34,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +13: [2023-04-29 11:37:34,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +23: [2023-04-29 11:37:34,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +51: [2023-04-29 11:37:34,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +51: [2023-04-29 11:37:34,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +51: [2023-04-29 11:37:34,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +51: [2023-04-29 11:37:34,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +39: [2023-04-29 11:37:34,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +49: [2023-04-29 11:37:34,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_69_mp_rank_02_optim_states.pt. +39: [2023-04-29 11:37:34,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +49: [2023-04-29 11:37:34,521] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 394 +39: [2023-04-29 11:37:34,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... +36: [2023-04-29 11:37:34,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +51: [2023-04-29 11:37:34,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +51: [2023-04-29 11:37:34,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +36: [2023-04-29 11:37:34,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +36: [2023-04-29 11:37:34,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +36: [2023-04-29 11:37:34,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +51: [2023-04-29 11:37:34,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +51: [2023-04-29 11:37:34,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +51: [2023-04-29 11:37:34,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +39: [2023-04-29 11:37:34,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +36: [2023-04-29 11:37:34,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +36: [2023-04-29 11:37:34,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +36: [2023-04-29 11:37:34,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +16: [2023-04-29 11:37:34,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +36: [2023-04-29 11:37:34,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. + 7: [2023-04-29 11:37:34,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +44: [2023-04-29 11:37:34,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_50_mp_rank_02_optim_states.pt. +44: [2023-04-29 11:37:34,531] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 356 + 4: [2023-04-29 11:37:34,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 4: [2023-04-29 11:37:34,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 4: [2023-04-29 11:37:34,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 4: [2023-04-29 11:37:34,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +16: [2023-04-29 11:37:34,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +16: [2023-04-29 11:37:34,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +11: [2023-04-29 11:37:34,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +11: [2023-04-29 11:37:34,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +11: [2023-04-29 11:37:34,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +11: [2023-04-29 11:37:34,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +56: [2023-04-29 11:37:34,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +16: [2023-04-29 11:37:34,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +43: [2023-04-29 11:37:34,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_47_mp_rank_02_optim_states.pt... +43: [2023-04-29 11:37:34,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_45_mp_rank_02_optim_states.pt... +43: [2023-04-29 11:37:34,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_44_mp_rank_02_optim_states.pt... +43: [2023-04-29 11:37:34,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_46_mp_rank_02_optim_states.pt... +26: [2023-04-29 11:37:34,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +26: [2023-04-29 11:37:34,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +26: [2023-04-29 11:37:34,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +26: [2023-04-29 11:37:34,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +11: [2023-04-29 11:37:34,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +11: [2023-04-29 11:37:34,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +56: [2023-04-29 11:37:34,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +12: [2023-04-29 11:37:34,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +12: [2023-04-29 11:37:34,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +11: [2023-04-29 11:37:34,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +12: [2023-04-29 11:37:34,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +11: [2023-04-29 11:37:34,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +12: [2023-04-29 11:37:34,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +51: [2023-04-29 11:37:34,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +51: [2023-04-29 11:37:34,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +51: [2023-04-29 11:37:34,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +51: [2023-04-29 11:37:34,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +26: [2023-04-29 11:37:34,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +26: [2023-04-29 11:37:34,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +36: [2023-04-29 11:37:34,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_18_mp_rank_02_optim_states.pt... +36: [2023-04-29 11:37:34,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_16_mp_rank_02_optim_states.pt... +36: [2023-04-29 11:37:34,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_19_mp_rank_02_optim_states.pt... +36: [2023-04-29 11:37:34,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_17_mp_rank_02_optim_states.pt... +56: [2023-04-29 11:37:34,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +56: [2023-04-29 11:37:34,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +26: [2023-04-29 11:37:34,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +12: [2023-04-29 11:37:34,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +26: [2023-04-29 11:37:34,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +12: [2023-04-29 11:37:34,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 5: [2023-04-29 11:37:34,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 5: [2023-04-29 11:37:34,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 5: [2023-04-29 11:37:34,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 5: [2023-04-29 11:37:34,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +43: [2023-04-29 11:37:34,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +43: [2023-04-29 11:37:34,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +42: [2023-04-29 11:37:34,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_43_mp_rank_02_optim_states.pt... +42: [2023-04-29 11:37:34,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_42_mp_rank_02_optim_states.pt... +42: [2023-04-29 11:37:34,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_41_mp_rank_02_optim_states.pt... +42: [2023-04-29 11:37:34,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_40_mp_rank_02_optim_states.pt... +12: [2023-04-29 11:37:34,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +54: [2023-04-29 11:37:34,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_88_mp_rank_02_optim_states.pt. +54: [2023-04-29 11:37:34,548] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 432 +55: [2023-04-29 11:37:34,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_92_mp_rank_02_optim_states.pt. +12: [2023-04-29 11:37:34,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +55: [2023-04-29 11:37:34,549] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 440 +56: [2023-04-29 11:37:34,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +56: [2023-04-29 11:37:34,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +30: [2023-04-29 11:37:34,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +30: [2023-04-29 11:37:34,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +30: [2023-04-29 11:37:34,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +43: [2023-04-29 11:37:34,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +30: [2023-04-29 11:37:34,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +25: [2023-04-29 11:37:34,551] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 4: [2023-04-29 11:37:34,551] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 4: [2023-04-29 11:37:34,551] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 4: [2023-04-29 11:37:34,551] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +56: [2023-04-29 11:37:34,551] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +43: [2023-04-29 11:37:34,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. + 5: [2023-04-29 11:37:34,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 5: [2023-04-29 11:37:34,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 5: [2023-04-29 11:37:34,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 4: [2023-04-29 11:37:34,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 5: [2023-04-29 11:37:34,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +43: [2023-04-29 11:37:34,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +43: [2023-04-29 11:37:34,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +49: [2023-04-29 11:37:34,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_70_mp_rank_02_optim_states.pt. +30: [2023-04-29 11:37:34,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +49: [2023-04-29 11:37:34,555] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 396 + 4: [2023-04-29 11:37:34,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +30: [2023-04-29 11:37:34,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +57: [2023-04-29 11:37:34,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_102_mp_rank_02_optim_states.pt... +57: [2023-04-29 11:37:34,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_103_mp_rank_02_optim_states.pt... +57: [2023-04-29 11:37:34,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_100_mp_rank_02_optim_states.pt... +57: [2023-04-29 11:37:34,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_101_mp_rank_02_optim_states.pt... + 4: [2023-04-29 11:37:34,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +43: [2023-04-29 11:37:34,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +25: [2023-04-29 11:37:34,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +56: [2023-04-29 11:37:34,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +30: [2023-04-29 11:37:34,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +30: [2023-04-29 11:37:34,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +43: [2023-04-29 11:37:34,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... + 4: [2023-04-29 11:37:34,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 4: [2023-04-29 11:37:34,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 4: [2023-04-29 11:37:34,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +25: [2023-04-29 11:37:34,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 4: [2023-04-29 11:37:34,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 4: [2023-04-29 11:37:34,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 4: [2023-04-29 11:37:34,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +25: [2023-04-29 11:37:34,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +20: [2023-04-29 11:37:34,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +51: [2023-04-29 11:37:34,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +51: [2023-04-29 11:37:34,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +20: [2023-04-29 11:37:34,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +14: [2023-04-29 11:37:34,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +14: [2023-04-29 11:37:34,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +14: [2023-04-29 11:37:34,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +20: [2023-04-29 11:37:34,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +20: [2023-04-29 11:37:34,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +14: [2023-04-29 11:37:34,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +10: [2023-04-29 11:37:34,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +10: [2023-04-29 11:37:34,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +27: [2023-04-29 11:37:34,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +27: [2023-04-29 11:37:34,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +10: [2023-04-29 11:37:34,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +10: [2023-04-29 11:37:34,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +10: [2023-04-29 11:37:34,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +30: [2023-04-29 11:37:34,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +27: [2023-04-29 11:37:34,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +27: [2023-04-29 11:37:34,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 2: [2023-04-29 11:37:34,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +10: [2023-04-29 11:37:34,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +10: [2023-04-29 11:37:34,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +10: [2023-04-29 11:37:34,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +51: [2023-04-29 11:37:34,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +30: [2023-04-29 11:37:34,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +51: [2023-04-29 11:37:34,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +51: [2023-04-29 11:37:34,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_77_mp_rank_02_optim_states.pt... +51: [2023-04-29 11:37:34,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_76_mp_rank_02_optim_states.pt... +51: [2023-04-29 11:37:34,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_79_mp_rank_02_optim_states.pt... +51: [2023-04-29 11:37:34,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_78_mp_rank_02_optim_states.pt... +14: [2023-04-29 11:37:34,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +27: [2023-04-29 11:37:34,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +27: [2023-04-29 11:37:34,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +27: [2023-04-29 11:37:34,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +14: [2023-04-29 11:37:34,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +14: [2023-04-29 11:37:34,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +14: [2023-04-29 11:37:34,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 9: [2023-04-29 11:37:34,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +27: [2023-04-29 11:37:34,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 2: [2023-04-29 11:37:34,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 9: [2023-04-29 11:37:34,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +30: [2023-04-29 11:37:34,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 2: [2023-04-29 11:37:34,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +25: [2023-04-29 11:37:34,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 9: [2023-04-29 11:37:34,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +37: [2023-04-29 11:37:34,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_21_mp_rank_02_optim_states.pt. +30: [2023-04-29 11:37:34,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +30: [2023-04-29 11:37:34,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 2: [2023-04-29 11:37:34,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +37: [2023-04-29 11:37:34,576] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 298 +30: [2023-04-29 11:37:34,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 2: [2023-04-29 11:37:34,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 2: [2023-04-29 11:37:34,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +23: [2023-04-29 11:37:34,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +23: [2023-04-29 11:37:34,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 9: [2023-04-29 11:37:34,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 2: [2023-04-29 11:37:34,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +23: [2023-04-29 11:37:34,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +23: [2023-04-29 11:37:34,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +48: [2023-04-29 11:37:34,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_66_mp_rank_02_optim_states.pt. +48: [2023-04-29 11:37:34,583] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 388 +19: [2023-04-29 11:37:34,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +19: [2023-04-29 11:37:34,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +19: [2023-04-29 11:37:34,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +19: [2023-04-29 11:37:34,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +30: [2023-04-29 11:37:34,584] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 2: [2023-04-29 11:37:34,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +47: [2023-04-29 11:37:34,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_61_mp_rank_02_optim_states.pt. +47: [2023-04-29 11:37:34,586] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 378 +30: [2023-04-29 11:37:34,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +25: [2023-04-29 11:37:34,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +39: [2023-04-29 11:37:34,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +19: [2023-04-29 11:37:34,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +19: [2023-04-29 11:37:34,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +28: [2023-04-29 11:37:34,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +28: [2023-04-29 11:37:34,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +39: [2023-04-29 11:37:34,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +20: [2023-04-29 11:37:34,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +19: [2023-04-29 11:37:34,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +25: [2023-04-29 11:37:34,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +19: [2023-04-29 11:37:34,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +37: [2023-04-29 11:37:34,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +37: [2023-04-29 11:37:34,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +37: [2023-04-29 11:37:34,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +28: [2023-04-29 11:37:34,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +28: [2023-04-29 11:37:34,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +37: [2023-04-29 11:37:34,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. + 7: [2023-04-29 11:37:34,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 7: [2023-04-29 11:37:34,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +28: [2023-04-29 11:37:34,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +28: [2023-04-29 11:37:34,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +47: [2023-04-29 11:37:34,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_60_mp_rank_02_optim_states.pt. +20: [2023-04-29 11:37:34,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +28: [2023-04-29 11:37:34,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +47: [2023-04-29 11:37:34,592] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 376 +28: [2023-04-29 11:37:34,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +39: [2023-04-29 11:37:34,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +25: [2023-04-29 11:37:34,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +10: [2023-04-29 11:37:34,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +20: [2023-04-29 11:37:34,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +20: [2023-04-29 11:37:34,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +28: [2023-04-29 11:37:34,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +28: [2023-04-29 11:37:34,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +39: [2023-04-29 11:37:34,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +10: [2023-04-29 11:37:34,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +28: [2023-04-29 11:37:34,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +47: [2023-04-29 11:37:34,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_63_mp_rank_02_optim_states.pt. +47: [2023-04-29 11:37:34,598] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 382 +11: [2023-04-29 11:37:34,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +28: [2023-04-29 11:37:34,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +10: [2023-04-29 11:37:34,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +39: [2023-04-29 11:37:34,600] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +12: [2023-04-29 11:37:34,600] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +10: [2023-04-29 11:37:34,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +10: [2023-04-29 11:37:34,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +52: [2023-04-29 11:37:34,601] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_80_mp_rank_02_optim_states.pt. +52: [2023-04-29 11:37:34,601] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 416 +39: [2023-04-29 11:37:34,601] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_00-model_states.pt. +10: [2023-04-29 11:37:34,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +10: [2023-04-29 11:37:34,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +10: [2023-04-29 11:37:34,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 9: [2023-04-29 11:37:34,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +11: [2023-04-29 11:37:34,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +18: [2023-04-29 11:37:34,606] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +18: [2023-04-29 11:37:34,606] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +18: [2023-04-29 11:37:34,606] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +18: [2023-04-29 11:37:34,606] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +39: [2023-04-29 11:37:34,607] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +11: [2023-04-29 11:37:34,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 9: [2023-04-29 11:37:34,607] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +26: [2023-04-29 11:37:34,608] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +26: [2023-04-29 11:37:34,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +23: [2023-04-29 11:37:34,609] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +23: [2023-04-29 11:37:34,609] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +39: [2023-04-29 11:37:34,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt... +47: [2023-04-29 11:37:34,610] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_62_mp_rank_02_optim_states.pt. +47: [2023-04-29 11:37:34,610] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 380 +53: [2023-04-29 11:37:34,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +53: [2023-04-29 11:37:34,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. + 9: [2023-04-29 11:37:34,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +53: [2023-04-29 11:37:34,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +53: [2023-04-29 11:37:34,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +46: [2023-04-29 11:37:34,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +46: [2023-04-29 11:37:34,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +44: [2023-04-29 11:37:34,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +44: [2023-04-29 11:37:34,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +46: [2023-04-29 11:37:34,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +44: [2023-04-29 11:37:34,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +44: [2023-04-29 11:37:34,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +11: [2023-04-29 11:37:34,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +46: [2023-04-29 11:37:34,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. + 4: [2023-04-29 11:37:34,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +20: [2023-04-29 11:37:34,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +20: [2023-04-29 11:37:34,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +37: [2023-04-29 11:37:34,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +37: [2023-04-29 11:37:34,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +13: [2023-04-29 11:37:34,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +13: [2023-04-29 11:37:34,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +13: [2023-04-29 11:37:34,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +37: [2023-04-29 11:37:34,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +62: [2023-04-29 11:37:34,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_123_mp_rank_02_optim_states.pt. +62: [2023-04-29 11:37:34,616] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 502 +20: [2023-04-29 11:37:34,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +31: [2023-04-29 11:37:34,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +31: [2023-04-29 11:37:34,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +26: [2023-04-29 11:37:34,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +26: [2023-04-29 11:37:34,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +20: [2023-04-29 11:37:34,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +13: [2023-04-29 11:37:34,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +23: [2023-04-29 11:37:34,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +31: [2023-04-29 11:37:34,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +23: [2023-04-29 11:37:34,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +31: [2023-04-29 11:37:34,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +28: [2023-04-29 11:37:34,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 9: [2023-04-29 11:37:34,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +30: [2023-04-29 11:37:34,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +12: [2023-04-29 11:37:34,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +12: [2023-04-29 11:37:34,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 4: [2023-04-29 11:37:34,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +12: [2023-04-29 11:37:34,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +12: [2023-04-29 11:37:34,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +12: [2023-04-29 11:37:34,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +22: [2023-04-29 11:37:34,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +22: [2023-04-29 11:37:34,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +22: [2023-04-29 11:37:34,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +22: [2023-04-29 11:37:34,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 7: [2023-04-29 11:37:34,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +31: [2023-04-29 11:37:34,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +37: [2023-04-29 11:37:34,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +28: [2023-04-29 11:37:34,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +37: [2023-04-29 11:37:34,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. + 7: [2023-04-29 11:37:34,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +37: [2023-04-29 11:37:34,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... + 7: [2023-04-29 11:37:34,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +37: [2023-04-29 11:37:34,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +37: [2023-04-29 11:37:34,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +11: [2023-04-29 11:37:34,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 4: [2023-04-29 11:37:34,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +31: [2023-04-29 11:37:34,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +31: [2023-04-29 11:37:34,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +12: [2023-04-29 11:37:34,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +12: [2023-04-29 11:37:34,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +31: [2023-04-29 11:37:34,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +30: [2023-04-29 11:37:34,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +28: [2023-04-29 11:37:34,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +28: [2023-04-29 11:37:34,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 5: [2023-04-29 11:37:34,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 5: [2023-04-29 11:37:34,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 5: [2023-04-29 11:37:34,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 5: [2023-04-29 11:37:34,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +48: [2023-04-29 11:37:34,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_65_mp_rank_02_optim_states.pt. +12: [2023-04-29 11:37:34,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +48: [2023-04-29 11:37:34,629] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 386 + 4: [2023-04-29 11:37:34,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +37: [2023-04-29 11:37:34,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +37: [2023-04-29 11:37:34,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +14: [2023-04-29 11:37:34,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +37: [2023-04-29 11:37:34,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +37: [2023-04-29 11:37:34,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +37: [2023-04-29 11:37:34,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +37: [2023-04-29 11:37:34,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +37: [2023-04-29 11:37:34,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +37: [2023-04-29 11:37:34,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +48: [2023-04-29 11:37:34,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_67_mp_rank_02_optim_states.pt. +30: [2023-04-29 11:37:34,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +30: [2023-04-29 11:37:34,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +48: [2023-04-29 11:37:34,631] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 390 +18: [2023-04-29 11:37:34,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +48: [2023-04-29 11:37:34,634] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_64_mp_rank_02_optim_states.pt. +48: [2023-04-29 11:37:34,634] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 384 + 3: [2023-04-29 11:37:34,634] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 3: [2023-04-29 11:37:34,634] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 3: [2023-04-29 11:37:34,634] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +11: [2023-04-29 11:37:34,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 3: [2023-04-29 11:37:34,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 4: [2023-04-29 11:37:34,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +27: [2023-04-29 11:37:34,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +26: [2023-04-29 11:37:34,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +26: [2023-04-29 11:37:34,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +18: [2023-04-29 11:37:34,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +46: [2023-04-29 11:37:34,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +46: [2023-04-29 11:37:34,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +11: [2023-04-29 11:37:34,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +49: [2023-04-29 11:37:34,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_71_mp_rank_02_optim_states.pt. +46: [2023-04-29 11:37:34,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +49: [2023-04-29 11:37:34,639] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 398 +14: [2023-04-29 11:37:34,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +46: [2023-04-29 11:37:34,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +46: [2023-04-29 11:37:34,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +27: [2023-04-29 11:37:34,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +55: [2023-04-29 11:37:34,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +55: [2023-04-29 11:37:34,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +55: [2023-04-29 11:37:34,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +46: [2023-04-29 11:37:34,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +55: [2023-04-29 11:37:34,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +27: [2023-04-29 11:37:34,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +18: [2023-04-29 11:37:34,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +18: [2023-04-29 11:37:34,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +13: [2023-04-29 11:37:34,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +44: [2023-04-29 11:37:34,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +53: [2023-04-29 11:37:34,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +44: [2023-04-29 11:37:34,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 2: [2023-04-29 11:37:34,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 2: [2023-04-29 11:37:34,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 2: [2023-04-29 11:37:34,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +44: [2023-04-29 11:37:34,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +53: [2023-04-29 11:37:34,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +44: [2023-04-29 11:37:34,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +53: [2023-04-29 11:37:34,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +53: [2023-04-29 11:37:34,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +53: [2023-04-29 11:37:34,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +20: [2023-04-29 11:37:34,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +44: [2023-04-29 11:37:34,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +44: [2023-04-29 11:37:34,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +53: [2023-04-29 11:37:34,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +53: [2023-04-29 11:37:34,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +53: [2023-04-29 11:37:34,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +53: [2023-04-29 11:37:34,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +53: [2023-04-29 11:37:34,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +53: [2023-04-29 11:37:34,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +53: [2023-04-29 11:37:34,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +44: [2023-04-29 11:37:34,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +44: [2023-04-29 11:37:34,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +11: [2023-04-29 11:37:34,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +29: [2023-04-29 11:37:34,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +44: [2023-04-29 11:37:34,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +29: [2023-04-29 11:37:34,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +29: [2023-04-29 11:37:34,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +29: [2023-04-29 11:37:34,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +38: [2023-04-29 11:37:34,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_25_mp_rank_02_optim_states.pt. + 7: [2023-04-29 11:37:34,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +44: [2023-04-29 11:37:34,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +38: [2023-04-29 11:37:34,644] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 306 +44: [2023-04-29 11:37:34,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +15: [2023-04-29 11:37:34,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +15: [2023-04-29 11:37:34,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +44: [2023-04-29 11:37:34,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +22: [2023-04-29 11:37:34,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +15: [2023-04-29 11:37:34,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +15: [2023-04-29 11:37:34,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +53: [2023-04-29 11:37:34,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +53: [2023-04-29 11:37:34,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +53: [2023-04-29 11:37:34,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +27: [2023-04-29 11:37:34,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +12: [2023-04-29 11:37:34,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 4: [2023-04-29 11:37:34,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 4: [2023-04-29 11:37:34,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +30: [2023-04-29 11:37:34,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +26: [2023-04-29 11:37:34,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +46: [2023-04-29 11:37:34,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +20: [2023-04-29 11:37:34,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +26: [2023-04-29 11:37:34,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +46: [2023-04-29 11:37:34,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +44: [2023-04-29 11:37:34,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +44: [2023-04-29 11:37:34,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +44: [2023-04-29 11:37:34,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +53: [2023-04-29 11:37:34,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +46: [2023-04-29 11:37:34,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +46: [2023-04-29 11:37:34,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +46: [2023-04-29 11:37:34,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +46: [2023-04-29 11:37:34,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +44: [2023-04-29 11:37:34,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. + 4: [2023-04-29 11:37:34,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +14: [2023-04-29 11:37:34,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +14: [2023-04-29 11:37:34,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +20: [2023-04-29 11:37:34,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +20: [2023-04-29 11:37:34,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +22: [2023-04-29 11:37:34,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 4: [2023-04-29 11:37:34,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +46: [2023-04-29 11:37:34,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +46: [2023-04-29 11:37:34,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +46: [2023-04-29 11:37:34,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +46: [2023-04-29 11:37:34,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +22: [2023-04-29 11:37:34,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +13: [2023-04-29 11:37:34,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 4: [2023-04-29 11:37:34,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +40: [2023-04-29 11:37:34,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_33_mp_rank_02_optim_states.pt. +15: [2023-04-29 11:37:34,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +15: [2023-04-29 11:37:34,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +40: [2023-04-29 11:37:34,651] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 322 +15: [2023-04-29 11:37:34,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +19: [2023-04-29 11:37:34,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +19: [2023-04-29 11:37:34,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 7: [2023-04-29 11:37:34,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +15: [2023-04-29 11:37:34,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +22: [2023-04-29 11:37:34,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +12: [2023-04-29 11:37:34,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +13: [2023-04-29 11:37:34,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +13: [2023-04-29 11:37:34,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +24: [2023-04-29 11:37:34,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +24: [2023-04-29 11:37:34,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +30: [2023-04-29 11:37:34,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +12: [2023-04-29 11:37:34,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +24: [2023-04-29 11:37:34,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 3: [2023-04-29 11:37:34,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +24: [2023-04-29 11:37:34,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 4: [2023-04-29 11:37:34,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 3: [2023-04-29 11:37:34,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +12: [2023-04-29 11:37:34,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +12: [2023-04-29 11:37:34,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 3: [2023-04-29 11:37:34,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +14: [2023-04-29 11:37:34,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +19: [2023-04-29 11:37:34,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +19: [2023-04-29 11:37:34,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 5: [2023-04-29 11:37:34,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 5: [2023-04-29 11:37:34,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 3: [2023-04-29 11:37:34,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 4: [2023-04-29 11:37:34,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +12: [2023-04-29 11:37:34,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +21: [2023-04-29 11:37:34,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +21: [2023-04-29 11:37:34,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 3: [2023-04-29 11:37:34,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +30: [2023-04-29 11:37:34,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +12: [2023-04-29 11:37:34,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +10: [2023-04-29 11:37:34,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +21: [2023-04-29 11:37:34,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 5: [2023-04-29 11:37:34,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +21: [2023-04-29 11:37:34,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 5: [2023-04-29 11:37:34,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 3: [2023-04-29 11:37:34,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 4: [2023-04-29 11:37:34,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 3: [2023-04-29 11:37:34,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +27: [2023-04-29 11:37:34,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +30: [2023-04-29 11:37:34,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 3: [2023-04-29 11:37:34,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 3: [2023-04-29 11:37:34,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 3: [2023-04-29 11:37:34,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +16: [2023-04-29 11:37:34,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +16: [2023-04-29 11:37:34,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 3: [2023-04-29 11:37:34,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 3: [2023-04-29 11:37:34,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +10: [2023-04-29 11:37:34,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +14: [2023-04-29 11:37:34,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +10: [2023-04-29 11:37:34,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +16: [2023-04-29 11:37:34,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +16: [2023-04-29 11:37:34,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +23: [2023-04-29 11:37:34,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +21: [2023-04-29 11:37:34,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +21: [2023-04-29 11:37:34,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +21: [2023-04-29 11:37:34,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +28: [2023-04-29 11:37:34,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +10: [2023-04-29 11:37:34,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +21: [2023-04-29 11:37:34,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +58: [2023-04-29 11:37:34,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_106_mp_rank_02_optim_states.pt. +58: [2023-04-29 11:37:34,670] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 468 +10: [2023-04-29 11:37:34,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +37: [2023-04-29 11:37:34,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_22_mp_rank_03_optim_states.pt... +37: [2023-04-29 11:37:34,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_20_mp_rank_03_optim_states.pt... +37: [2023-04-29 11:37:34,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_21_mp_rank_03_optim_states.pt... +37: [2023-04-29 11:37:34,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_23_mp_rank_03_optim_states.pt... +55: [2023-04-29 11:37:34,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +27: [2023-04-29 11:37:34,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +55: [2023-04-29 11:37:34,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +55: [2023-04-29 11:37:34,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +29: [2023-04-29 11:37:34,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +55: [2023-04-29 11:37:34,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +55: [2023-04-29 11:37:34,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +55: [2023-04-29 11:37:34,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +27: [2023-04-29 11:37:34,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +29: [2023-04-29 11:37:34,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +55: [2023-04-29 11:37:34,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +55: [2023-04-29 11:37:34,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +55: [2023-04-29 11:37:34,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +23: [2023-04-29 11:37:34,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +27: [2023-04-29 11:37:34,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +55: [2023-04-29 11:37:34,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +55: [2023-04-29 11:37:34,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +38: [2023-04-29 11:37:34,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_24_mp_rank_02_optim_states.pt. +55: [2023-04-29 11:37:34,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +38: [2023-04-29 11:37:34,673] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 304 +10: [2023-04-29 11:37:34,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +29: [2023-04-29 11:37:34,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +19: [2023-04-29 11:37:34,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +19: [2023-04-29 11:37:34,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +10: [2023-04-29 11:37:34,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +28: [2023-04-29 11:37:34,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +28: [2023-04-29 11:37:34,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +29: [2023-04-29 11:37:34,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +10: [2023-04-29 11:37:34,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +28: [2023-04-29 11:37:34,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 6: [2023-04-29 11:37:34,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 6: [2023-04-29 11:37:34,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 6: [2023-04-29 11:37:34,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +14: [2023-04-29 11:37:34,677] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 6: [2023-04-29 11:37:34,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +55: [2023-04-29 11:37:34,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +55: [2023-04-29 11:37:34,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +55: [2023-04-29 11:37:34,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +55: [2023-04-29 11:37:34,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. + 4: [2023-04-29 11:37:34,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +23: [2023-04-29 11:37:34,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +14: [2023-04-29 11:37:34,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +49: [2023-04-29 11:37:34,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +49: [2023-04-29 11:37:34,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. + 4: [2023-04-29 11:37:34,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 4: [2023-04-29 11:37:34,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +49: [2023-04-29 11:37:34,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +49: [2023-04-29 11:37:34,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +24: [2023-04-29 11:37:34,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +58: [2023-04-29 11:37:34,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_104_mp_rank_02_optim_states.pt. +58: [2023-04-29 11:37:34,682] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 464 +53: [2023-04-29 11:37:34,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_87_mp_rank_03_optim_states.pt... +53: [2023-04-29 11:37:34,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_85_mp_rank_03_optim_states.pt... +53: [2023-04-29 11:37:34,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_86_mp_rank_03_optim_states.pt... +53: [2023-04-29 11:37:34,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_84_mp_rank_03_optim_states.pt... + 6: [2023-04-29 11:37:34,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 6: [2023-04-29 11:37:34,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 6: [2023-04-29 11:37:34,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 6: [2023-04-29 11:37:34,683] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +19: [2023-04-29 11:37:34,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +23: [2023-04-29 11:37:34,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 2: [2023-04-29 11:37:34,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 2: [2023-04-29 11:37:34,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 2: [2023-04-29 11:37:34,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 2: [2023-04-29 11:37:34,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 2: [2023-04-29 11:37:34,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +31: [2023-04-29 11:37:34,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +24: [2023-04-29 11:37:34,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +24: [2023-04-29 11:37:34,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +24: [2023-04-29 11:37:34,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +23: [2023-04-29 11:37:34,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +19: [2023-04-29 11:37:34,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +44: [2023-04-29 11:37:34,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_49_mp_rank_03_optim_states.pt... +44: [2023-04-29 11:37:34,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_50_mp_rank_03_optim_states.pt... +44: [2023-04-29 11:37:34,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_48_mp_rank_03_optim_states.pt... +44: [2023-04-29 11:37:34,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_51_mp_rank_03_optim_states.pt... +23: [2023-04-29 11:37:34,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +22: [2023-04-29 11:37:34,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +22: [2023-04-29 11:37:34,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +22: [2023-04-29 11:37:34,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +22: [2023-04-29 11:37:34,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +16: [2023-04-29 11:37:34,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +31: [2023-04-29 11:37:34,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +31: [2023-04-29 11:37:34,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +31: [2023-04-29 11:37:34,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +28: [2023-04-29 11:37:34,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +38: [2023-04-29 11:37:34,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_26_mp_rank_02_optim_states.pt. +38: [2023-04-29 11:37:34,695] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 308 +23: [2023-04-29 11:37:34,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +16: [2023-04-29 11:37:34,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +28: [2023-04-29 11:37:34,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +38: [2023-04-29 11:37:34,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_27_mp_rank_02_optim_states.pt. +38: [2023-04-29 11:37:34,696] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 310 +58: [2023-04-29 11:37:34,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_105_mp_rank_02_optim_states.pt. +58: [2023-04-29 11:37:34,697] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 466 +22: [2023-04-29 11:37:34,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +22: [2023-04-29 11:37:34,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +23: [2023-04-29 11:37:34,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +22: [2023-04-29 11:37:34,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +55: [2023-04-29 11:37:34,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_93_mp_rank_02_optim_states.pt. +22: [2023-04-29 11:37:34,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +55: [2023-04-29 11:37:34,699] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 442 +18: [2023-04-29 11:37:34,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +28: [2023-04-29 11:37:34,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +28: [2023-04-29 11:37:34,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +62: [2023-04-29 11:37:34,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_122_mp_rank_02_optim_states.pt. +62: [2023-04-29 11:37:34,702] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 500 +28: [2023-04-29 11:37:34,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +49: [2023-04-29 11:37:34,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +49: [2023-04-29 11:37:34,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +16: [2023-04-29 11:37:34,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +49: [2023-04-29 11:37:34,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +50: [2023-04-29 11:37:34,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +50: [2023-04-29 11:37:34,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +50: [2023-04-29 11:37:34,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +18: [2023-04-29 11:37:34,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +50: [2023-04-29 11:37:34,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +18: [2023-04-29 11:37:34,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +13: [2023-04-29 11:37:34,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +28: [2023-04-29 11:37:34,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +22: [2023-04-29 11:37:34,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +28: [2023-04-29 11:37:34,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +28: [2023-04-29 11:37:34,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +18: [2023-04-29 11:37:34,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +40: [2023-04-29 11:37:34,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_35_mp_rank_02_optim_states.pt. +40: [2023-04-29 11:37:34,707] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 326 +49: [2023-04-29 11:37:34,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +28: [2023-04-29 11:37:34,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +49: [2023-04-29 11:37:34,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +49: [2023-04-29 11:37:34,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +49: [2023-04-29 11:37:34,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +28: [2023-04-29 11:37:34,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 7: [2023-04-29 11:37:34,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +49: [2023-04-29 11:37:34,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +28: [2023-04-29 11:37:34,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +16: [2023-04-29 11:37:34,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +18: [2023-04-29 11:37:34,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +31: [2023-04-29 11:37:34,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +49: [2023-04-29 11:37:34,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +22: [2023-04-29 11:37:34,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +49: [2023-04-29 11:37:34,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +13: [2023-04-29 11:37:34,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +49: [2023-04-29 11:37:34,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +49: [2023-04-29 11:37:34,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +49: [2023-04-29 11:37:34,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +49: [2023-04-29 11:37:34,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +12: [2023-04-29 11:37:34,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +49: [2023-04-29 11:37:34,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +49: [2023-04-29 11:37:34,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +28: [2023-04-29 11:37:34,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +20: [2023-04-29 11:37:34,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +18: [2023-04-29 11:37:34,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 7: [2023-04-29 11:37:34,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +62: [2023-04-29 11:37:34,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_121_mp_rank_02_optim_states.pt. +62: [2023-04-29 11:37:34,715] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 498 +12: [2023-04-29 11:37:34,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +20: [2023-04-29 11:37:34,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +12: [2023-04-29 11:37:34,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +20: [2023-04-29 11:37:34,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +18: [2023-04-29 11:37:34,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +20: [2023-04-29 11:37:34,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +31: [2023-04-29 11:37:34,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +31: [2023-04-29 11:37:34,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +31: [2023-04-29 11:37:34,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 5: [2023-04-29 11:37:34,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +31: [2023-04-29 11:37:34,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 5: [2023-04-29 11:37:34,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 5: [2023-04-29 11:37:34,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 5: [2023-04-29 11:37:34,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 0: [2023-04-29 11:37:34,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 0: [2023-04-29 11:37:34,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +20: [2023-04-29 11:37:34,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +31: [2023-04-29 11:37:34,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 7: [2023-04-29 11:37:34,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 0: [2023-04-29 11:37:34,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 9: [2023-04-29 11:37:34,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 9: [2023-04-29 11:37:34,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 9: [2023-04-29 11:37:34,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 9: [2023-04-29 11:37:34,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 0: [2023-04-29 11:37:34,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +22: [2023-04-29 11:37:34,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +12: [2023-04-29 11:37:34,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 7: [2023-04-29 11:37:34,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +18: [2023-04-29 11:37:34,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +20: [2023-04-29 11:37:34,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +20: [2023-04-29 11:37:34,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +31: [2023-04-29 11:37:34,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +15: [2023-04-29 11:37:34,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +15: [2023-04-29 11:37:34,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +15: [2023-04-29 11:37:34,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +15: [2023-04-29 11:37:34,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +55: [2023-04-29 11:37:34,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_93_mp_rank_03_optim_states.pt... +55: [2023-04-29 11:37:34,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_94_mp_rank_03_optim_states.pt... +55: [2023-04-29 11:37:34,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_92_mp_rank_03_optim_states.pt... +55: [2023-04-29 11:37:34,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_95_mp_rank_03_optim_states.pt... +13: [2023-04-29 11:37:34,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +22: [2023-04-29 11:37:34,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +12: [2023-04-29 11:37:34,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +12: [2023-04-29 11:37:34,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +31: [2023-04-29 11:37:34,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 7: [2023-04-29 11:37:34,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 7: [2023-04-29 11:37:34,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 2: [2023-04-29 11:37:34,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 2: [2023-04-29 11:37:34,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 2: [2023-04-29 11:37:34,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 2: [2023-04-29 11:37:34,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 3: [2023-04-29 11:37:34,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 7: [2023-04-29 11:37:34,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +13: [2023-04-29 11:37:34,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +13: [2023-04-29 11:37:34,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 0: [2023-04-29 11:37:34,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 0: [2023-04-29 11:37:34,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +32: [2023-04-29 11:37:34,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_3_mp_rank_02_optim_states.pt. +22: [2023-04-29 11:37:34,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +32: [2023-04-29 11:37:34,730] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 262 +22: [2023-04-29 11:37:34,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +13: [2023-04-29 11:37:34,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +20: [2023-04-29 11:37:34,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 0: [2023-04-29 11:37:34,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 3: [2023-04-29 11:37:34,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +50: [2023-04-29 11:37:34,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +50: [2023-04-29 11:37:34,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +13: [2023-04-29 11:37:34,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +50: [2023-04-29 11:37:34,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +50: [2023-04-29 11:37:34,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +32: [2023-04-29 11:37:34,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_0_mp_rank_02_optim_states.pt. +21: [2023-04-29 11:37:34,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +32: [2023-04-29 11:37:34,732] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 256 +29: [2023-04-29 11:37:34,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +12: [2023-04-29 11:37:34,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +12: [2023-04-29 11:37:34,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +21: [2023-04-29 11:37:34,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 0: [2023-04-29 11:37:34,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +13: [2023-04-29 11:37:34,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +13: [2023-04-29 11:37:34,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +22: [2023-04-29 11:37:34,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +50: [2023-04-29 11:37:34,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +50: [2023-04-29 11:37:34,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +50: [2023-04-29 11:37:34,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +50: [2023-04-29 11:37:34,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +50: [2023-04-29 11:37:34,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +13: [2023-04-29 11:37:34,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +13: [2023-04-29 11:37:34,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 3: [2023-04-29 11:37:34,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 0: [2023-04-29 11:37:34,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +50: [2023-04-29 11:37:34,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +50: [2023-04-29 11:37:34,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +50: [2023-04-29 11:37:34,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. + 0: [2023-04-29 11:37:34,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +50: [2023-04-29 11:37:34,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +13: [2023-04-29 11:37:34,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +29: [2023-04-29 11:37:34,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 0: [2023-04-29 11:37:34,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +17: [2023-04-29 11:37:34,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +17: [2023-04-29 11:37:34,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +17: [2023-04-29 11:37:34,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +50: [2023-04-29 11:37:34,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +50: [2023-04-29 11:37:34,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +17: [2023-04-29 11:37:34,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 2: [2023-04-29 11:37:34,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +50: [2023-04-29 11:37:34,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. + 3: [2023-04-29 11:37:34,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +13: [2023-04-29 11:37:34,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +22: [2023-04-29 11:37:34,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 0: [2023-04-29 11:37:34,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 3: [2023-04-29 11:37:34,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +13: [2023-04-29 11:37:34,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +29: [2023-04-29 11:37:34,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +32: [2023-04-29 11:37:34,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_1_mp_rank_02_optim_states.pt. +13: [2023-04-29 11:37:34,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 3: [2023-04-29 11:37:34,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +32: [2023-04-29 11:37:34,741] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 258 + 3: [2023-04-29 11:37:34,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +24: [2023-04-29 11:37:34,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 3: [2023-04-29 11:37:34,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +21: [2023-04-29 11:37:34,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +13: [2023-04-29 11:37:34,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 3: [2023-04-29 11:37:34,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +29: [2023-04-29 11:37:34,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 2: [2023-04-29 11:37:34,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +26: [2023-04-29 11:37:34,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +26: [2023-04-29 11:37:34,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +26: [2023-04-29 11:37:34,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +58: [2023-04-29 11:37:34,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_107_mp_rank_02_optim_states.pt. +58: [2023-04-29 11:37:34,746] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 470 +26: [2023-04-29 11:37:34,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +29: [2023-04-29 11:37:34,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 3: [2023-04-29 11:37:34,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 6: [2023-04-29 11:37:34,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 6: [2023-04-29 11:37:34,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 3: [2023-04-29 11:37:34,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +46: [2023-04-29 11:37:34,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_56_mp_rank_02_optim_states.pt. +46: [2023-04-29 11:37:34,748] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 368 +24: [2023-04-29 11:37:34,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +49: [2023-04-29 11:37:34,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_70_mp_rank_03_optim_states.pt... +49: [2023-04-29 11:37:34,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_71_mp_rank_03_optim_states.pt... +49: [2023-04-29 11:37:34,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_68_mp_rank_03_optim_states.pt... +49: [2023-04-29 11:37:34,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_69_mp_rank_03_optim_states.pt... +21: [2023-04-29 11:37:34,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +31: [2023-04-29 11:37:34,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 3: [2023-04-29 11:37:34,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +62: [2023-04-29 11:37:34,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. + 5: [2023-04-29 11:37:34,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +62: [2023-04-29 11:37:34,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +62: [2023-04-29 11:37:34,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. + 5: [2023-04-29 11:37:34,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +62: [2023-04-29 11:37:34,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +29: [2023-04-29 11:37:34,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 0: [2023-04-29 11:37:34,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +29: [2023-04-29 11:37:34,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +31: [2023-04-29 11:37:34,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +31: [2023-04-29 11:37:34,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +15: [2023-04-29 11:37:34,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +15: [2023-04-29 11:37:34,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. +31: [2023-04-29 11:37:34,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +15: [2023-04-29 11:37:34,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 9: [2023-04-29 11:37:34,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 6: [2023-04-29 11:37:34,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 0: [2023-04-29 11:37:34,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 0: [2023-04-29 11:37:34,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 0: [2023-04-29 11:37:34,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +14: [2023-04-29 11:37:34,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +14: [2023-04-29 11:37:34,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +14: [2023-04-29 11:37:34,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +14: [2023-04-29 11:37:34,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 9: [2023-04-29 11:37:34,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +33: [2023-04-29 11:37:34,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_4_mp_rank_02_optim_states.pt. +33: [2023-04-29 11:37:34,754] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 264 + 6: [2023-04-29 11:37:34,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 5: [2023-04-29 11:37:34,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 5: [2023-04-29 11:37:34,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 2: [2023-04-29 11:37:34,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 2: [2023-04-29 11:37:34,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +15: [2023-04-29 11:37:34,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +15: [2023-04-29 11:37:34,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +15: [2023-04-29 11:37:34,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_17-model_01-model_states.pt. + 9: [2023-04-29 11:37:34,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 9: [2023-04-29 11:37:34,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +24: [2023-04-29 11:37:34,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +24: [2023-04-29 11:37:34,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +24: [2023-04-29 11:37:34,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +29: [2023-04-29 11:37:34,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 3: [2023-04-29 11:37:34,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 3: [2023-04-29 11:37:34,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +17: [2023-04-29 11:37:34,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +21: [2023-04-29 11:37:34,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +15: [2023-04-29 11:37:34,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +15: [2023-04-29 11:37:34,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +16: [2023-04-29 11:37:34,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +16: [2023-04-29 11:37:34,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +21: [2023-04-29 11:37:34,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +24: [2023-04-29 11:37:34,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +24: [2023-04-29 11:37:34,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +17: [2023-04-29 11:37:34,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +24: [2023-04-29 11:37:34,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +46: [2023-04-29 11:37:34,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_56_mp_rank_03_optim_states.pt... +46: [2023-04-29 11:37:34,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_58_mp_rank_03_optim_states.pt... +46: [2023-04-29 11:37:34,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_57_mp_rank_03_optim_states.pt... +46: [2023-04-29 11:37:34,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_59_mp_rank_03_optim_states.pt... +22: [2023-04-29 11:37:34,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +54: [2023-04-29 11:37:34,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_88_mp_rank_03_optim_states.pt. +54: [2023-04-29 11:37:34,767] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 433 +17: [2023-04-29 11:37:34,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +17: [2023-04-29 11:37:34,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 3: [2023-04-29 11:37:34,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 3: [2023-04-29 11:37:34,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +16: [2023-04-29 11:37:34,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +16: [2023-04-29 11:37:34,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +50: [2023-04-29 11:37:34,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_72_mp_rank_03_optim_states.pt... +50: [2023-04-29 11:37:34,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_74_mp_rank_03_optim_states.pt... +50: [2023-04-29 11:37:34,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_73_mp_rank_03_optim_states.pt... +50: [2023-04-29 11:37:34,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_75_mp_rank_03_optim_states.pt... + 6: [2023-04-29 11:37:34,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +22: [2023-04-29 11:37:34,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +16: [2023-04-29 11:37:34,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +16: [2023-04-29 11:37:34,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +21: [2023-04-29 11:37:34,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +16: [2023-04-29 11:37:34,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +26: [2023-04-29 11:37:34,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 6: [2023-04-29 11:37:34,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +16: [2023-04-29 11:37:34,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +22: [2023-04-29 11:37:34,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +22: [2023-04-29 11:37:34,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +26: [2023-04-29 11:37:34,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 8: [2023-04-29 11:37:34,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 8: [2023-04-29 11:37:34,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +24: [2023-04-29 11:37:34,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +24: [2023-04-29 11:37:34,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +26: [2023-04-29 11:37:34,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 8: [2023-04-29 11:37:34,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +24: [2023-04-29 11:37:34,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 8: [2023-04-29 11:37:34,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 8: [2023-04-29 11:37:34,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 8: [2023-04-29 11:37:34,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 8: [2023-04-29 11:37:34,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +21: [2023-04-29 11:37:34,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 8: [2023-04-29 11:37:34,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +24: [2023-04-29 11:37:34,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +26: [2023-04-29 11:37:34,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +29: [2023-04-29 11:37:34,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +29: [2023-04-29 11:37:34,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +35: [2023-04-29 11:37:34,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +35: [2023-04-29 11:37:34,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +29: [2023-04-29 11:37:34,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +29: [2023-04-29 11:37:34,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +14: [2023-04-29 11:37:34,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 1: [2023-04-29 11:37:34,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 1: [2023-04-29 11:37:34,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 1: [2023-04-29 11:37:34,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 1: [2023-04-29 11:37:34,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 6: [2023-04-29 11:37:34,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 6: [2023-04-29 11:37:34,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +16: [2023-04-29 11:37:34,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +24: [2023-04-29 11:37:34,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +24: [2023-04-29 11:37:34,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +24: [2023-04-29 11:37:34,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +14: [2023-04-29 11:37:34,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +46: [2023-04-29 11:37:34,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_58_mp_rank_02_optim_states.pt. +46: [2023-04-29 11:37:34,784] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 372 + 8: [2023-04-29 11:37:34,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 8: [2023-04-29 11:37:34,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +24: [2023-04-29 11:37:34,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +14: [2023-04-29 11:37:34,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +14: [2023-04-29 11:37:34,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +35: [2023-04-29 11:37:34,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. + 1: [2023-04-29 11:37:34,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +16: [2023-04-29 11:37:34,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +16: [2023-04-29 11:37:34,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 1: [2023-04-29 11:37:34,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 1: [2023-04-29 11:37:34,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +29: [2023-04-29 11:37:34,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +29: [2023-04-29 11:37:34,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +29: [2023-04-29 11:37:34,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +62: [2023-04-29 11:37:34,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +29: [2023-04-29 11:37:34,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +16: [2023-04-29 11:37:34,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +15: [2023-04-29 11:37:34,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +62: [2023-04-29 11:37:34,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +62: [2023-04-29 11:37:34,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +62: [2023-04-29 11:37:34,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +62: [2023-04-29 11:37:34,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +62: [2023-04-29 11:37:34,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... + 1: [2023-04-29 11:37:34,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +15: [2023-04-29 11:37:34,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +15: [2023-04-29 11:37:34,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... +15: [2023-04-29 11:37:34,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt... + 8: [2023-04-29 11:37:34,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +54: [2023-04-29 11:37:34,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_89_mp_rank_03_optim_states.pt. +54: [2023-04-29 11:37:34,789] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 435 +16: [2023-04-29 11:37:34,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +62: [2023-04-29 11:37:34,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +62: [2023-04-29 11:37:34,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +62: [2023-04-29 11:37:34,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +62: [2023-04-29 11:37:34,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +62: [2023-04-29 11:37:34,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +62: [2023-04-29 11:37:34,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +62: [2023-04-29 11:37:34,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. + 8: [2023-04-29 11:37:34,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +62: [2023-04-29 11:37:34,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +62: [2023-04-29 11:37:34,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +16: [2023-04-29 11:37:34,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +62: [2023-04-29 11:37:34,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +35: [2023-04-29 11:37:34,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +17: [2023-04-29 11:37:34,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +17: [2023-04-29 11:37:34,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +17: [2023-04-29 11:37:34,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +17: [2023-04-29 11:37:34,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +16: [2023-04-29 11:37:34,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +13: [2023-04-29 11:37:34,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +13: [2023-04-29 11:37:34,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +17: [2023-04-29 11:37:34,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +17: [2023-04-29 11:37:34,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +17: [2023-04-29 11:37:34,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +17: [2023-04-29 11:37:34,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +22: [2023-04-29 11:37:34,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +16: [2023-04-29 11:37:34,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +33: [2023-04-29 11:37:34,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_5_mp_rank_02_optim_states.pt. +33: [2023-04-29 11:37:34,803] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 266 +47: [2023-04-29 11:37:34,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +47: [2023-04-29 11:37:34,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +47: [2023-04-29 11:37:34,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +47: [2023-04-29 11:37:34,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +13: [2023-04-29 11:37:34,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +13: [2023-04-29 11:37:34,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +22: [2023-04-29 11:37:34,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 8: [2023-04-29 11:37:34,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +22: [2023-04-29 11:37:34,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +35: [2023-04-29 11:37:34,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +35: [2023-04-29 11:37:34,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +22: [2023-04-29 11:37:34,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +35: [2023-04-29 11:37:34,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +35: [2023-04-29 11:37:34,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +35: [2023-04-29 11:37:34,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +35: [2023-04-29 11:37:34,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +63: [2023-04-29 11:37:34,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_125_mp_rank_02_optim_states.pt. +63: [2023-04-29 11:37:34,812] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 506 + 0: [2023-04-29 11:37:34,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 8: [2023-04-29 11:37:34,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 6: [2023-04-29 11:37:34,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 6: [2023-04-29 11:37:34,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 6: [2023-04-29 11:37:34,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 6: [2023-04-29 11:37:34,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +31: [2023-04-29 11:37:34,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 5: [2023-04-29 11:37:34,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +17: [2023-04-29 11:37:34,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 0: [2023-04-29 11:37:34,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 0: [2023-04-29 11:37:34,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 0: [2023-04-29 11:37:34,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 8: [2023-04-29 11:37:34,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 8: [2023-04-29 11:37:34,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 0: [2023-04-29 11:37:34,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +35: [2023-04-29 11:37:34,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +35: [2023-04-29 11:37:34,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +17: [2023-04-29 11:37:34,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 9: [2023-04-29 11:37:34,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 9: [2023-04-29 11:37:34,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +35: [2023-04-29 11:37:34,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +35: [2023-04-29 11:37:34,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +31: [2023-04-29 11:37:34,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 5: [2023-04-29 11:37:34,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +31: [2023-04-29 11:37:34,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +31: [2023-04-29 11:37:34,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +31: [2023-04-29 11:37:34,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +33: [2023-04-29 11:37:34,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_6_mp_rank_02_optim_states.pt. +54: [2023-04-29 11:37:34,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_91_mp_rank_03_optim_states.pt. +54: [2023-04-29 11:37:34,823] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 439 +33: [2023-04-29 11:37:34,823] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 268 +13: [2023-04-29 11:37:34,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 5: [2023-04-29 11:37:34,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +35: [2023-04-29 11:37:34,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +35: [2023-04-29 11:37:34,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +18: [2023-04-29 11:37:34,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +18: [2023-04-29 11:37:34,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 0: [2023-04-29 11:37:34,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +13: [2023-04-29 11:37:34,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 9: [2023-04-29 11:37:34,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +35: [2023-04-29 11:37:34,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +35: [2023-04-29 11:37:34,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +48: [2023-04-29 11:37:34,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +48: [2023-04-29 11:37:34,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +48: [2023-04-29 11:37:34,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +35: [2023-04-29 11:37:34,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. + 9: [2023-04-29 11:37:34,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +48: [2023-04-29 11:37:34,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +35: [2023-04-29 11:37:34,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. + 9: [2023-04-29 11:37:34,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 9: [2023-04-29 11:37:34,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 0: [2023-04-29 11:37:34,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 0: [2023-04-29 11:37:34,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 0: [2023-04-29 11:37:34,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +31: [2023-04-29 11:37:34,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +31: [2023-04-29 11:37:34,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +31: [2023-04-29 11:37:34,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +18: [2023-04-29 11:37:34,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +18: [2023-04-29 11:37:34,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +45: [2023-04-29 11:37:34,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_53_mp_rank_02_optim_states.pt. +45: [2023-04-29 11:37:34,829] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 362 + 5: [2023-04-29 11:37:34,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +47: [2023-04-29 11:37:34,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 9: [2023-04-29 11:37:34,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 9: [2023-04-29 11:37:34,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +47: [2023-04-29 11:37:34,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +18: [2023-04-29 11:37:34,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 5: [2023-04-29 11:37:34,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 5: [2023-04-29 11:37:34,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +18: [2023-04-29 11:37:34,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +34: [2023-04-29 11:37:34,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_10_mp_rank_02_optim_states.pt. +47: [2023-04-29 11:37:34,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +34: [2023-04-29 11:37:34,832] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 276 +17: [2023-04-29 11:37:34,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +47: [2023-04-29 11:37:34,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +18: [2023-04-29 11:37:34,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +47: [2023-04-29 11:37:34,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +47: [2023-04-29 11:37:34,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +25: [2023-04-29 11:37:34,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +25: [2023-04-29 11:37:34,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +47: [2023-04-29 11:37:34,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +25: [2023-04-29 11:37:34,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +18: [2023-04-29 11:37:34,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +25: [2023-04-29 11:37:34,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +47: [2023-04-29 11:37:34,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +24: [2023-04-29 11:37:34,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +47: [2023-04-29 11:37:34,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +47: [2023-04-29 11:37:34,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +33: [2023-04-29 11:37:34,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_7_mp_rank_02_optim_states.pt. + 0: [2023-04-29 11:37:34,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +33: [2023-04-29 11:37:34,835] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 270 +47: [2023-04-29 11:37:34,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. + 0: [2023-04-29 11:37:34,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +47: [2023-04-29 11:37:34,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +13: [2023-04-29 11:37:34,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 0: [2023-04-29 11:37:34,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +62: [2023-04-29 11:37:34,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_123_mp_rank_03_optim_states.pt... +32: [2023-04-29 11:37:34,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +32: [2023-04-29 11:37:34,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +62: [2023-04-29 11:37:34,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_121_mp_rank_03_optim_states.pt... +62: [2023-04-29 11:37:34,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_120_mp_rank_03_optim_states.pt... +62: [2023-04-29 11:37:34,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_122_mp_rank_03_optim_states.pt... +32: [2023-04-29 11:37:34,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +32: [2023-04-29 11:37:34,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +17: [2023-04-29 11:37:34,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 5: [2023-04-29 11:37:34,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... + 5: [2023-04-29 11:37:34,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +45: [2023-04-29 11:37:34,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_52_mp_rank_02_optim_states.pt. +45: [2023-04-29 11:37:34,838] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 360 +24: [2023-04-29 11:37:34,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +13: [2023-04-29 11:37:34,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +14: [2023-04-29 11:37:34,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +17: [2023-04-29 11:37:34,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +26: [2023-04-29 11:37:34,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +26: [2023-04-29 11:37:34,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 0: [2023-04-29 11:37:34,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 6: [2023-04-29 11:37:34,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +63: [2023-04-29 11:37:34,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. + 6: [2023-04-29 11:37:34,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +63: [2023-04-29 11:37:34,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +63: [2023-04-29 11:37:34,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +63: [2023-04-29 11:37:34,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. + 0: [2023-04-29 11:37:34,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +47: [2023-04-29 11:37:34,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +47: [2023-04-29 11:37:34,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +47: [2023-04-29 11:37:34,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +47: [2023-04-29 11:37:34,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. + 6: [2023-04-29 11:37:34,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +17: [2023-04-29 11:37:34,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 0: [2023-04-29 11:37:34,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +63: [2023-04-29 11:37:34,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_126_mp_rank_02_optim_states.pt. + 6: [2023-04-29 11:37:34,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +63: [2023-04-29 11:37:34,847] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 508 +14: [2023-04-29 11:37:34,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +24: [2023-04-29 11:37:34,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +24: [2023-04-29 11:37:34,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +26: [2023-04-29 11:37:34,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +26: [2023-04-29 11:37:34,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +17: [2023-04-29 11:37:34,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 1: [2023-04-29 11:37:34,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 8: [2023-04-29 11:37:34,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +26: [2023-04-29 11:37:34,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +48: [2023-04-29 11:37:34,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +15: [2023-04-29 11:37:34,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +15: [2023-04-29 11:37:34,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +34: [2023-04-29 11:37:34,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_8_mp_rank_02_optim_states.pt. +34: [2023-04-29 11:37:34,854] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 272 +48: [2023-04-29 11:37:34,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. + 1: [2023-04-29 11:37:34,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +26: [2023-04-29 11:37:34,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 0: [2023-04-29 11:37:34,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +17: [2023-04-29 11:37:34,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +48: [2023-04-29 11:37:34,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +14: [2023-04-29 11:37:34,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +48: [2023-04-29 11:37:34,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 1: [2023-04-29 11:37:34,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +48: [2023-04-29 11:37:34,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +48: [2023-04-29 11:37:34,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +14: [2023-04-29 11:37:34,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +29: [2023-04-29 11:37:34,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +29: [2023-04-29 11:37:34,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +48: [2023-04-29 11:37:34,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +48: [2023-04-29 11:37:34,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +36: [2023-04-29 11:37:34,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +48: [2023-04-29 11:37:34,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +48: [2023-04-29 11:37:34,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +26: [2023-04-29 11:37:34,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +48: [2023-04-29 11:37:34,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +36: [2023-04-29 11:37:34,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +36: [2023-04-29 11:37:34,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +15: [2023-04-29 11:37:34,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +15: [2023-04-29 11:37:34,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +48: [2023-04-29 11:37:34,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +48: [2023-04-29 11:37:34,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +14: [2023-04-29 11:37:34,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +29: [2023-04-29 11:37:34,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +29: [2023-04-29 11:37:34,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +48: [2023-04-29 11:37:34,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +48: [2023-04-29 11:37:34,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +48: [2023-04-29 11:37:34,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +26: [2023-04-29 11:37:34,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +15: [2023-04-29 11:37:34,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. + 1: [2023-04-29 11:37:34,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 8: [2023-04-29 11:37:34,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +24: [2023-04-29 11:37:34,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +25: [2023-04-29 11:37:34,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +36: [2023-04-29 11:37:34,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +14: [2023-04-29 11:37:34,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +16: [2023-04-29 11:37:34,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +16: [2023-04-29 11:37:34,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +16: [2023-04-29 11:37:34,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +25: [2023-04-29 11:37:34,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +25: [2023-04-29 11:37:34,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +14: [2023-04-29 11:37:34,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +25: [2023-04-29 11:37:34,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +46: [2023-04-29 11:37:34,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_59_mp_rank_02_optim_states.pt. +32: [2023-04-29 11:37:34,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +46: [2023-04-29 11:37:34,865] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 374 +32: [2023-04-29 11:37:34,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +15: [2023-04-29 11:37:34,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_00-model_states.pt. +14: [2023-04-29 11:37:34,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +32: [2023-04-29 11:37:34,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +32: [2023-04-29 11:37:34,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +17: [2023-04-29 11:37:34,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +32: [2023-04-29 11:37:34,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +32: [2023-04-29 11:37:34,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +32: [2023-04-29 11:37:34,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +15: [2023-04-29 11:37:34,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +27: [2023-04-29 11:37:34,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +27: [2023-04-29 11:37:34,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +32: [2023-04-29 11:37:34,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +32: [2023-04-29 11:37:34,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +27: [2023-04-29 11:37:34,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +27: [2023-04-29 11:37:34,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +35: [2023-04-29 11:37:34,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_14_mp_rank_02_optim_states.pt. +16: [2023-04-29 11:37:34,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +35: [2023-04-29 11:37:34,868] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 284 +32: [2023-04-29 11:37:34,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +24: [2023-04-29 11:37:34,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +32: [2023-04-29 11:37:34,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +32: [2023-04-29 11:37:34,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... + 1: [2023-04-29 11:37:34,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 1: [2023-04-29 11:37:34,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 1: [2023-04-29 11:37:34,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +15: [2023-04-29 11:37:34,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt... +17: [2023-04-29 11:37:34,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +17: [2023-04-29 11:37:34,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +17: [2023-04-29 11:37:34,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 1: [2023-04-29 11:37:34,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +63: [2023-04-29 11:37:34,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +63: [2023-04-29 11:37:34,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +57: [2023-04-29 11:37:34,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +57: [2023-04-29 11:37:34,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +24: [2023-04-29 11:37:34,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +57: [2023-04-29 11:37:34,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. + 1: [2023-04-29 11:37:34,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 8: [2023-04-29 11:37:34,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +63: [2023-04-29 11:37:34,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +57: [2023-04-29 11:37:34,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +63: [2023-04-29 11:37:34,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +63: [2023-04-29 11:37:34,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +63: [2023-04-29 11:37:34,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +63: [2023-04-29 11:37:34,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +63: [2023-04-29 11:37:34,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +24: [2023-04-29 11:37:34,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +63: [2023-04-29 11:37:34,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +63: [2023-04-29 11:37:34,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +63: [2023-04-29 11:37:34,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +63: [2023-04-29 11:37:34,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... + 1: [2023-04-29 11:37:34,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +32: [2023-04-29 11:37:34,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +32: [2023-04-29 11:37:34,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +32: [2023-04-29 11:37:34,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +32: [2023-04-29 11:37:34,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +11: [2023-04-29 11:37:34,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +11: [2023-04-29 11:37:34,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +11: [2023-04-29 11:37:34,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +11: [2023-04-29 11:37:34,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +23: [2023-04-29 11:37:34,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +23: [2023-04-29 11:37:34,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +63: [2023-04-29 11:37:34,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +63: [2023-04-29 11:37:34,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +63: [2023-04-29 11:37:34,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +63: [2023-04-29 11:37:34,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +23: [2023-04-29 11:37:34,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +23: [2023-04-29 11:37:34,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 8: [2023-04-29 11:37:34,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +58: [2023-04-29 11:37:34,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +58: [2023-04-29 11:37:34,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +58: [2023-04-29 11:37:34,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +58: [2023-04-29 11:37:34,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +47: [2023-04-29 11:37:34,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_61_mp_rank_03_optim_states.pt... +47: [2023-04-29 11:37:34,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_60_mp_rank_03_optim_states.pt... +47: [2023-04-29 11:37:34,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_63_mp_rank_03_optim_states.pt... +47: [2023-04-29 11:37:34,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_62_mp_rank_03_optim_states.pt... +36: [2023-04-29 11:37:34,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +36: [2023-04-29 11:37:34,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +36: [2023-04-29 11:37:34,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +36: [2023-04-29 11:37:34,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +51: [2023-04-29 11:37:34,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +51: [2023-04-29 11:37:34,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +51: [2023-04-29 11:37:34,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +36: [2023-04-29 11:37:34,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +51: [2023-04-29 11:37:34,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +36: [2023-04-29 11:37:34,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. + 1: [2023-04-29 11:37:34,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 8: [2023-04-29 11:37:34,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +23: [2023-04-29 11:37:34,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +63: [2023-04-29 11:37:34,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_127_mp_rank_02_optim_states.pt. +63: [2023-04-29 11:37:34,888] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 510 +29: [2023-04-29 11:37:34,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +23: [2023-04-29 11:37:34,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +23: [2023-04-29 11:37:34,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +23: [2023-04-29 11:37:34,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 1: [2023-04-29 11:37:34,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +41: [2023-04-29 11:37:34,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_39_mp_rank_02_optim_states.pt. +41: [2023-04-29 11:37:34,890] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 334 +29: [2023-04-29 11:37:34,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 8: [2023-04-29 11:37:34,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +29: [2023-04-29 11:37:34,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +29: [2023-04-29 11:37:34,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 8: [2023-04-29 11:37:34,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +41: [2023-04-29 11:37:34,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +41: [2023-04-29 11:37:34,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +36: [2023-04-29 11:37:34,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +36: [2023-04-29 11:37:34,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +41: [2023-04-29 11:37:34,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +41: [2023-04-29 11:37:34,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +41: [2023-04-29 11:37:34,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_37_mp_rank_02_optim_states.pt. +41: [2023-04-29 11:37:34,897] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 330 +25: [2023-04-29 11:37:34,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +25: [2023-04-29 11:37:34,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +16: [2023-04-29 11:37:34,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +18: [2023-04-29 11:37:34,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 8: [2023-04-29 11:37:34,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +17: [2023-04-29 11:37:34,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +16: [2023-04-29 11:37:34,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +25: [2023-04-29 11:37:34,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +27: [2023-04-29 11:37:34,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +27: [2023-04-29 11:37:34,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +25: [2023-04-29 11:37:34,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 8: [2023-04-29 11:37:34,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 1: [2023-04-29 11:37:34,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 1: [2023-04-29 11:37:34,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +27: [2023-04-29 11:37:34,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +36: [2023-04-29 11:37:34,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +36: [2023-04-29 11:37:34,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +36: [2023-04-29 11:37:34,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +36: [2023-04-29 11:37:34,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +35: [2023-04-29 11:37:34,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_13_mp_rank_02_optim_states.pt. +16: [2023-04-29 11:37:34,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 1: [2023-04-29 11:37:34,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +35: [2023-04-29 11:37:34,901] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 282 +25: [2023-04-29 11:37:34,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +56: [2023-04-29 11:37:34,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_98_mp_rank_02_optim_states.pt. +56: [2023-04-29 11:37:34,903] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 452 +48: [2023-04-29 11:37:34,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_64_mp_rank_03_optim_states.pt... +48: [2023-04-29 11:37:34,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_65_mp_rank_03_optim_states.pt... +48: [2023-04-29 11:37:34,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_66_mp_rank_03_optim_states.pt... +48: [2023-04-29 11:37:34,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_67_mp_rank_03_optim_states.pt... +25: [2023-04-29 11:37:34,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +27: [2023-04-29 11:37:34,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +25: [2023-04-29 11:37:34,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +36: [2023-04-29 11:37:34,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +36: [2023-04-29 11:37:34,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +36: [2023-04-29 11:37:34,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +57: [2023-04-29 11:37:34,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +18: [2023-04-29 11:37:34,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +18: [2023-04-29 11:37:34,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 6: [2023-04-29 11:37:34,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +36: [2023-04-29 11:37:34,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +59: [2023-04-29 11:37:34,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +59: [2023-04-29 11:37:34,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +59: [2023-04-29 11:37:34,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +57: [2023-04-29 11:37:34,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +18: [2023-04-29 11:37:34,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +25: [2023-04-29 11:37:34,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 8: [2023-04-29 11:37:34,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +16: [2023-04-29 11:37:34,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +17: [2023-04-29 11:37:34,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 1: [2023-04-29 11:37:34,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +17: [2023-04-29 11:37:34,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +17: [2023-04-29 11:37:34,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +11: [2023-04-29 11:37:34,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 6: [2023-04-29 11:37:34,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +57: [2023-04-29 11:37:34,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +57: [2023-04-29 11:37:34,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +57: [2023-04-29 11:37:34,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +57: [2023-04-29 11:37:34,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +57: [2023-04-29 11:37:34,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. + 8: [2023-04-29 11:37:34,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +39: [2023-04-29 11:37:34,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_29_mp_rank_02_optim_states.pt. +57: [2023-04-29 11:37:34,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +39: [2023-04-29 11:37:34,910] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 314 + 6: [2023-04-29 11:37:34,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +57: [2023-04-29 11:37:34,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +57: [2023-04-29 11:37:34,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +57: [2023-04-29 11:37:34,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +57: [2023-04-29 11:37:34,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +11: [2023-04-29 11:37:34,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +11: [2023-04-29 11:37:34,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +11: [2023-04-29 11:37:34,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 8: [2023-04-29 11:37:34,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +51: [2023-04-29 11:37:34,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +51: [2023-04-29 11:37:34,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +57: [2023-04-29 11:37:34,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +51: [2023-04-29 11:37:34,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +57: [2023-04-29 11:37:34,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +57: [2023-04-29 11:37:34,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +51: [2023-04-29 11:37:34,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. + 6: [2023-04-29 11:37:34,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +58: [2023-04-29 11:37:34,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +58: [2023-04-29 11:37:34,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +58: [2023-04-29 11:37:34,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +58: [2023-04-29 11:37:34,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +39: [2023-04-29 11:37:34,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_31_mp_rank_02_optim_states.pt. +58: [2023-04-29 11:37:34,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +58: [2023-04-29 11:37:34,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. + 6: [2023-04-29 11:37:34,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 6: [2023-04-29 11:37:34,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +51: [2023-04-29 11:37:34,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +58: [2023-04-29 11:37:34,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +39: [2023-04-29 11:37:34,916] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 318 +57: [2023-04-29 11:37:34,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +51: [2023-04-29 11:37:34,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +59: [2023-04-29 11:37:34,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_109_mp_rank_02_optim_states.pt. +58: [2023-04-29 11:37:34,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +58: [2023-04-29 11:37:34,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +59: [2023-04-29 11:37:34,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +58: [2023-04-29 11:37:34,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +59: [2023-04-29 11:37:34,917] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 474 +58: [2023-04-29 11:37:34,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. + 8: [2023-04-29 11:37:34,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +58: [2023-04-29 11:37:34,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +32: [2023-04-29 11:37:34,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_3_mp_rank_03_optim_states.pt... +32: [2023-04-29 11:37:34,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_0_mp_rank_03_optim_states.pt... +32: [2023-04-29 11:37:34,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_2_mp_rank_03_optim_states.pt... +32: [2023-04-29 11:37:34,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_1_mp_rank_03_optim_states.pt... +58: [2023-04-29 11:37:34,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +58: [2023-04-29 11:37:34,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +58: [2023-04-29 11:37:34,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +58: [2023-04-29 11:37:34,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +35: [2023-04-29 11:37:34,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_12_mp_rank_02_optim_states.pt. +51: [2023-04-29 11:37:34,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +35: [2023-04-29 11:37:34,920] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 280 +18: [2023-04-29 11:37:34,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +51: [2023-04-29 11:37:34,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +51: [2023-04-29 11:37:34,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +51: [2023-04-29 11:37:34,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +51: [2023-04-29 11:37:34,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +42: [2023-04-29 11:37:34,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +42: [2023-04-29 11:37:34,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +42: [2023-04-29 11:37:34,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +51: [2023-04-29 11:37:34,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +51: [2023-04-29 11:37:34,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... + 8: [2023-04-29 11:37:34,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +51: [2023-04-29 11:37:34,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +51: [2023-04-29 11:37:34,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +41: [2023-04-29 11:37:34,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +42: [2023-04-29 11:37:34,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +35: [2023-04-29 11:37:34,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_12_mp_rank_03_optim_states.pt... +35: [2023-04-29 11:37:34,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_13_mp_rank_03_optim_states.pt... +35: [2023-04-29 11:37:34,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_14_mp_rank_03_optim_states.pt... +51: [2023-04-29 11:37:34,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +35: [2023-04-29 11:37:34,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_15_mp_rank_03_optim_states.pt... +41: [2023-04-29 11:37:34,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +41: [2023-04-29 11:37:34,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +41: [2023-04-29 11:37:34,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. + 6: [2023-04-29 11:37:34,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 6: [2023-04-29 11:37:34,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +63: [2023-04-29 11:37:34,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_126_mp_rank_03_optim_states.pt... +63: [2023-04-29 11:37:34,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_124_mp_rank_03_optim_states.pt... +63: [2023-04-29 11:37:34,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_125_mp_rank_03_optim_states.pt... +63: [2023-04-29 11:37:34,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_127_mp_rank_03_optim_states.pt... + 8: [2023-04-29 11:37:34,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +34: [2023-04-29 11:37:34,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_9_mp_rank_02_optim_states.pt. +34: [2023-04-29 11:37:34,924] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 274 +25: [2023-04-29 11:37:34,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +41: [2023-04-29 11:37:34,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +41: [2023-04-29 11:37:34,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. + 8: [2023-04-29 11:37:34,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +41: [2023-04-29 11:37:34,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +59: [2023-04-29 11:37:34,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +41: [2023-04-29 11:37:34,931] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +59: [2023-04-29 11:37:34,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +59: [2023-04-29 11:37:34,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +41: [2023-04-29 11:37:34,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +41: [2023-04-29 11:37:34,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +41: [2023-04-29 11:37:34,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +41: [2023-04-29 11:37:34,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +59: [2023-04-29 11:37:34,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +59: [2023-04-29 11:37:34,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +25: [2023-04-29 11:37:34,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +59: [2023-04-29 11:37:34,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +12: [2023-04-29 11:37:34,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +12: [2023-04-29 11:37:34,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +59: [2023-04-29 11:37:34,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +59: [2023-04-29 11:37:34,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +59: [2023-04-29 11:37:34,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +25: [2023-04-29 11:37:34,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +12: [2023-04-29 11:37:34,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +12: [2023-04-29 11:37:34,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +25: [2023-04-29 11:37:34,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +25: [2023-04-29 11:37:34,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +61: [2023-04-29 11:37:34,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_116_mp_rank_02_optim_states.pt. +18: [2023-04-29 11:37:34,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +18: [2023-04-29 11:37:34,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +12: [2023-04-29 11:37:34,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +45: [2023-04-29 11:37:34,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +12: [2023-04-29 11:37:34,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +45: [2023-04-29 11:37:34,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +45: [2023-04-29 11:37:34,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +25: [2023-04-29 11:37:34,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +18: [2023-04-29 11:37:34,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +61: [2023-04-29 11:37:34,938] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 488 +41: [2023-04-29 11:37:34,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_38_mp_rank_02_optim_states.pt. +25: [2023-04-29 11:37:34,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +41: [2023-04-29 11:37:34,943] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 332 +25: [2023-04-29 11:37:34,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +59: [2023-04-29 11:37:34,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +59: [2023-04-29 11:37:34,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +59: [2023-04-29 11:37:34,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +12: [2023-04-29 11:37:34,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +45: [2023-04-29 11:37:34,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +41: [2023-04-29 11:37:34,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +41: [2023-04-29 11:37:34,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +41: [2023-04-29 11:37:34,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +41: [2023-04-29 11:37:34,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +12: [2023-04-29 11:37:34,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +59: [2023-04-29 11:37:34,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +59: [2023-04-29 11:37:34,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +59: [2023-04-29 11:37:34,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +42: [2023-04-29 11:37:34,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +59: [2023-04-29 11:37:34,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +42: [2023-04-29 11:37:34,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +35: [2023-04-29 11:37:34,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_15_mp_rank_02_optim_states.pt. +35: [2023-04-29 11:37:34,948] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 286 +45: [2023-04-29 11:37:34,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_54_mp_rank_02_optim_states.pt. +45: [2023-04-29 11:37:34,948] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 364 +10: [2023-04-29 11:37:34,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +10: [2023-04-29 11:37:34,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 2: [2023-04-29 11:37:34,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 2: [2023-04-29 11:37:34,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +10: [2023-04-29 11:37:34,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +10: [2023-04-29 11:37:34,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +30: [2023-04-29 11:37:34,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +30: [2023-04-29 11:37:34,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +30: [2023-04-29 11:37:34,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 2: [2023-04-29 11:37:34,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +21: [2023-04-29 11:37:34,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +21: [2023-04-29 11:37:34,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +30: [2023-04-29 11:37:34,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +21: [2023-04-29 11:37:34,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 2: [2023-04-29 11:37:34,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +21: [2023-04-29 11:37:34,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +42: [2023-04-29 11:37:34,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +42: [2023-04-29 11:37:34,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +23: [2023-04-29 11:37:34,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +42: [2023-04-29 11:37:34,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +42: [2023-04-29 11:37:34,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +60: [2023-04-29 11:37:34,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_113_mp_rank_02_optim_states.pt. +60: [2023-04-29 11:37:34,955] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 482 +10: [2023-04-29 11:37:34,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +10: [2023-04-29 11:37:34,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +38: [2023-04-29 11:37:34,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +38: [2023-04-29 11:37:34,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +10: [2023-04-29 11:37:34,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +10: [2023-04-29 11:37:34,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +38: [2023-04-29 11:37:34,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +42: [2023-04-29 11:37:34,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +38: [2023-04-29 11:37:34,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +42: [2023-04-29 11:37:34,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +33: [2023-04-29 11:37:34,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +33: [2023-04-29 11:37:34,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +33: [2023-04-29 11:37:34,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +33: [2023-04-29 11:37:34,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +60: [2023-04-29 11:37:34,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_114_mp_rank_02_optim_states.pt. +60: [2023-04-29 11:37:34,959] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 484 +60: [2023-04-29 11:37:34,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_112_mp_rank_02_optim_states.pt. +60: [2023-04-29 11:37:34,959] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 480 +42: [2023-04-29 11:37:34,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_42_mp_rank_02_optim_states.pt. +36: [2023-04-29 11:37:34,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_19_mp_rank_02_optim_states.pt. +42: [2023-04-29 11:37:34,960] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 340 +36: [2023-04-29 11:37:34,960] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 294 +46: [2023-04-29 11:37:34,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_57_mp_rank_02_optim_states.pt. +46: [2023-04-29 11:37:34,961] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 370 +27: [2023-04-29 11:37:34,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +61: [2023-04-29 11:37:34,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_119_mp_rank_02_optim_states.pt. +61: [2023-04-29 11:37:34,962] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 494 +23: [2023-04-29 11:37:34,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +23: [2023-04-29 11:37:34,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +23: [2023-04-29 11:37:34,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +42: [2023-04-29 11:37:34,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +42: [2023-04-29 11:37:34,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +42: [2023-04-29 11:37:34,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +42: [2023-04-29 11:37:34,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +61: [2023-04-29 11:37:34,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_117_mp_rank_02_optim_states.pt. +61: [2023-04-29 11:37:34,963] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 490 +61: [2023-04-29 11:37:34,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +61: [2023-04-29 11:37:34,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +61: [2023-04-29 11:37:34,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +25: [2023-04-29 11:37:34,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +61: [2023-04-29 11:37:34,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +43: [2023-04-29 11:37:34,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +43: [2023-04-29 11:37:34,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +43: [2023-04-29 11:37:34,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +27: [2023-04-29 11:37:34,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +56: [2023-04-29 11:37:34,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_97_mp_rank_02_optim_states.pt. +56: [2023-04-29 11:37:34,966] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 450 + 1: [2023-04-29 11:37:34,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 1: [2023-04-29 11:37:34,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +43: [2023-04-29 11:37:34,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +43: [2023-04-29 11:37:34,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_45_mp_rank_02_optim_states.pt. +43: [2023-04-29 11:37:34,967] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 346 +45: [2023-04-29 11:37:34,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 1: [2023-04-29 11:37:34,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +23: [2023-04-29 11:37:34,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +23: [2023-04-29 11:37:34,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +23: [2023-04-29 11:37:34,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +45: [2023-04-29 11:37:34,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +23: [2023-04-29 11:37:34,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +27: [2023-04-29 11:37:34,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +45: [2023-04-29 11:37:34,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +61: [2023-04-29 11:37:34,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_118_mp_rank_02_optim_states.pt. +45: [2023-04-29 11:37:34,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +45: [2023-04-29 11:37:34,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +61: [2023-04-29 11:37:34,970] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 492 +27: [2023-04-29 11:37:34,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +45: [2023-04-29 11:37:34,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +45: [2023-04-29 11:37:34,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +45: [2023-04-29 11:37:34,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +45: [2023-04-29 11:37:34,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +42: [2023-04-29 11:37:34,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +42: [2023-04-29 11:37:34,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +42: [2023-04-29 11:37:34,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +45: [2023-04-29 11:37:34,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +45: [2023-04-29 11:37:34,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +45: [2023-04-29 11:37:34,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +27: [2023-04-29 11:37:34,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 1: [2023-04-29 11:37:34,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 1: [2023-04-29 11:37:34,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 1: [2023-04-29 11:37:34,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +42: [2023-04-29 11:37:34,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +45: [2023-04-29 11:37:34,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +45: [2023-04-29 11:37:34,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +45: [2023-04-29 11:37:34,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +45: [2023-04-29 11:37:34,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. + 1: [2023-04-29 11:37:34,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +11: [2023-04-29 11:37:34,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +11: [2023-04-29 11:37:34,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +25: [2023-04-29 11:37:34,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +43: [2023-04-29 11:37:34,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_46_mp_rank_02_optim_states.pt. +27: [2023-04-29 11:37:34,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +43: [2023-04-29 11:37:34,974] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 348 +52: [2023-04-29 11:37:34,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +52: [2023-04-29 11:37:34,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +25: [2023-04-29 11:37:34,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +59: [2023-04-29 11:37:34,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_108_mp_rank_02_optim_states.pt. +25: [2023-04-29 11:37:34,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +59: [2023-04-29 11:37:34,976] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 472 + 2: [2023-04-29 11:37:34,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +52: [2023-04-29 11:37:34,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +27: [2023-04-29 11:37:34,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +21: [2023-04-29 11:37:34,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +45: [2023-04-29 11:37:34,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_55_mp_rank_02_optim_states.pt. +52: [2023-04-29 11:37:34,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +45: [2023-04-29 11:37:34,976] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 366 +30: [2023-04-29 11:37:34,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +30: [2023-04-29 11:37:34,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +23: [2023-04-29 11:37:34,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 1: [2023-04-29 11:37:34,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 2: [2023-04-29 11:37:34,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +11: [2023-04-29 11:37:34,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +11: [2023-04-29 11:37:34,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +11: [2023-04-29 11:37:34,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +11: [2023-04-29 11:37:34,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +30: [2023-04-29 11:37:34,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +30: [2023-04-29 11:37:34,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +27: [2023-04-29 11:37:34,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 2: [2023-04-29 11:37:34,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 2: [2023-04-29 11:37:34,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +41: [2023-04-29 11:37:34,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_36_mp_rank_02_optim_states.pt. +41: [2023-04-29 11:37:34,980] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 328 +57: [2023-04-29 11:37:34,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_100_mp_rank_02_optim_states.pt. +57: [2023-04-29 11:37:34,980] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 456 +51: [2023-04-29 11:37:34,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_79_mp_rank_03_optim_states.pt... +51: [2023-04-29 11:37:34,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_77_mp_rank_03_optim_states.pt... +21: [2023-04-29 11:37:34,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +51: [2023-04-29 11:37:34,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_76_mp_rank_03_optim_states.pt... +51: [2023-04-29 11:37:34,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_78_mp_rank_03_optim_states.pt... +28: [2023-04-29 11:37:34,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +28: [2023-04-29 11:37:34,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +28: [2023-04-29 11:37:34,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +28: [2023-04-29 11:37:34,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +58: [2023-04-29 11:37:34,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_106_mp_rank_03_optim_states.pt... +58: [2023-04-29 11:37:34,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_105_mp_rank_03_optim_states.pt... +58: [2023-04-29 11:37:34,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_104_mp_rank_03_optim_states.pt... +58: [2023-04-29 11:37:34,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_107_mp_rank_03_optim_states.pt... +19: [2023-04-29 11:37:34,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +19: [2023-04-29 11:37:34,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +10: [2023-04-29 11:37:34,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +10: [2023-04-29 11:37:34,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +10: [2023-04-29 11:37:34,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +10: [2023-04-29 11:37:34,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +21: [2023-04-29 11:37:34,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +14: [2023-04-29 11:37:34,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +14: [2023-04-29 11:37:34,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +14: [2023-04-29 11:37:34,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +14: [2023-04-29 11:37:34,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +11: [2023-04-29 11:37:34,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +11: [2023-04-29 11:37:34,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +33: [2023-04-29 11:37:34,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +21: [2023-04-29 11:37:34,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 4: [2023-04-29 11:37:34,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 4: [2023-04-29 11:37:34,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +57: [2023-04-29 11:37:34,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_101_mp_rank_02_optim_states.pt. +57: [2023-04-29 11:37:34,987] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 458 +33: [2023-04-29 11:37:34,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +19: [2023-04-29 11:37:34,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +33: [2023-04-29 11:37:34,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +38: [2023-04-29 11:37:34,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +38: [2023-04-29 11:37:34,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +38: [2023-04-29 11:37:34,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +38: [2023-04-29 11:37:34,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 4: [2023-04-29 11:37:34,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +38: [2023-04-29 11:37:34,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. + 4: [2023-04-29 11:37:34,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +38: [2023-04-29 11:37:34,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +38: [2023-04-29 11:37:34,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +38: [2023-04-29 11:37:34,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +38: [2023-04-29 11:37:34,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +33: [2023-04-29 11:37:34,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +14: [2023-04-29 11:37:34,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +23: [2023-04-29 11:37:34,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +33: [2023-04-29 11:37:34,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +33: [2023-04-29 11:37:34,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +33: [2023-04-29 11:37:34,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +33: [2023-04-29 11:37:34,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +14: [2023-04-29 11:37:34,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +39: [2023-04-29 11:37:34,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_30_mp_rank_02_optim_states.pt. +33: [2023-04-29 11:37:34,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +39: [2023-04-29 11:37:34,990] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 316 +33: [2023-04-29 11:37:34,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +33: [2023-04-29 11:37:34,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +33: [2023-04-29 11:37:34,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +19: [2023-04-29 11:37:34,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +38: [2023-04-29 11:37:34,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +38: [2023-04-29 11:37:34,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +38: [2023-04-29 11:37:34,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +38: [2023-04-29 11:37:34,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +38: [2023-04-29 11:37:34,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +38: [2023-04-29 11:37:34,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +61: [2023-04-29 11:37:34,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +57: [2023-04-29 11:37:34,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_102_mp_rank_03_optim_states.pt... +57: [2023-04-29 11:37:34,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_100_mp_rank_03_optim_states.pt... +57: [2023-04-29 11:37:34,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_101_mp_rank_03_optim_states.pt... +57: [2023-04-29 11:37:34,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_103_mp_rank_03_optim_states.pt... +38: [2023-04-29 11:37:34,992] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +14: [2023-04-29 11:37:34,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +61: [2023-04-29 11:37:34,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +61: [2023-04-29 11:37:34,992] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +61: [2023-04-29 11:37:34,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +25: [2023-04-29 11:37:34,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +59: [2023-04-29 11:37:34,992] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_110_mp_rank_02_optim_states.pt. +59: [2023-04-29 11:37:34,992] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 476 +61: [2023-04-29 11:37:34,992] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +33: [2023-04-29 11:37:34,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +33: [2023-04-29 11:37:34,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +33: [2023-04-29 11:37:34,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +33: [2023-04-29 11:37:34,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +61: [2023-04-29 11:37:34,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +61: [2023-04-29 11:37:34,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +14: [2023-04-29 11:37:34,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 4: [2023-04-29 11:37:34,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +61: [2023-04-29 11:37:34,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +61: [2023-04-29 11:37:34,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +43: [2023-04-29 11:37:34,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +43: [2023-04-29 11:37:34,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 4: [2023-04-29 11:37:34,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +43: [2023-04-29 11:37:34,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +43: [2023-04-29 11:37:34,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +43: [2023-04-29 11:37:34,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 4: [2023-04-29 11:37:34,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +61: [2023-04-29 11:37:34,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +61: [2023-04-29 11:37:34,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +61: [2023-04-29 11:37:34,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +43: [2023-04-29 11:37:34,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +43: [2023-04-29 11:37:34,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +61: [2023-04-29 11:37:34,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +61: [2023-04-29 11:37:34,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +61: [2023-04-29 11:37:34,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +43: [2023-04-29 11:37:34,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +43: [2023-04-29 11:37:34,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +43: [2023-04-29 11:37:34,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +61: [2023-04-29 11:37:34,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +43: [2023-04-29 11:37:34,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +43: [2023-04-29 11:37:34,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... + 4: [2023-04-29 11:37:34,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +23: [2023-04-29 11:37:34,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +23: [2023-04-29 11:37:35,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +23: [2023-04-29 11:37:35,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +23: [2023-04-29 11:37:35,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +41: [2023-04-29 11:37:35,001] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_37_mp_rank_03_optim_states.pt... +41: [2023-04-29 11:37:35,001] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_38_mp_rank_03_optim_states.pt... +41: [2023-04-29 11:37:35,001] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_36_mp_rank_03_optim_states.pt... +41: [2023-04-29 11:37:35,001] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_39_mp_rank_03_optim_states.pt... +25: [2023-04-29 11:37:35,001] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +40: [2023-04-29 11:37:35,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +40: [2023-04-29 11:37:35,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +40: [2023-04-29 11:37:35,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +40: [2023-04-29 11:37:35,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +43: [2023-04-29 11:37:35,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +43: [2023-04-29 11:37:35,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +43: [2023-04-29 11:37:35,003] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +43: [2023-04-29 11:37:35,003] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +52: [2023-04-29 11:37:35,004] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +52: [2023-04-29 11:37:35,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +52: [2023-04-29 11:37:35,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +25: [2023-04-29 11:37:35,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +52: [2023-04-29 11:37:35,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +52: [2023-04-29 11:37:35,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +52: [2023-04-29 11:37:35,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +30: [2023-04-29 11:37:35,006] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +23: [2023-04-29 11:37:35,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +23: [2023-04-29 11:37:35,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +30: [2023-04-29 11:37:35,006] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +59: [2023-04-29 11:37:35,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_111_mp_rank_03_optim_states.pt... +59: [2023-04-29 11:37:35,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_110_mp_rank_03_optim_states.pt... +59: [2023-04-29 11:37:35,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_108_mp_rank_03_optim_states.pt... +59: [2023-04-29 11:37:35,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_109_mp_rank_03_optim_states.pt... +42: [2023-04-29 11:37:35,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_40_mp_rank_02_optim_states.pt. +42: [2023-04-29 11:37:35,007] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 336 +30: [2023-04-29 11:37:35,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 9: [2023-04-29 11:37:35,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +52: [2023-04-29 11:37:35,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +36: [2023-04-29 11:37:35,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_18_mp_rank_03_optim_states.pt... + 9: [2023-04-29 11:37:35,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +36: [2023-04-29 11:37:35,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_16_mp_rank_03_optim_states.pt... +36: [2023-04-29 11:37:35,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_17_mp_rank_03_optim_states.pt... +36: [2023-04-29 11:37:35,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_19_mp_rank_03_optim_states.pt... +52: [2023-04-29 11:37:35,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +52: [2023-04-29 11:37:35,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +30: [2023-04-29 11:37:35,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +12: [2023-04-29 11:37:35,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +12: [2023-04-29 11:37:35,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 9: [2023-04-29 11:37:35,009] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +10: [2023-04-29 11:37:35,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +25: [2023-04-29 11:37:35,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +22: [2023-04-29 11:37:35,010] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +22: [2023-04-29 11:37:35,010] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +22: [2023-04-29 11:37:35,010] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +22: [2023-04-29 11:37:35,010] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +52: [2023-04-29 11:37:35,011] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +52: [2023-04-29 11:37:35,011] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +52: [2023-04-29 11:37:35,011] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. + 9: [2023-04-29 11:37:35,011] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +45: [2023-04-29 11:37:35,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_54_mp_rank_03_optim_states.pt... +45: [2023-04-29 11:37:35,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_55_mp_rank_03_optim_states.pt... +45: [2023-04-29 11:37:35,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_53_mp_rank_03_optim_states.pt... +45: [2023-04-29 11:37:35,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_52_mp_rank_03_optim_states.pt... +28: [2023-04-29 11:37:35,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +28: [2023-04-29 11:37:35,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +36: [2023-04-29 11:37:35,012] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_17_mp_rank_02_optim_states.pt. +19: [2023-04-29 11:37:35,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +30: [2023-04-29 11:37:35,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +19: [2023-04-29 11:37:35,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +36: [2023-04-29 11:37:35,013] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 290 +59: [2023-04-29 11:37:35,013] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_111_mp_rank_02_optim_states.pt. +59: [2023-04-29 11:37:35,013] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 478 +30: [2023-04-29 11:37:35,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +28: [2023-04-29 11:37:35,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +52: [2023-04-29 11:37:35,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +28: [2023-04-29 11:37:35,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +43: [2023-04-29 11:37:35,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_47_mp_rank_02_optim_states.pt. +52: [2023-04-29 11:37:35,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +30: [2023-04-29 11:37:35,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +52: [2023-04-29 11:37:35,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +10: [2023-04-29 11:37:35,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +43: [2023-04-29 11:37:35,014] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 350 +12: [2023-04-29 11:37:35,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +52: [2023-04-29 11:37:35,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +30: [2023-04-29 11:37:35,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 9: [2023-04-29 11:37:35,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +10: [2023-04-29 11:37:35,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 9: [2023-04-29 11:37:35,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +42: [2023-04-29 11:37:35,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_43_mp_rank_02_optim_states.pt. +12: [2023-04-29 11:37:35,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +42: [2023-04-29 11:37:35,016] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 342 +10: [2023-04-29 11:37:35,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 9: [2023-04-29 11:37:35,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 9: [2023-04-29 11:37:35,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 7: [2023-04-29 11:37:35,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 7: [2023-04-29 11:37:35,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 7: [2023-04-29 11:37:35,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 7: [2023-04-29 11:37:35,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 5: [2023-04-29 11:37:35,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +19: [2023-04-29 11:37:35,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +19: [2023-04-29 11:37:35,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 5: [2023-04-29 11:37:35,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +42: [2023-04-29 11:37:35,022] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_41_mp_rank_02_optim_states.pt. +27: [2023-04-29 11:37:35,022] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +27: [2023-04-29 11:37:35,022] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +42: [2023-04-29 11:37:35,022] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 338 +27: [2023-04-29 11:37:35,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +27: [2023-04-29 11:37:35,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +26: [2023-04-29 11:37:35,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +26: [2023-04-29 11:37:35,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +18: [2023-04-29 11:37:35,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +18: [2023-04-29 11:37:35,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +18: [2023-04-29 11:37:35,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +26: [2023-04-29 11:37:35,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +18: [2023-04-29 11:37:35,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +26: [2023-04-29 11:37:35,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +27: [2023-04-29 11:37:35,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +27: [2023-04-29 11:37:35,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +40: [2023-04-29 11:37:35,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +27: [2023-04-29 11:37:35,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +40: [2023-04-29 11:37:35,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +40: [2023-04-29 11:37:35,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 5: [2023-04-29 11:37:35,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +40: [2023-04-29 11:37:35,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +40: [2023-04-29 11:37:35,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +40: [2023-04-29 11:37:35,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... + 5: [2023-04-29 11:37:35,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +27: [2023-04-29 11:37:35,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +26: [2023-04-29 11:37:35,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +26: [2023-04-29 11:37:35,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +42: [2023-04-29 11:37:35,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_42_mp_rank_03_optim_states.pt... +42: [2023-04-29 11:37:35,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_40_mp_rank_03_optim_states.pt... +42: [2023-04-29 11:37:35,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_41_mp_rank_03_optim_states.pt... +42: [2023-04-29 11:37:35,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_43_mp_rank_03_optim_states.pt... +26: [2023-04-29 11:37:35,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +40: [2023-04-29 11:37:35,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +33: [2023-04-29 11:37:35,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_4_mp_rank_03_optim_states.pt... +33: [2023-04-29 11:37:35,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_7_mp_rank_03_optim_states.pt... +33: [2023-04-29 11:37:35,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_5_mp_rank_03_optim_states.pt... +33: [2023-04-29 11:37:35,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_6_mp_rank_03_optim_states.pt... +26: [2023-04-29 11:37:35,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +40: [2023-04-29 11:37:35,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +40: [2023-04-29 11:37:35,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +40: [2023-04-29 11:37:35,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +40: [2023-04-29 11:37:35,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +40: [2023-04-29 11:37:35,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +40: [2023-04-29 11:37:35,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +38: [2023-04-29 11:37:35,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_27_mp_rank_03_optim_states.pt... +38: [2023-04-29 11:37:35,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_26_mp_rank_03_optim_states.pt... +38: [2023-04-29 11:37:35,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_24_mp_rank_03_optim_states.pt... +38: [2023-04-29 11:37:35,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_25_mp_rank_03_optim_states.pt... +40: [2023-04-29 11:37:35,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +40: [2023-04-29 11:37:35,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +40: [2023-04-29 11:37:35,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +36: [2023-04-29 11:37:35,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_18_mp_rank_02_optim_states.pt. +36: [2023-04-29 11:37:35,035] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 292 +22: [2023-04-29 11:37:35,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +12: [2023-04-29 11:37:35,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +61: [2023-04-29 11:37:35,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_117_mp_rank_03_optim_states.pt... +61: [2023-04-29 11:37:35,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_119_mp_rank_03_optim_states.pt... +61: [2023-04-29 11:37:35,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_116_mp_rank_03_optim_states.pt... +61: [2023-04-29 11:37:35,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_118_mp_rank_03_optim_states.pt... +34: [2023-04-29 11:37:35,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +34: [2023-04-29 11:37:35,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +34: [2023-04-29 11:37:35,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +34: [2023-04-29 11:37:35,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +44: [2023-04-29 11:37:35,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_51_mp_rank_03_optim_states.pt. +44: [2023-04-29 11:37:35,038] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 359 +12: [2023-04-29 11:37:35,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +22: [2023-04-29 11:37:35,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +10: [2023-04-29 11:37:35,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +10: [2023-04-29 11:37:35,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +10: [2023-04-29 11:37:35,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +20: [2023-04-29 11:37:35,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +22: [2023-04-29 11:37:35,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 2: [2023-04-29 11:37:35,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +20: [2023-04-29 11:37:35,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +20: [2023-04-29 11:37:35,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +22: [2023-04-29 11:37:35,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +20: [2023-04-29 11:37:35,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +21: [2023-04-29 11:37:35,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +43: [2023-04-29 11:37:35,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_45_mp_rank_03_optim_states.pt... +43: [2023-04-29 11:37:35,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_44_mp_rank_03_optim_states.pt... +43: [2023-04-29 11:37:35,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_47_mp_rank_03_optim_states.pt... +43: [2023-04-29 11:37:35,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_46_mp_rank_03_optim_states.pt... +10: [2023-04-29 11:37:35,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 7: [2023-04-29 11:37:35,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +14: [2023-04-29 11:37:35,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +30: [2023-04-29 11:37:35,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +20: [2023-04-29 11:37:35,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 2: [2023-04-29 11:37:35,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +21: [2023-04-29 11:37:35,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 7: [2023-04-29 11:37:35,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 7: [2023-04-29 11:37:35,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +12: [2023-04-29 11:37:35,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 2: [2023-04-29 11:37:35,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +20: [2023-04-29 11:37:35,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +20: [2023-04-29 11:37:35,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +12: [2023-04-29 11:37:35,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +20: [2023-04-29 11:37:35,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +30: [2023-04-29 11:37:35,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 7: [2023-04-29 11:37:35,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 2: [2023-04-29 11:37:35,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +30: [2023-04-29 11:37:35,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +14: [2023-04-29 11:37:35,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +19: [2023-04-29 11:37:35,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +19: [2023-04-29 11:37:35,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +18: [2023-04-29 11:37:35,052] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +21: [2023-04-29 11:37:35,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 7: [2023-04-29 11:37:35,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 7: [2023-04-29 11:37:35,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 7: [2023-04-29 11:37:35,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 7: [2023-04-29 11:37:35,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +12: [2023-04-29 11:37:35,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +12: [2023-04-29 11:37:35,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +28: [2023-04-29 11:37:35,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +28: [2023-04-29 11:37:35,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +12: [2023-04-29 11:37:35,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +19: [2023-04-29 11:37:35,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +19: [2023-04-29 11:37:35,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 2: [2023-04-29 11:37:35,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +12: [2023-04-29 11:37:35,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +28: [2023-04-29 11:37:35,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +30: [2023-04-29 11:37:35,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +30: [2023-04-29 11:37:35,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +30: [2023-04-29 11:37:35,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +28: [2023-04-29 11:37:35,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +19: [2023-04-29 11:37:35,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +39: [2023-04-29 11:37:35,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_28_mp_rank_02_optim_states.pt. +52: [2023-04-29 11:37:35,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_82_mp_rank_03_optim_states.pt... +52: [2023-04-29 11:37:35,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_80_mp_rank_03_optim_states.pt... +52: [2023-04-29 11:37:35,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_83_mp_rank_03_optim_states.pt... +52: [2023-04-29 11:37:35,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_81_mp_rank_03_optim_states.pt... +19: [2023-04-29 11:37:35,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +39: [2023-04-29 11:37:35,057] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 312 +31: [2023-04-29 11:37:35,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +31: [2023-04-29 11:37:35,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +31: [2023-04-29 11:37:35,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +21: [2023-04-29 11:37:35,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 2: [2023-04-29 11:37:35,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 2: [2023-04-29 11:37:35,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +31: [2023-04-29 11:37:35,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +21: [2023-04-29 11:37:35,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +18: [2023-04-29 11:37:35,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 7: [2023-04-29 11:37:35,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 2: [2023-04-29 11:37:35,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +28: [2023-04-29 11:37:35,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +28: [2023-04-29 11:37:35,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +19: [2023-04-29 11:37:35,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +28: [2023-04-29 11:37:35,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 7: [2023-04-29 11:37:35,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 7: [2023-04-29 11:37:35,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +18: [2023-04-29 11:37:35,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +18: [2023-04-29 11:37:35,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +31: [2023-04-29 11:37:35,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +19: [2023-04-29 11:37:35,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 4: [2023-04-29 11:37:35,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 4: [2023-04-29 11:37:35,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 7: [2023-04-29 11:37:35,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +28: [2023-04-29 11:37:35,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +34: [2023-04-29 11:37:35,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +34: [2023-04-29 11:37:35,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +30: [2023-04-29 11:37:35,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +21: [2023-04-29 11:37:35,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 4: [2023-04-29 11:37:35,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +30: [2023-04-29 11:37:35,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +34: [2023-04-29 11:37:35,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +34: [2023-04-29 11:37:35,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +34: [2023-04-29 11:37:35,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +34: [2023-04-29 11:37:35,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +31: [2023-04-29 11:37:35,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +31: [2023-04-29 11:37:35,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +31: [2023-04-29 11:37:35,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +21: [2023-04-29 11:37:35,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +24: [2023-04-29 11:37:35,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +24: [2023-04-29 11:37:35,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +34: [2023-04-29 11:37:35,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. + 4: [2023-04-29 11:37:35,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +14: [2023-04-29 11:37:35,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +34: [2023-04-29 11:37:35,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +34: [2023-04-29 11:37:35,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +34: [2023-04-29 11:37:35,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +23: [2023-04-29 11:37:35,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +34: [2023-04-29 11:37:35,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +34: [2023-04-29 11:37:35,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +34: [2023-04-29 11:37:35,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +34: [2023-04-29 11:37:35,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +14: [2023-04-29 11:37:35,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +55: [2023-04-29 11:37:35,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_95_mp_rank_03_optim_states.pt. +34: [2023-04-29 11:37:35,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +23: [2023-04-29 11:37:35,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +55: [2023-04-29 11:37:35,069] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 447 +34: [2023-04-29 11:37:35,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +24: [2023-04-29 11:37:35,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +24: [2023-04-29 11:37:35,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +11: [2023-04-29 11:37:35,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +14: [2023-04-29 11:37:35,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +11: [2023-04-29 11:37:35,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +11: [2023-04-29 11:37:35,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +10: [2023-04-29 11:37:35,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +10: [2023-04-29 11:37:35,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +11: [2023-04-29 11:37:35,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +10: [2023-04-29 11:37:35,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +28: [2023-04-29 11:37:35,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +10: [2023-04-29 11:37:35,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +10: [2023-04-29 11:37:35,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +21: [2023-04-29 11:37:35,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +29: [2023-04-29 11:37:35,075] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +29: [2023-04-29 11:37:35,075] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +29: [2023-04-29 11:37:35,075] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +29: [2023-04-29 11:37:35,075] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +10: [2023-04-29 11:37:35,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +23: [2023-04-29 11:37:35,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +23: [2023-04-29 11:37:35,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +11: [2023-04-29 11:37:35,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +40: [2023-04-29 11:37:35,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_33_mp_rank_03_optim_states.pt... +40: [2023-04-29 11:37:35,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_32_mp_rank_03_optim_states.pt... +40: [2023-04-29 11:37:35,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_35_mp_rank_03_optim_states.pt... +40: [2023-04-29 11:37:35,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_34_mp_rank_03_optim_states.pt... +30: [2023-04-29 11:37:35,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +12: [2023-04-29 11:37:35,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +28: [2023-04-29 11:37:35,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +11: [2023-04-29 11:37:35,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +11: [2023-04-29 11:37:35,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +11: [2023-04-29 11:37:35,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +14: [2023-04-29 11:37:35,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +56: [2023-04-29 11:37:35,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +56: [2023-04-29 11:37:35,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +56: [2023-04-29 11:37:35,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +15: [2023-04-29 11:37:35,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +15: [2023-04-29 11:37:35,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +56: [2023-04-29 11:37:35,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +15: [2023-04-29 11:37:35,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +28: [2023-04-29 11:37:35,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +15: [2023-04-29 11:37:35,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +30: [2023-04-29 11:37:35,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +23: [2023-04-29 11:37:35,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +23: [2023-04-29 11:37:35,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 9: [2023-04-29 11:37:35,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +15: [2023-04-29 11:37:35,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +12: [2023-04-29 11:37:35,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +16: [2023-04-29 11:37:35,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +16: [2023-04-29 11:37:35,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +15: [2023-04-29 11:37:35,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +12: [2023-04-29 11:37:35,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +15: [2023-04-29 11:37:35,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +19: [2023-04-29 11:37:35,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +19: [2023-04-29 11:37:35,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +15: [2023-04-29 11:37:35,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +16: [2023-04-29 11:37:35,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +12: [2023-04-29 11:37:35,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +28: [2023-04-29 11:37:35,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +28: [2023-04-29 11:37:35,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +28: [2023-04-29 11:37:35,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +16: [2023-04-29 11:37:35,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 9: [2023-04-29 11:37:35,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +23: [2023-04-29 11:37:35,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 9: [2023-04-29 11:37:35,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +23: [2023-04-29 11:37:35,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 9: [2023-04-29 11:37:35,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +30: [2023-04-29 11:37:35,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +30: [2023-04-29 11:37:35,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +19: [2023-04-29 11:37:35,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +27: [2023-04-29 11:37:35,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +27: [2023-04-29 11:37:35,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +28: [2023-04-29 11:37:35,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +28: [2023-04-29 11:37:35,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +27: [2023-04-29 11:37:35,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +44: [2023-04-29 11:37:35,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_48_mp_rank_03_optim_states.pt. +44: [2023-04-29 11:37:35,093] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 353 +19: [2023-04-29 11:37:35,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +19: [2023-04-29 11:37:35,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +27: [2023-04-29 11:37:35,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +10: [2023-04-29 11:37:35,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +26: [2023-04-29 11:37:35,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +26: [2023-04-29 11:37:35,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 4: [2023-04-29 11:37:35,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 4: [2023-04-29 11:37:35,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 4: [2023-04-29 11:37:35,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +24: [2023-04-29 11:37:35,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +10: [2023-04-29 11:37:35,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +20: [2023-04-29 11:37:35,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +26: [2023-04-29 11:37:35,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +26: [2023-04-29 11:37:35,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +24: [2023-04-29 11:37:35,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +19: [2023-04-29 11:37:35,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 7: [2023-04-29 11:37:35,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 4: [2023-04-29 11:37:35,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +24: [2023-04-29 11:37:35,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +14: [2023-04-29 11:37:35,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +24: [2023-04-29 11:37:35,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +19: [2023-04-29 11:37:35,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +22: [2023-04-29 11:37:35,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +10: [2023-04-29 11:37:35,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +10: [2023-04-29 11:37:35,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +37: [2023-04-29 11:37:35,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_20_mp_rank_03_optim_states.pt. + 7: [2023-04-29 11:37:35,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +37: [2023-04-29 11:37:35,102] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 297 + 5: [2023-04-29 11:37:35,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +30: [2023-04-29 11:37:35,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +10: [2023-04-29 11:37:35,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +29: [2023-04-29 11:37:35,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +21: [2023-04-29 11:37:35,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +21: [2023-04-29 11:37:35,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +21: [2023-04-29 11:37:35,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +29: [2023-04-29 11:37:35,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +21: [2023-04-29 11:37:35,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +56: [2023-04-29 11:37:35,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +56: [2023-04-29 11:37:35,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +56: [2023-04-29 11:37:35,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +10: [2023-04-29 11:37:35,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +50: [2023-04-29 11:37:35,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_73_mp_rank_03_optim_states.pt. +19: [2023-04-29 11:37:35,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +50: [2023-04-29 11:37:35,106] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 403 +56: [2023-04-29 11:37:35,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +56: [2023-04-29 11:37:35,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +56: [2023-04-29 11:37:35,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +55: [2023-04-29 11:37:35,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_93_mp_rank_03_optim_states.pt. +55: [2023-04-29 11:37:35,107] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 443 +14: [2023-04-29 11:37:35,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +56: [2023-04-29 11:37:35,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +56: [2023-04-29 11:37:35,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +18: [2023-04-29 11:37:35,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +30: [2023-04-29 11:37:35,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +29: [2023-04-29 11:37:35,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +20: [2023-04-29 11:37:35,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +20: [2023-04-29 11:37:35,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +22: [2023-04-29 11:37:35,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +20: [2023-04-29 11:37:35,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +29: [2023-04-29 11:37:35,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +20: [2023-04-29 11:37:35,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 2: [2023-04-29 11:37:35,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +22: [2023-04-29 11:37:35,111] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +53: [2023-04-29 11:37:35,111] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_85_mp_rank_03_optim_states.pt. +56: [2023-04-29 11:37:35,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +56: [2023-04-29 11:37:35,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +53: [2023-04-29 11:37:35,111] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 427 +56: [2023-04-29 11:37:35,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +56: [2023-04-29 11:37:35,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +21: [2023-04-29 11:37:35,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +22: [2023-04-29 11:37:35,112] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +21: [2023-04-29 11:37:35,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +21: [2023-04-29 11:37:35,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +21: [2023-04-29 11:37:35,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +16: [2023-04-29 11:37:35,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +16: [2023-04-29 11:37:35,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +22: [2023-04-29 11:37:35,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +56: [2023-04-29 11:37:35,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +56: [2023-04-29 11:37:35,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +56: [2023-04-29 11:37:35,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. + 5: [2023-04-29 11:37:35,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 5: [2023-04-29 11:37:35,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +56: [2023-04-29 11:37:35,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +18: [2023-04-29 11:37:35,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +22: [2023-04-29 11:37:35,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +22: [2023-04-29 11:37:35,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 5: [2023-04-29 11:37:35,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 2: [2023-04-29 11:37:35,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 9: [2023-04-29 11:37:35,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 9: [2023-04-29 11:37:35,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 9: [2023-04-29 11:37:35,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +28: [2023-04-29 11:37:35,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +34: [2023-04-29 11:37:35,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_9_mp_rank_03_optim_states.pt... +34: [2023-04-29 11:37:35,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_8_mp_rank_03_optim_states.pt... +34: [2023-04-29 11:37:35,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_10_mp_rank_03_optim_states.pt... +34: [2023-04-29 11:37:35,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_11_mp_rank_03_optim_states.pt... + 9: [2023-04-29 11:37:35,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 7: [2023-04-29 11:37:35,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 7: [2023-04-29 11:37:35,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +53: [2023-04-29 11:37:35,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_86_mp_rank_03_optim_states.pt. +53: [2023-04-29 11:37:35,118] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 429 +22: [2023-04-29 11:37:35,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +20: [2023-04-29 11:37:35,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +27: [2023-04-29 11:37:35,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 9: [2023-04-29 11:37:35,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +19: [2023-04-29 11:37:35,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +19: [2023-04-29 11:37:35,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 9: [2023-04-29 11:37:35,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +16: [2023-04-29 11:37:35,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +16: [2023-04-29 11:37:35,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +20: [2023-04-29 11:37:35,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +30: [2023-04-29 11:37:35,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +30: [2023-04-29 11:37:35,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 7: [2023-04-29 11:37:35,123] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +26: [2023-04-29 11:37:35,123] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +26: [2023-04-29 11:37:35,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 9: [2023-04-29 11:37:35,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 7: [2023-04-29 11:37:35,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +20: [2023-04-29 11:37:35,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +20: [2023-04-29 11:37:35,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +18: [2023-04-29 11:37:35,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +27: [2023-04-29 11:37:35,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +27: [2023-04-29 11:37:35,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 7: [2023-04-29 11:37:35,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 9: [2023-04-29 11:37:35,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +31: [2023-04-29 11:37:35,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +19: [2023-04-29 11:37:35,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +26: [2023-04-29 11:37:35,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +26: [2023-04-29 11:37:35,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +27: [2023-04-29 11:37:35,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +62: [2023-04-29 11:37:35,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_120_mp_rank_02_optim_states.pt. +62: [2023-04-29 11:37:35,129] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 496 +18: [2023-04-29 11:37:35,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +28: [2023-04-29 11:37:35,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +28: [2023-04-29 11:37:35,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 4: [2023-04-29 11:37:35,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 4: [2023-04-29 11:37:35,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 4: [2023-04-29 11:37:35,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 4: [2023-04-29 11:37:35,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 2: [2023-04-29 11:37:35,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 7: [2023-04-29 11:37:35,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +15: [2023-04-29 11:37:35,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +15: [2023-04-29 11:37:35,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +15: [2023-04-29 11:37:35,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +15: [2023-04-29 11:37:35,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 7: [2023-04-29 11:37:35,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +18: [2023-04-29 11:37:35,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +18: [2023-04-29 11:37:35,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +28: [2023-04-29 11:37:35,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 5: [2023-04-29 11:37:35,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 5: [2023-04-29 11:37:35,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 7: [2023-04-29 11:37:35,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +31: [2023-04-29 11:37:35,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +31: [2023-04-29 11:37:35,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +31: [2023-04-29 11:37:35,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +22: [2023-04-29 11:37:35,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +22: [2023-04-29 11:37:35,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 5: [2023-04-29 11:37:35,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +22: [2023-04-29 11:37:35,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +22: [2023-04-29 11:37:35,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +12: [2023-04-29 11:37:35,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +19: [2023-04-29 11:37:35,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 7: [2023-04-29 11:37:35,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 7: [2023-04-29 11:37:35,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +28: [2023-04-29 11:37:35,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +37: [2023-04-29 11:37:35,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_22_mp_rank_03_optim_states.pt. +11: [2023-04-29 11:37:35,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 3: [2023-04-29 11:37:35,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 3: [2023-04-29 11:37:35,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +37: [2023-04-29 11:37:35,142] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 301 + 3: [2023-04-29 11:37:35,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +18: [2023-04-29 11:37:35,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +18: [2023-04-29 11:37:35,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 3: [2023-04-29 11:37:35,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +11: [2023-04-29 11:37:35,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +11: [2023-04-29 11:37:35,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +22: [2023-04-29 11:37:35,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +20: [2023-04-29 11:37:35,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +20: [2023-04-29 11:37:35,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 5: [2023-04-29 11:37:35,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 5: [2023-04-29 11:37:35,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +20: [2023-04-29 11:37:35,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +22: [2023-04-29 11:37:35,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +12: [2023-04-29 11:37:35,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +22: [2023-04-29 11:37:35,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 5: [2023-04-29 11:37:35,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +22: [2023-04-29 11:37:35,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +63: [2023-04-29 11:37:35,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_124_mp_rank_02_optim_states.pt. +56: [2023-04-29 11:37:35,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_96_mp_rank_02_optim_states.pt. +63: [2023-04-29 11:37:35,146] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 504 + 5: [2023-04-29 11:37:35,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +20: [2023-04-29 11:37:35,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +56: [2023-04-29 11:37:35,146] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 448 + 3: [2023-04-29 11:37:35,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 9: [2023-04-29 11:37:35,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +19: [2023-04-29 11:37:35,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +11: [2023-04-29 11:37:35,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 3: [2023-04-29 11:37:35,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 2: [2023-04-29 11:37:35,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 3: [2023-04-29 11:37:35,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +20: [2023-04-29 11:37:35,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +19: [2023-04-29 11:37:35,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 3: [2023-04-29 11:37:35,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +55: [2023-04-29 11:37:35,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_92_mp_rank_03_optim_states.pt. +55: [2023-04-29 11:37:35,153] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 441 +31: [2023-04-29 11:37:35,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +12: [2023-04-29 11:37:35,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 9: [2023-04-29 11:37:35,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 9: [2023-04-29 11:37:35,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +12: [2023-04-29 11:37:35,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 4: [2023-04-29 11:37:35,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +20: [2023-04-29 11:37:35,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +19: [2023-04-29 11:37:35,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 8: [2023-04-29 11:37:35,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 8: [2023-04-29 11:37:35,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +28: [2023-04-29 11:37:35,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +24: [2023-04-29 11:37:35,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +24: [2023-04-29 11:37:35,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +28: [2023-04-29 11:37:35,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 4: [2023-04-29 11:37:35,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +55: [2023-04-29 11:37:35,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_94_mp_rank_03_optim_states.pt. +55: [2023-04-29 11:37:35,158] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 445 + 9: [2023-04-29 11:37:35,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +12: [2023-04-29 11:37:35,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 7: [2023-04-29 11:37:35,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 8: [2023-04-29 11:37:35,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +12: [2023-04-29 11:37:35,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +13: [2023-04-29 11:37:35,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 8: [2023-04-29 11:37:35,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +13: [2023-04-29 11:37:35,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +13: [2023-04-29 11:37:35,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +20: [2023-04-29 11:37:35,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +17: [2023-04-29 11:37:35,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +17: [2023-04-29 11:37:35,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +17: [2023-04-29 11:37:35,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +13: [2023-04-29 11:37:35,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +17: [2023-04-29 11:37:35,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 2: [2023-04-29 11:37:35,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +24: [2023-04-29 11:37:35,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +56: [2023-04-29 11:37:35,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_98_mp_rank_03_optim_states.pt... +56: [2023-04-29 11:37:35,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_99_mp_rank_03_optim_states.pt... +56: [2023-04-29 11:37:35,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_97_mp_rank_03_optim_states.pt... +24: [2023-04-29 11:37:35,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +56: [2023-04-29 11:37:35,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_96_mp_rank_03_optim_states.pt... + 4: [2023-04-29 11:37:35,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 4: [2023-04-29 11:37:35,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +24: [2023-04-29 11:37:35,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +12: [2023-04-29 11:37:35,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +24: [2023-04-29 11:37:35,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +15: [2023-04-29 11:37:35,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 8: [2023-04-29 11:37:35,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 2: [2023-04-29 11:37:35,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 8: [2023-04-29 11:37:35,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 8: [2023-04-29 11:37:35,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +13: [2023-04-29 11:37:35,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 8: [2023-04-29 11:37:35,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +13: [2023-04-29 11:37:35,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +12: [2023-04-29 11:37:35,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +13: [2023-04-29 11:37:35,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +24: [2023-04-29 11:37:35,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +15: [2023-04-29 11:37:35,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +15: [2023-04-29 11:37:35,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +15: [2023-04-29 11:37:35,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +13: [2023-04-29 11:37:35,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +28: [2023-04-29 11:37:35,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +11: [2023-04-29 11:37:35,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +24: [2023-04-29 11:37:35,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 3: [2023-04-29 11:37:35,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. + 3: [2023-04-29 11:37:35,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +24: [2023-04-29 11:37:35,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 3: [2023-04-29 11:37:35,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +15: [2023-04-29 11:37:35,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +15: [2023-04-29 11:37:35,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +15: [2023-04-29 11:37:35,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 3: [2023-04-29 11:37:35,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_18-model_01-model_states.pt. +19: [2023-04-29 11:37:35,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +29: [2023-04-29 11:37:35,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +15: [2023-04-29 11:37:35,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +53: [2023-04-29 11:37:35,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_84_mp_rank_03_optim_states.pt. +53: [2023-04-29 11:37:35,171] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 425 +31: [2023-04-29 11:37:35,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 7: [2023-04-29 11:37:35,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +31: [2023-04-29 11:37:35,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +31: [2023-04-29 11:37:35,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +24: [2023-04-29 11:37:35,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +24: [2023-04-29 11:37:35,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +24: [2023-04-29 11:37:35,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +24: [2023-04-29 11:37:35,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +37: [2023-04-29 11:37:35,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_23_mp_rank_03_optim_states.pt. +21: [2023-04-29 11:37:35,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +37: [2023-04-29 11:37:35,174] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 303 +29: [2023-04-29 11:37:35,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 7: [2023-04-29 11:37:35,175] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +11: [2023-04-29 11:37:35,175] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +54: [2023-04-29 11:37:35,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_90_mp_rank_03_optim_states.pt. +54: [2023-04-29 11:37:35,175] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 437 +29: [2023-04-29 11:37:35,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +11: [2023-04-29 11:37:35,175] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +49: [2023-04-29 11:37:35,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_68_mp_rank_03_optim_states.pt. +49: [2023-04-29 11:37:35,177] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 393 +29: [2023-04-29 11:37:35,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +16: [2023-04-29 11:37:35,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +16: [2023-04-29 11:37:35,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 7: [2023-04-29 11:37:35,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +29: [2023-04-29 11:37:35,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +24: [2023-04-29 11:37:35,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +24: [2023-04-29 11:37:35,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +24: [2023-04-29 11:37:35,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +11: [2023-04-29 11:37:35,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +29: [2023-04-29 11:37:35,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +29: [2023-04-29 11:37:35,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +49: [2023-04-29 11:37:35,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_71_mp_rank_03_optim_states.pt. +49: [2023-04-29 11:37:35,183] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 399 + 0: [2023-04-29 11:37:35,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 0: [2023-04-29 11:37:35,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 0: [2023-04-29 11:37:35,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 0: [2023-04-29 11:37:35,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +17: [2023-04-29 11:37:35,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +21: [2023-04-29 11:37:35,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +21: [2023-04-29 11:37:35,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +21: [2023-04-29 11:37:35,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +29: [2023-04-29 11:37:35,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +46: [2023-04-29 11:37:35,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_59_mp_rank_03_optim_states.pt. +46: [2023-04-29 11:37:35,190] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 375 +17: [2023-04-29 11:37:35,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 0: [2023-04-29 11:37:35,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 0: [2023-04-29 11:37:35,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +53: [2023-04-29 11:37:35,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_87_mp_rank_03_optim_states.pt. + 0: [2023-04-29 11:37:35,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +53: [2023-04-29 11:37:35,191] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 431 + 0: [2023-04-29 11:37:35,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +16: [2023-04-29 11:37:35,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +17: [2023-04-29 11:37:35,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +16: [2023-04-29 11:37:35,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +16: [2023-04-29 11:37:35,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +17: [2023-04-29 11:37:35,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +17: [2023-04-29 11:37:35,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +17: [2023-04-29 11:37:35,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +17: [2023-04-29 11:37:35,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +17: [2023-04-29 11:37:35,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +60: [2023-04-29 11:37:35,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +60: [2023-04-29 11:37:35,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +60: [2023-04-29 11:37:35,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +60: [2023-04-29 11:37:35,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +50: [2023-04-29 11:37:35,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_75_mp_rank_03_optim_states.pt. +50: [2023-04-29 11:37:35,196] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 407 + 3: [2023-04-29 11:37:35,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +16: [2023-04-29 11:37:35,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 3: [2023-04-29 11:37:35,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... + 3: [2023-04-29 11:37:35,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +21: [2023-04-29 11:37:35,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +15: [2023-04-29 11:37:35,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 3: [2023-04-29 11:37:35,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt... +16: [2023-04-29 11:37:35,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +17: [2023-04-29 11:37:35,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +17: [2023-04-29 11:37:35,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +17: [2023-04-29 11:37:35,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +17: [2023-04-29 11:37:35,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +15: [2023-04-29 11:37:35,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +15: [2023-04-29 11:37:35,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +22: [2023-04-29 11:37:35,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +15: [2023-04-29 11:37:35,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +31: [2023-04-29 11:37:35,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +31: [2023-04-29 11:37:35,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +31: [2023-04-29 11:37:35,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +20: [2023-04-29 11:37:35,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +31: [2023-04-29 11:37:35,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 5: [2023-04-29 11:37:35,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +16: [2023-04-29 11:37:35,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +22: [2023-04-29 11:37:35,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +20: [2023-04-29 11:37:35,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 5: [2023-04-29 11:37:35,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 5: [2023-04-29 11:37:35,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +20: [2023-04-29 11:37:35,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +21: [2023-04-29 11:37:35,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +21: [2023-04-29 11:37:35,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 4: [2023-04-29 11:37:35,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +21: [2023-04-29 11:37:35,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +22: [2023-04-29 11:37:35,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +22: [2023-04-29 11:37:35,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 3: [2023-04-29 11:37:35,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +20: [2023-04-29 11:37:35,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 4: [2023-04-29 11:37:35,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +20: [2023-04-29 11:37:35,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 5: [2023-04-29 11:37:35,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 5: [2023-04-29 11:37:35,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 3: [2023-04-29 11:37:35,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 3: [2023-04-29 11:37:35,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +60: [2023-04-29 11:37:35,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 4: [2023-04-29 11:37:35,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +60: [2023-04-29 11:37:35,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +20: [2023-04-29 11:37:35,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 9: [2023-04-29 11:37:35,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 9: [2023-04-29 11:37:35,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +46: [2023-04-29 11:37:35,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_56_mp_rank_03_optim_states.pt. + 9: [2023-04-29 11:37:35,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +46: [2023-04-29 11:37:35,224] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 369 +60: [2023-04-29 11:37:35,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +60: [2023-04-29 11:37:35,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +60: [2023-04-29 11:37:35,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +60: [2023-04-29 11:37:35,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +16: [2023-04-29 11:37:35,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +16: [2023-04-29 11:37:35,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +16: [2023-04-29 11:37:35,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +24: [2023-04-29 11:37:35,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +16: [2023-04-29 11:37:35,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 3: [2023-04-29 11:37:35,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +60: [2023-04-29 11:37:35,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +60: [2023-04-29 11:37:35,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +60: [2023-04-29 11:37:35,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +49: [2023-04-29 11:37:35,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_70_mp_rank_03_optim_states.pt. +60: [2023-04-29 11:37:35,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +60: [2023-04-29 11:37:35,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +60: [2023-04-29 11:37:35,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +49: [2023-04-29 11:37:35,228] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 397 +60: [2023-04-29 11:37:35,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +13: [2023-04-29 11:37:35,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +60: [2023-04-29 11:37:35,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +60: [2023-04-29 11:37:35,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... + 4: [2023-04-29 11:37:35,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +60: [2023-04-29 11:37:35,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +24: [2023-04-29 11:37:35,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 9: [2023-04-29 11:37:35,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +20: [2023-04-29 11:37:35,229] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +24: [2023-04-29 11:37:35,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +20: [2023-04-29 11:37:35,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 8: [2023-04-29 11:37:35,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 8: [2023-04-29 11:37:35,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +13: [2023-04-29 11:37:35,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +14: [2023-04-29 11:37:35,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +14: [2023-04-29 11:37:35,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +14: [2023-04-29 11:37:35,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +14: [2023-04-29 11:37:35,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 9: [2023-04-29 11:37:35,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 9: [2023-04-29 11:37:35,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 9: [2023-04-29 11:37:35,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +22: [2023-04-29 11:37:35,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +31: [2023-04-29 11:37:35,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 4: [2023-04-29 11:37:35,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +16: [2023-04-29 11:37:35,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +13: [2023-04-29 11:37:35,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +13: [2023-04-29 11:37:35,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +16: [2023-04-29 11:37:35,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 9: [2023-04-29 11:37:35,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 8: [2023-04-29 11:37:35,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +16: [2023-04-29 11:37:35,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +16: [2023-04-29 11:37:35,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +31: [2023-04-29 11:37:35,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +24: [2023-04-29 11:37:35,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +22: [2023-04-29 11:37:35,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 4: [2023-04-29 11:37:35,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +62: [2023-04-29 11:37:35,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_123_mp_rank_03_optim_states.pt. +62: [2023-04-29 11:37:35,238] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 503 + 8: [2023-04-29 11:37:35,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 4: [2023-04-29 11:37:35,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +31: [2023-04-29 11:37:35,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +31: [2023-04-29 11:37:35,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +15: [2023-04-29 11:37:35,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 6: [2023-04-29 11:37:35,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 6: [2023-04-29 11:37:35,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 4: [2023-04-29 11:37:35,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 6: [2023-04-29 11:37:35,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 6: [2023-04-29 11:37:35,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +49: [2023-04-29 11:37:35,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_69_mp_rank_03_optim_states.pt. +49: [2023-04-29 11:37:35,244] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 395 +15: [2023-04-29 11:37:35,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +17: [2023-04-29 11:37:35,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 6: [2023-04-29 11:37:35,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 6: [2023-04-29 11:37:35,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 6: [2023-04-29 11:37:35,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +52: [2023-04-29 11:37:35,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_83_mp_rank_02_optim_states.pt. +52: [2023-04-29 11:37:35,248] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 422 + 6: [2023-04-29 11:37:35,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +15: [2023-04-29 11:37:35,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 3: [2023-04-29 11:37:35,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +22: [2023-04-29 11:37:35,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +24: [2023-04-29 11:37:35,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +22: [2023-04-29 11:37:35,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 3: [2023-04-29 11:37:35,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +15: [2023-04-29 11:37:35,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +17: [2023-04-29 11:37:35,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +15: [2023-04-29 11:37:35,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 0: [2023-04-29 11:37:35,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +24: [2023-04-29 11:37:35,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +15: [2023-04-29 11:37:35,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 3: [2023-04-29 11:37:35,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +44: [2023-04-29 11:37:35,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_50_mp_rank_03_optim_states.pt. + 3: [2023-04-29 11:37:35,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +44: [2023-04-29 11:37:35,254] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 357 +15: [2023-04-29 11:37:35,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +13: [2023-04-29 11:37:35,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +24: [2023-04-29 11:37:35,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +14: [2023-04-29 11:37:35,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +13: [2023-04-29 11:37:35,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +15: [2023-04-29 11:37:35,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 0: [2023-04-29 11:37:35,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 0: [2023-04-29 11:37:35,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 0: [2023-04-29 11:37:35,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 8: [2023-04-29 11:37:35,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +17: [2023-04-29 11:37:35,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +17: [2023-04-29 11:37:35,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +14: [2023-04-29 11:37:35,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 0: [2023-04-29 11:37:35,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 0: [2023-04-29 11:37:35,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 0: [2023-04-29 11:37:35,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 0: [2023-04-29 11:37:35,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 8: [2023-04-29 11:37:35,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +14: [2023-04-29 11:37:35,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +14: [2023-04-29 11:37:35,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +13: [2023-04-29 11:37:35,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +13: [2023-04-29 11:37:35,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +24: [2023-04-29 11:37:35,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +62: [2023-04-29 11:37:35,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_120_mp_rank_03_optim_states.pt. +62: [2023-04-29 11:37:35,267] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 497 +60: [2023-04-29 11:37:35,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_112_mp_rank_03_optim_states.pt... +60: [2023-04-29 11:37:35,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_113_mp_rank_03_optim_states.pt... + 1: [2023-04-29 11:37:35,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 1: [2023-04-29 11:37:35,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 1: [2023-04-29 11:37:35,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +60: [2023-04-29 11:37:35,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_115_mp_rank_03_optim_states.pt... +60: [2023-04-29 11:37:35,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_114_mp_rank_03_optim_states.pt... + 1: [2023-04-29 11:37:35,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 8: [2023-04-29 11:37:35,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +17: [2023-04-29 11:37:35,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +17: [2023-04-29 11:37:35,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 8: [2023-04-29 11:37:35,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 8: [2023-04-29 11:37:35,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 8: [2023-04-29 11:37:35,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 8: [2023-04-29 11:37:35,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +35: [2023-04-29 11:37:35,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_13_mp_rank_03_optim_states.pt. +35: [2023-04-29 11:37:35,270] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 283 +17: [2023-04-29 11:37:35,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 1: [2023-04-29 11:37:35,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 1: [2023-04-29 11:37:35,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +47: [2023-04-29 11:37:35,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_60_mp_rank_03_optim_states.pt. +47: [2023-04-29 11:37:35,273] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 377 + 1: [2023-04-29 11:37:35,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +17: [2023-04-29 11:37:35,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 1: [2023-04-29 11:37:35,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 3: [2023-04-29 11:37:35,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 3: [2023-04-29 11:37:35,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. + 8: [2023-04-29 11:37:35,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +17: [2023-04-29 11:37:35,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +17: [2023-04-29 11:37:35,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +17: [2023-04-29 11:37:35,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +23: [2023-04-29 11:37:35,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +23: [2023-04-29 11:37:35,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +23: [2023-04-29 11:37:35,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +23: [2023-04-29 11:37:35,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 3: [2023-04-29 11:37:35,278] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +34: [2023-04-29 11:37:35,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_11_mp_rank_02_optim_states.pt. +34: [2023-04-29 11:37:35,279] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 278 +17: [2023-04-29 11:37:35,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 3: [2023-04-29 11:37:35,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_00-model_states.pt. +23: [2023-04-29 11:37:35,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 3: [2023-04-29 11:37:35,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 3: [2023-04-29 11:37:35,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +23: [2023-04-29 11:37:35,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +23: [2023-04-29 11:37:35,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +23: [2023-04-29 11:37:35,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +47: [2023-04-29 11:37:35,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_63_mp_rank_03_optim_states.pt. + 3: [2023-04-29 11:37:35,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... +47: [2023-04-29 11:37:35,284] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 383 +63: [2023-04-29 11:37:35,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_127_mp_rank_03_optim_states.pt. +63: [2023-04-29 11:37:35,284] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 511 +32: [2023-04-29 11:37:35,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_3_mp_rank_03_optim_states.pt. +32: [2023-04-29 11:37:35,285] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 263 + 3: [2023-04-29 11:37:35,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt... + 0: [2023-04-29 11:37:35,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 0: [2023-04-29 11:37:35,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 8: [2023-04-29 11:37:35,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 0: [2023-04-29 11:37:35,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 0: [2023-04-29 11:37:35,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 0: [2023-04-29 11:37:35,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 0: [2023-04-29 11:37:35,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 0: [2023-04-29 11:37:35,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 0: [2023-04-29 11:37:35,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +31: [2023-04-29 11:37:35,301] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +63: [2023-04-29 11:37:35,301] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_125_mp_rank_03_optim_states.pt. +63: [2023-04-29 11:37:35,301] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 507 + 8: [2023-04-29 11:37:35,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +18: [2023-04-29 11:37:35,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +18: [2023-04-29 11:37:35,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +18: [2023-04-29 11:37:35,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +18: [2023-04-29 11:37:35,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 8: [2023-04-29 11:37:35,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +32: [2023-04-29 11:37:35,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_1_mp_rank_03_optim_states.pt. +32: [2023-04-29 11:37:35,306] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 259 +16: [2023-04-29 11:37:35,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +16: [2023-04-29 11:37:35,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +16: [2023-04-29 11:37:35,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 8: [2023-04-29 11:37:35,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +17: [2023-04-29 11:37:35,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +31: [2023-04-29 11:37:35,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +17: [2023-04-29 11:37:35,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +18: [2023-04-29 11:37:35,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +17: [2023-04-29 11:37:35,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +17: [2023-04-29 11:37:35,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 6: [2023-04-29 11:37:35,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 6: [2023-04-29 11:37:35,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +31: [2023-04-29 11:37:35,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +31: [2023-04-29 11:37:35,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +31: [2023-04-29 11:37:35,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +16: [2023-04-29 11:37:35,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +18: [2023-04-29 11:37:35,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +18: [2023-04-29 11:37:35,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +29: [2023-04-29 11:37:35,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +29: [2023-04-29 11:37:35,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +29: [2023-04-29 11:37:35,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +29: [2023-04-29 11:37:35,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +18: [2023-04-29 11:37:35,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 6: [2023-04-29 11:37:35,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 6: [2023-04-29 11:37:35,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +29: [2023-04-29 11:37:35,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +29: [2023-04-29 11:37:35,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +29: [2023-04-29 11:37:35,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +29: [2023-04-29 11:37:35,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +31: [2023-04-29 11:37:35,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +48: [2023-04-29 11:37:35,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_64_mp_rank_03_optim_states.pt. +31: [2023-04-29 11:37:35,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +48: [2023-04-29 11:37:35,321] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 385 +31: [2023-04-29 11:37:35,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +14: [2023-04-29 11:37:35,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +63: [2023-04-29 11:37:35,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_126_mp_rank_03_optim_states.pt. +63: [2023-04-29 11:37:35,323] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 509 +12: [2023-04-29 11:37:35,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +12: [2023-04-29 11:37:35,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 1: [2023-04-29 11:37:35,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +14: [2023-04-29 11:37:35,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +48: [2023-04-29 11:37:35,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_67_mp_rank_03_optim_states.pt. +12: [2023-04-29 11:37:35,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +48: [2023-04-29 11:37:35,329] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 391 +12: [2023-04-29 11:37:35,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +12: [2023-04-29 11:37:35,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +12: [2023-04-29 11:37:35,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +56: [2023-04-29 11:37:35,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_99_mp_rank_02_optim_states.pt. +56: [2023-04-29 11:37:35,334] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 454 +12: [2023-04-29 11:37:35,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +14: [2023-04-29 11:37:35,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +12: [2023-04-29 11:37:35,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 1: [2023-04-29 11:37:35,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +16: [2023-04-29 11:37:35,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 6: [2023-04-29 11:37:35,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +14: [2023-04-29 11:37:35,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 6: [2023-04-29 11:37:35,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 1: [2023-04-29 11:37:35,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +14: [2023-04-29 11:37:35,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 6: [2023-04-29 11:37:35,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 6: [2023-04-29 11:37:35,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +16: [2023-04-29 11:37:35,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +47: [2023-04-29 11:37:35,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_61_mp_rank_03_optim_states.pt. +47: [2023-04-29 11:37:35,343] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 379 +45: [2023-04-29 11:37:35,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_52_mp_rank_03_optim_states.pt. +45: [2023-04-29 11:37:35,344] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 361 +14: [2023-04-29 11:37:35,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +23: [2023-04-29 11:37:35,345] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +16: [2023-04-29 11:37:35,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +14: [2023-04-29 11:37:35,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +14: [2023-04-29 11:37:35,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +46: [2023-04-29 11:37:35,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_57_mp_rank_03_optim_states.pt. +46: [2023-04-29 11:37:35,347] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 371 +10: [2023-04-29 11:37:35,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +10: [2023-04-29 11:37:35,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +23: [2023-04-29 11:37:35,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 1: [2023-04-29 11:37:35,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +16: [2023-04-29 11:37:35,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +10: [2023-04-29 11:37:35,354] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +23: [2023-04-29 11:37:35,354] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +23: [2023-04-29 11:37:35,354] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +10: [2023-04-29 11:37:35,354] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 1: [2023-04-29 11:37:35,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +10: [2023-04-29 11:37:35,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +58: [2023-04-29 11:37:35,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_105_mp_rank_03_optim_states.pt. +58: [2023-04-29 11:37:35,357] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 467 +10: [2023-04-29 11:37:35,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +62: [2023-04-29 11:37:35,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_121_mp_rank_03_optim_states.pt. +62: [2023-04-29 11:37:35,358] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 499 +58: [2023-04-29 11:37:35,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_107_mp_rank_03_optim_states.pt. +58: [2023-04-29 11:37:35,359] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 471 +10: [2023-04-29 11:37:35,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +10: [2023-04-29 11:37:35,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 0: [2023-04-29 11:37:35,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +41: [2023-04-29 11:37:35,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_37_mp_rank_03_optim_states.pt. +48: [2023-04-29 11:37:35,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_65_mp_rank_03_optim_states.pt. +41: [2023-04-29 11:37:35,362] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 331 +48: [2023-04-29 11:37:35,363] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 387 + 1: [2023-04-29 11:37:35,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 8: [2023-04-29 11:37:35,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +14: [2023-04-29 11:37:35,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +14: [2023-04-29 11:37:35,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +14: [2023-04-29 11:37:35,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +14: [2023-04-29 11:37:35,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +43: [2023-04-29 11:37:35,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_46_mp_rank_03_optim_states.pt. +43: [2023-04-29 11:37:35,365] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 349 +59: [2023-04-29 11:37:35,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_109_mp_rank_03_optim_states.pt. +59: [2023-04-29 11:37:35,366] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 475 + 0: [2023-04-29 11:37:35,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +57: [2023-04-29 11:37:35,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_102_mp_rank_02_optim_states.pt. + 1: [2023-04-29 11:37:35,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +57: [2023-04-29 11:37:35,367] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 460 + 0: [2023-04-29 11:37:35,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 2: [2023-04-29 11:37:35,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 8: [2023-04-29 11:37:35,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +23: [2023-04-29 11:37:35,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +11: [2023-04-29 11:37:35,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +11: [2023-04-29 11:37:35,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +11: [2023-04-29 11:37:35,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +51: [2023-04-29 11:37:35,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_76_mp_rank_02_optim_states.pt. +11: [2023-04-29 11:37:35,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +51: [2023-04-29 11:37:35,371] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 408 +51: [2023-04-29 11:37:35,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_78_mp_rank_03_optim_states.pt. +51: [2023-04-29 11:37:35,371] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 413 +14: [2023-04-29 11:37:35,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +18: [2023-04-29 11:37:35,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +35: [2023-04-29 11:37:35,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_15_mp_rank_03_optim_states.pt. +14: [2023-04-29 11:37:35,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +35: [2023-04-29 11:37:35,373] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 287 +14: [2023-04-29 11:37:35,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 2: [2023-04-29 11:37:35,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +14: [2023-04-29 11:37:35,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 0: [2023-04-29 11:37:35,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 0: [2023-04-29 11:37:35,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 0: [2023-04-29 11:37:35,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +38: [2023-04-29 11:37:35,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_27_mp_rank_03_optim_states.pt. + 2: [2023-04-29 11:37:35,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 2: [2023-04-29 11:37:35,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +38: [2023-04-29 11:37:35,376] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 311 +13: [2023-04-29 11:37:35,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +13: [2023-04-29 11:37:35,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +13: [2023-04-29 11:37:35,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +23: [2023-04-29 11:37:35,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +13: [2023-04-29 11:37:35,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 8: [2023-04-29 11:37:35,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 8: [2023-04-29 11:37:35,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 0: [2023-04-29 11:37:35,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 0: [2023-04-29 11:37:35,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 1: [2023-04-29 11:37:35,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +33: [2023-04-29 11:37:35,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_6_mp_rank_03_optim_states.pt. +33: [2023-04-29 11:37:35,382] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 269 +23: [2023-04-29 11:37:35,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +29: [2023-04-29 11:37:35,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +23: [2023-04-29 11:37:35,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 8: [2023-04-29 11:37:35,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 8: [2023-04-29 11:37:35,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +62: [2023-04-29 11:37:35,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_122_mp_rank_03_optim_states.pt. +62: [2023-04-29 11:37:35,386] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 501 +29: [2023-04-29 11:37:35,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +29: [2023-04-29 11:37:35,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 8: [2023-04-29 11:37:35,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +29: [2023-04-29 11:37:35,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +18: [2023-04-29 11:37:35,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +18: [2023-04-29 11:37:35,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +18: [2023-04-29 11:37:35,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +25: [2023-04-29 11:37:35,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +25: [2023-04-29 11:37:35,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +25: [2023-04-29 11:37:35,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +25: [2023-04-29 11:37:35,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +38: [2023-04-29 11:37:35,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_25_mp_rank_03_optim_states.pt. + 8: [2023-04-29 11:37:35,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +38: [2023-04-29 11:37:35,395] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 307 +57: [2023-04-29 11:37:35,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_101_mp_rank_03_optim_states.pt. +57: [2023-04-29 11:37:35,395] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 459 +18: [2023-04-29 11:37:35,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +32: [2023-04-29 11:37:35,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_0_mp_rank_03_optim_states.pt. +11: [2023-04-29 11:37:35,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +32: [2023-04-29 11:37:35,397] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 257 +25: [2023-04-29 11:37:35,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +25: [2023-04-29 11:37:35,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +11: [2023-04-29 11:37:35,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +11: [2023-04-29 11:37:35,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +11: [2023-04-29 11:37:35,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +12: [2023-04-29 11:37:35,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +25: [2023-04-29 11:37:35,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +13: [2023-04-29 11:37:35,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +25: [2023-04-29 11:37:35,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +51: [2023-04-29 11:37:35,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_79_mp_rank_02_optim_states.pt. +51: [2023-04-29 11:37:35,402] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 414 +12: [2023-04-29 11:37:35,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +12: [2023-04-29 11:37:35,405] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +13: [2023-04-29 11:37:35,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 1: [2023-04-29 11:37:35,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 1: [2023-04-29 11:37:35,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 1: [2023-04-29 11:37:35,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 1: [2023-04-29 11:37:35,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +32: [2023-04-29 11:37:35,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_2_mp_rank_02_optim_states.pt. +32: [2023-04-29 11:37:35,408] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 260 +12: [2023-04-29 11:37:35,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +36: [2023-04-29 11:37:35,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_18_mp_rank_03_optim_states.pt. +36: [2023-04-29 11:37:35,409] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 293 +25: [2023-04-29 11:37:35,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +25: [2023-04-29 11:37:35,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +25: [2023-04-29 11:37:35,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +25: [2023-04-29 11:37:35,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +52: [2023-04-29 11:37:35,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_82_mp_rank_02_optim_states.pt. +13: [2023-04-29 11:37:35,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +52: [2023-04-29 11:37:35,410] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 420 +13: [2023-04-29 11:37:35,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +29: [2023-04-29 11:37:35,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +29: [2023-04-29 11:37:35,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +29: [2023-04-29 11:37:35,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +29: [2023-04-29 11:37:35,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +57: [2023-04-29 11:37:35,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_103_mp_rank_02_optim_states.pt. +57: [2023-04-29 11:37:35,418] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 462 +43: [2023-04-29 11:37:35,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_47_mp_rank_03_optim_states.pt. +43: [2023-04-29 11:37:35,418] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 351 +31: [2023-04-29 11:37:35,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +31: [2023-04-29 11:37:35,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +31: [2023-04-29 11:37:35,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +59: [2023-04-29 11:37:35,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_110_mp_rank_03_optim_states.pt. +59: [2023-04-29 11:37:35,420] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 477 +31: [2023-04-29 11:37:35,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +30: [2023-04-29 11:37:35,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +30: [2023-04-29 11:37:35,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +30: [2023-04-29 11:37:35,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +30: [2023-04-29 11:37:35,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 9: [2023-04-29 11:37:35,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 9: [2023-04-29 11:37:35,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +61: [2023-04-29 11:37:35,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_118_mp_rank_03_optim_states.pt. +61: [2023-04-29 11:37:35,422] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 493 +51: [2023-04-29 11:37:35,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_79_mp_rank_03_optim_states.pt. +51: [2023-04-29 11:37:35,422] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 415 +35: [2023-04-29 11:37:35,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_12_mp_rank_03_optim_states.pt. +35: [2023-04-29 11:37:35,423] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 281 + 9: [2023-04-29 11:37:35,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +18: [2023-04-29 11:37:35,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 9: [2023-04-29 11:37:35,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +18: [2023-04-29 11:37:35,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +18: [2023-04-29 11:37:35,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +57: [2023-04-29 11:37:35,425] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_100_mp_rank_03_optim_states.pt. +57: [2023-04-29 11:37:35,425] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 457 +10: [2023-04-29 11:37:35,425] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +10: [2023-04-29 11:37:35,425] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +10: [2023-04-29 11:37:35,425] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +30: [2023-04-29 11:37:35,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +30: [2023-04-29 11:37:35,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +26: [2023-04-29 11:37:35,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +26: [2023-04-29 11:37:35,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +31: [2023-04-29 11:37:35,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +31: [2023-04-29 11:37:35,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +31: [2023-04-29 11:37:35,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +26: [2023-04-29 11:37:35,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +30: [2023-04-29 11:37:35,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +26: [2023-04-29 11:37:35,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +33: [2023-04-29 11:37:35,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_5_mp_rank_03_optim_states.pt. +30: [2023-04-29 11:37:35,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +31: [2023-04-29 11:37:35,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +33: [2023-04-29 11:37:35,428] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 267 +27: [2023-04-29 11:37:35,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +27: [2023-04-29 11:37:35,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +27: [2023-04-29 11:37:35,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +27: [2023-04-29 11:37:35,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +10: [2023-04-29 11:37:35,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +61: [2023-04-29 11:37:35,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_117_mp_rank_03_optim_states.pt. +51: [2023-04-29 11:37:35,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_77_mp_rank_03_optim_states.pt. + 9: [2023-04-29 11:37:35,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +59: [2023-04-29 11:37:35,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_111_mp_rank_03_optim_states.pt. +15: [2023-04-29 11:37:35,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +19: [2023-04-29 11:37:35,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +19: [2023-04-29 11:37:35,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +12: [2023-04-29 11:37:35,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +34: [2023-04-29 11:37:35,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_10_mp_rank_03_optim_states.pt. +26: [2023-04-29 11:37:35,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +27: [2023-04-29 11:37:35,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +25: [2023-04-29 11:37:35,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +47: [2023-04-29 11:37:35,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_62_mp_rank_03_optim_states.pt. +33: [2023-04-29 11:37:35,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_7_mp_rank_03_optim_states.pt. +41: [2023-04-29 11:37:35,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_38_mp_rank_03_optim_states.pt. +13: [2023-04-29 11:37:35,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +42: [2023-04-29 11:37:35,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_42_mp_rank_03_optim_states.pt. + 2: [2023-04-29 11:37:35,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +10: [2023-04-29 11:37:35,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 1: [2023-04-29 11:37:35,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +38: [2023-04-29 11:37:35,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_26_mp_rank_03_optim_states.pt. +21: [2023-04-29 11:37:35,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 4: [2023-04-29 11:37:35,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 4: [2023-04-29 11:37:35,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +20: [2023-04-29 11:37:35,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +30: [2023-04-29 11:37:35,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +28: [2023-04-29 11:37:35,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +28: [2023-04-29 11:37:35,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +52: [2023-04-29 11:37:35,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_82_mp_rank_03_optim_states.pt. + 6: [2023-04-29 11:37:35,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 6: [2023-04-29 11:37:35,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +11: [2023-04-29 11:37:35,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +14: [2023-04-29 11:37:35,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +45: [2023-04-29 11:37:35,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_53_mp_rank_03_optim_states.pt. +61: [2023-04-29 11:37:35,433] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 491 +51: [2023-04-29 11:37:35,471] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 411 + 9: [2023-04-29 11:37:35,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 9: [2023-04-29 11:37:35,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +59: [2023-04-29 11:37:35,450] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 479 +15: [2023-04-29 11:37:35,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +15: [2023-04-29 11:37:35,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +19: [2023-04-29 11:37:35,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +12: [2023-04-29 11:37:35,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +34: [2023-04-29 11:37:35,486] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 277 +26: [2023-04-29 11:37:35,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +27: [2023-04-29 11:37:35,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +25: [2023-04-29 11:37:35,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +47: [2023-04-29 11:37:35,437] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 381 +33: [2023-04-29 11:37:35,439] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 271 +41: [2023-04-29 11:37:35,477] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 333 + 5: [2023-04-29 11:37:35,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +42: [2023-04-29 11:37:35,437] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 341 + 2: [2023-04-29 11:37:35,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +10: [2023-04-29 11:37:35,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 1: [2023-04-29 11:37:35,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +38: [2023-04-29 11:37:35,482] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 309 +21: [2023-04-29 11:37:35,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +21: [2023-04-29 11:37:35,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 4: [2023-04-29 11:37:35,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +20: [2023-04-29 11:37:35,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +20: [2023-04-29 11:37:35,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +30: [2023-04-29 11:37:35,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +28: [2023-04-29 11:37:35,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +52: [2023-04-29 11:37:35,434] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 421 + 6: [2023-04-29 11:37:35,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +14: [2023-04-29 11:37:35,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +45: [2023-04-29 11:37:35,467] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 363 +51: [2023-04-29 11:37:35,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_78_mp_rank_02_optim_states.pt. + 9: [2023-04-29 11:37:35,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +15: [2023-04-29 11:37:35,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +19: [2023-04-29 11:37:35,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +56: [2023-04-29 11:37:35,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_99_mp_rank_03_optim_states.pt. +12: [2023-04-29 11:37:35,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +26: [2023-04-29 11:37:35,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +27: [2023-04-29 11:37:35,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +25: [2023-04-29 11:37:35,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +13: [2023-04-29 11:37:35,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 5: [2023-04-29 11:37:35,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 5: [2023-04-29 11:37:35,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 5: [2023-04-29 11:37:35,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +42: [2023-04-29 11:37:35,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_43_mp_rank_03_optim_states.pt. + 2: [2023-04-29 11:37:35,447] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,447] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +10: [2023-04-29 11:37:35,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 1: [2023-04-29 11:37:35,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 1: [2023-04-29 11:37:35,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +21: [2023-04-29 11:37:35,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 4: [2023-04-29 11:37:35,473] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +20: [2023-04-29 11:37:35,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +30: [2023-04-29 11:37:35,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +28: [2023-04-29 11:37:35,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 6: [2023-04-29 11:37:35,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +11: [2023-04-29 11:37:35,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +14: [2023-04-29 11:37:35,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +45: [2023-04-29 11:37:35,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_55_mp_rank_03_optim_states.pt. +51: [2023-04-29 11:37:35,483] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 412 +15: [2023-04-29 11:37:35,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +19: [2023-04-29 11:37:35,470] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +12: [2023-04-29 11:37:35,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +26: [2023-04-29 11:37:35,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +27: [2023-04-29 11:37:35,448] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +25: [2023-04-29 11:37:35,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +13: [2023-04-29 11:37:35,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +13: [2023-04-29 11:37:35,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +13: [2023-04-29 11:37:35,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +42: [2023-04-29 11:37:35,455] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 343 + 2: [2023-04-29 11:37:35,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +10: [2023-04-29 11:37:35,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +21: [2023-04-29 11:37:35,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 4: [2023-04-29 11:37:35,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 4: [2023-04-29 11:37:35,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 4: [2023-04-29 11:37:35,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +20: [2023-04-29 11:37:35,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +30: [2023-04-29 11:37:35,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +28: [2023-04-29 11:37:35,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +11: [2023-04-29 11:37:35,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +11: [2023-04-29 11:37:35,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +14: [2023-04-29 11:37:35,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +45: [2023-04-29 11:37:35,477] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 367 +15: [2023-04-29 11:37:35,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +19: [2023-04-29 11:37:35,470] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +56: [2023-04-29 11:37:35,488] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 455 +27: [2023-04-29 11:37:35,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +25: [2023-04-29 11:37:35,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +21: [2023-04-29 11:37:35,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 4: [2023-04-29 11:37:35,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +20: [2023-04-29 11:37:35,470] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +20: [2023-04-29 11:37:35,470] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +30: [2023-04-29 11:37:35,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +28: [2023-04-29 11:37:35,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +11: [2023-04-29 11:37:35,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +14: [2023-04-29 11:37:35,470] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +15: [2023-04-29 11:37:35,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +19: [2023-04-29 11:37:35,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +27: [2023-04-29 11:37:35,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +25: [2023-04-29 11:37:35,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +21: [2023-04-29 11:37:35,462] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +20: [2023-04-29 11:37:35,470] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +30: [2023-04-29 11:37:35,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +28: [2023-04-29 11:37:35,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +11: [2023-04-29 11:37:35,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +11: [2023-04-29 11:37:35,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +14: [2023-04-29 11:37:35,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +15: [2023-04-29 11:37:35,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +19: [2023-04-29 11:37:35,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +27: [2023-04-29 11:37:35,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +25: [2023-04-29 11:37:35,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +21: [2023-04-29 11:37:35,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +30: [2023-04-29 11:37:35,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +30: [2023-04-29 11:37:35,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +28: [2023-04-29 11:37:35,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +11: [2023-04-29 11:37:35,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +27: [2023-04-29 11:37:35,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +25: [2023-04-29 11:37:35,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +27: [2023-04-29 11:37:35,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +27: [2023-04-29 11:37:35,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +27: [2023-04-29 11:37:35,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +27: [2023-04-29 11:37:35,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +14: [2023-04-29 11:37:35,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +14: [2023-04-29 11:37:35,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +31: [2023-04-29 11:37:35,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +61: [2023-04-29 11:37:35,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_119_mp_rank_03_optim_states.pt. +13: [2023-04-29 11:37:35,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +13: [2023-04-29 11:37:35,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +61: [2023-04-29 11:37:35,491] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 495 +13: [2023-04-29 11:37:35,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +23: [2023-04-29 11:37:35,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +23: [2023-04-29 11:37:35,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +23: [2023-04-29 11:37:35,495] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +23: [2023-04-29 11:37:35,495] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +36: [2023-04-29 11:37:35,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_16_mp_rank_03_optim_states.pt. +36: [2023-04-29 11:37:35,496] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 289 +25: [2023-04-29 11:37:35,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +52: [2023-04-29 11:37:35,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_80_mp_rank_03_optim_states.pt. +39: [2023-04-29 11:37:35,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +39: [2023-04-29 11:37:35,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +31: [2023-04-29 11:37:35,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +31: [2023-04-29 11:37:35,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +38: [2023-04-29 11:37:35,499] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_24_mp_rank_03_optim_states.pt. +52: [2023-04-29 11:37:35,499] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 417 +31: [2023-04-29 11:37:35,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +38: [2023-04-29 11:37:35,499] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 305 + 1: [2023-04-29 11:37:35,499] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +39: [2023-04-29 11:37:35,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +39: [2023-04-29 11:37:35,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_44-model_01-model_states.pt. +30: [2023-04-29 11:37:35,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +28: [2023-04-29 11:37:35,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +28: [2023-04-29 11:37:35,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +28: [2023-04-29 11:37:35,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +28: [2023-04-29 11:37:35,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 9: [2023-04-29 11:37:35,502] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 9: [2023-04-29 11:37:35,502] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +30: [2023-04-29 11:37:35,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 9: [2023-04-29 11:37:35,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 1: [2023-04-29 11:37:35,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 9: [2023-04-29 11:37:35,505] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 6: [2023-04-29 11:37:35,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +42: [2023-04-29 11:37:35,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_40_mp_rank_03_optim_states.pt. +42: [2023-04-29 11:37:35,506] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 337 +21: [2023-04-29 11:37:35,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +21: [2023-04-29 11:37:35,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +21: [2023-04-29 11:37:35,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 6: [2023-04-29 11:37:35,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +21: [2023-04-29 11:37:35,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +28: [2023-04-29 11:37:35,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +28: [2023-04-29 11:37:35,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 6: [2023-04-29 11:37:35,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 1: [2023-04-29 11:37:35,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 6: [2023-04-29 11:37:35,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +52: [2023-04-29 11:37:35,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_81_mp_rank_03_optim_states.pt. +52: [2023-04-29 11:37:35,508] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 419 +25: [2023-04-29 11:37:35,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 1: [2023-04-29 11:37:35,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +25: [2023-04-29 11:37:35,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +25: [2023-04-29 11:37:35,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 1: [2023-04-29 11:37:35,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +21: [2023-04-29 11:37:35,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +58: [2023-04-29 11:37:35,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_106_mp_rank_03_optim_states.pt. +58: [2023-04-29 11:37:35,512] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 469 +41: [2023-04-29 11:37:35,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_36_mp_rank_03_optim_states.pt. +41: [2023-04-29 11:37:35,513] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 329 +27: [2023-04-29 11:37:35,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +26: [2023-04-29 11:37:35,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +26: [2023-04-29 11:37:35,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 1: [2023-04-29 11:37:35,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +19: [2023-04-29 11:37:35,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +19: [2023-04-29 11:37:35,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +12: [2023-04-29 11:37:35,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +12: [2023-04-29 11:37:35,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +21: [2023-04-29 11:37:35,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +21: [2023-04-29 11:37:35,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +21: [2023-04-29 11:37:35,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +25: [2023-04-29 11:37:35,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +31: [2023-04-29 11:37:35,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 1: [2023-04-29 11:37:35,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +25: [2023-04-29 11:37:35,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +25: [2023-04-29 11:37:35,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +26: [2023-04-29 11:37:35,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +12: [2023-04-29 11:37:35,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +30: [2023-04-29 11:37:35,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +30: [2023-04-29 11:37:35,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +28: [2023-04-29 11:37:35,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +12: [2023-04-29 11:37:35,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +28: [2023-04-29 11:37:35,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +26: [2023-04-29 11:37:35,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +51: [2023-04-29 11:37:35,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_76_mp_rank_03_optim_states.pt. +51: [2023-04-29 11:37:35,518] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 409 +25: [2023-04-29 11:37:35,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +61: [2023-04-29 11:37:35,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_116_mp_rank_03_optim_states.pt. + 1: [2023-04-29 11:37:35,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +61: [2023-04-29 11:37:35,518] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 489 +19: [2023-04-29 11:37:35,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +19: [2023-04-29 11:37:35,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +19: [2023-04-29 11:37:35,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +19: [2023-04-29 11:37:35,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 7: [2023-04-29 11:37:35,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 7: [2023-04-29 11:37:35,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +56: [2023-04-29 11:37:35,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_97_mp_rank_03_optim_states.pt. + 2: [2023-04-29 11:37:35,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 2: [2023-04-29 11:37:35,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 2: [2023-04-29 11:37:35,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 2: [2023-04-29 11:37:35,502] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 2: [2023-04-29 11:37:35,502] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +56: [2023-04-29 11:37:35,520] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 451 + 7: [2023-04-29 11:37:35,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 7: [2023-04-29 11:37:35,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +25: [2023-04-29 11:37:35,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +26: [2023-04-29 11:37:35,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +26: [2023-04-29 11:37:35,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +26: [2023-04-29 11:37:35,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +26: [2023-04-29 11:37:35,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +25: [2023-04-29 11:37:35,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +21: [2023-04-29 11:37:35,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +40: [2023-04-29 11:37:35,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_35_mp_rank_03_optim_states.pt. +19: [2023-04-29 11:37:35,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +19: [2023-04-29 11:37:35,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +40: [2023-04-29 11:37:35,524] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 327 +25: [2023-04-29 11:37:35,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +26: [2023-04-29 11:37:35,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +39: [2023-04-29 11:37:35,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 2: [2023-04-29 11:37:35,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +26: [2023-04-29 11:37:35,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +39: [2023-04-29 11:37:35,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +23: [2023-04-29 11:37:35,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +23: [2023-04-29 11:37:35,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +39: [2023-04-29 11:37:35,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... + 7: [2023-04-29 11:37:35,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 7: [2023-04-29 11:37:35,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +21: [2023-04-29 11:37:35,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +21: [2023-04-29 11:37:35,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +30: [2023-04-29 11:37:35,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 7: [2023-04-29 11:37:35,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +27: [2023-04-29 11:37:35,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +27: [2023-04-29 11:37:35,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +39: [2023-04-29 11:37:35,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 2: [2023-04-29 11:37:35,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +39: [2023-04-29 11:37:35,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +39: [2023-04-29 11:37:35,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +20: [2023-04-29 11:37:35,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +39: [2023-04-29 11:37:35,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... +39: [2023-04-29 11:37:35,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. + 7: [2023-04-29 11:37:35,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +39: [2023-04-29 11:37:35,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +39: [2023-04-29 11:37:35,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +39: [2023-04-29 11:37:35,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +23: [2023-04-29 11:37:35,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +23: [2023-04-29 11:37:35,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +27: [2023-04-29 11:37:35,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +39: [2023-04-29 11:37:35,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +25: [2023-04-29 11:37:35,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 2: [2023-04-29 11:37:35,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +27: [2023-04-29 11:37:35,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +26: [2023-04-29 11:37:35,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +26: [2023-04-29 11:37:35,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +26: [2023-04-29 11:37:35,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +26: [2023-04-29 11:37:35,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +31: [2023-04-29 11:37:35,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +31: [2023-04-29 11:37:35,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +31: [2023-04-29 11:37:35,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 5: [2023-04-29 11:37:35,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +28: [2023-04-29 11:37:35,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +39: [2023-04-29 11:37:35,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt... + 9: [2023-04-29 11:37:35,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +28: [2023-04-29 11:37:35,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +39: [2023-04-29 11:37:35,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_00-model_states.pt. +39: [2023-04-29 11:37:35,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt... +39: [2023-04-29 11:37:35,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_46-model_01-model_states.pt. +57: [2023-04-29 11:37:35,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_103_mp_rank_03_optim_states.pt. + 4: [2023-04-29 11:37:35,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +57: [2023-04-29 11:37:35,534] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 463 +21: [2023-04-29 11:37:35,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +30: [2023-04-29 11:37:35,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +27: [2023-04-29 11:37:35,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 9: [2023-04-29 11:37:35,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 9: [2023-04-29 11:37:35,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +27: [2023-04-29 11:37:35,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +28: [2023-04-29 11:37:35,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +28: [2023-04-29 11:37:35,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +27: [2023-04-29 11:37:35,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +27: [2023-04-29 11:37:35,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +20: [2023-04-29 11:37:35,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +30: [2023-04-29 11:37:35,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +27: [2023-04-29 11:37:35,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +26: [2023-04-29 11:37:35,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 7: [2023-04-29 11:37:35,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 9: [2023-04-29 11:37:35,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 7: [2023-04-29 11:37:35,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 7: [2023-04-29 11:37:35,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +26: [2023-04-29 11:37:35,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 7: [2023-04-29 11:37:35,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +28: [2023-04-29 11:37:35,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +28: [2023-04-29 11:37:35,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +20: [2023-04-29 11:37:35,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +19: [2023-04-29 11:37:35,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 4: [2023-04-29 11:37:35,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 4: [2023-04-29 11:37:35,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 4: [2023-04-29 11:37:35,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 4: [2023-04-29 11:37:35,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +12: [2023-04-29 11:37:35,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +10: [2023-04-29 11:37:35,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +10: [2023-04-29 11:37:35,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +10: [2023-04-29 11:37:35,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +10: [2023-04-29 11:37:35,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +21: [2023-04-29 11:37:35,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +15: [2023-04-29 11:37:35,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +20: [2023-04-29 11:37:35,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +30: [2023-04-29 11:37:35,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +18: [2023-04-29 11:37:35,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +18: [2023-04-29 11:37:35,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +40: [2023-04-29 11:37:35,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_33_mp_rank_03_optim_states.pt. +12: [2023-04-29 11:37:35,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +18: [2023-04-29 11:37:35,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +40: [2023-04-29 11:37:35,545] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 323 +18: [2023-04-29 11:37:35,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +12: [2023-04-29 11:37:35,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +62: [2023-04-29 11:37:35,546] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 496 +62: [2023-04-29 11:37:35,546] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 498 +12: [2023-04-29 11:37:35,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +27: [2023-04-29 11:37:35,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +27: [2023-04-29 11:37:35,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +19: [2023-04-29 11:37:35,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 5: [2023-04-29 11:37:35,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +22: [2023-04-29 11:37:35,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +22: [2023-04-29 11:37:35,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +28: [2023-04-29 11:37:35,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +15: [2023-04-29 11:37:35,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +15: [2023-04-29 11:37:35,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +15: [2023-04-29 11:37:35,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +28: [2023-04-29 11:37:35,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +19: [2023-04-29 11:37:35,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +19: [2023-04-29 11:37:35,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +21: [2023-04-29 11:37:35,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +21: [2023-04-29 11:37:35,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +22: [2023-04-29 11:37:35,551] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +22: [2023-04-29 11:37:35,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +22: [2023-04-29 11:37:35,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +22: [2023-04-29 11:37:35,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +19: [2023-04-29 11:37:35,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +13: [2023-04-29 11:37:35,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +13: [2023-04-29 11:37:35,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +13: [2023-04-29 11:37:35,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +13: [2023-04-29 11:37:35,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +22: [2023-04-29 11:37:35,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +59: [2023-04-29 11:37:35,555] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 474 +22: [2023-04-29 11:37:35,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +22: [2023-04-29 11:37:35,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +22: [2023-04-29 11:37:35,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +30: [2023-04-29 11:37:35,558] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +19: [2023-04-29 11:37:35,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +13: [2023-04-29 11:37:35,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +13: [2023-04-29 11:37:35,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +19: [2023-04-29 11:37:35,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +13: [2023-04-29 11:37:35,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +22: [2023-04-29 11:37:35,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +13: [2023-04-29 11:37:35,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 4: [2023-04-29 11:37:35,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 4: [2023-04-29 11:37:35,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 4: [2023-04-29 11:37:35,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +21: [2023-04-29 11:37:35,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +22: [2023-04-29 11:37:35,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +19: [2023-04-29 11:37:35,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +30: [2023-04-29 11:37:35,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 4: [2023-04-29 11:37:35,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 5: [2023-04-29 11:37:35,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 5: [2023-04-29 11:37:35,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +52: [2023-04-29 11:37:35,565] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 416 +62: [2023-04-29 11:37:35,566] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 500 + 7: [2023-04-29 11:37:35,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +39: [2023-04-29 11:37:35,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_29_mp_rank_03_optim_states.pt... +39: [2023-04-29 11:37:35,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_31_mp_rank_03_optim_states.pt... +39: [2023-04-29 11:37:35,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_30_mp_rank_03_optim_states.pt... +39: [2023-04-29 11:37:35,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_28_mp_rank_03_optim_states.pt... +62: [2023-04-29 11:37:35,568] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 502 +10: [2023-04-29 11:37:35,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +44: [2023-04-29 11:37:35,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_49_mp_rank_03_optim_states.pt. +30: [2023-04-29 11:37:35,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +44: [2023-04-29 11:37:35,568] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 355 + 4: [2023-04-29 11:37:35,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 5: [2023-04-29 11:37:35,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +30: [2023-04-29 11:37:35,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +18: [2023-04-29 11:37:35,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +10: [2023-04-29 11:37:35,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +15: [2023-04-29 11:37:35,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 6: [2023-04-29 11:37:35,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 6: [2023-04-29 11:37:35,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +10: [2023-04-29 11:37:35,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 6: [2023-04-29 11:37:35,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +18: [2023-04-29 11:37:35,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 6: [2023-04-29 11:37:35,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 7: [2023-04-29 11:37:35,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 7: [2023-04-29 11:37:35,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +18: [2023-04-29 11:37:35,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +10: [2023-04-29 11:37:35,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 7: [2023-04-29 11:37:35,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 6: [2023-04-29 11:37:35,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 6: [2023-04-29 11:37:35,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 4: [2023-04-29 11:37:35,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +33: [2023-04-29 11:37:35,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_4_mp_rank_03_optim_states.pt. +33: [2023-04-29 11:37:35,576] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 265 +59: [2023-04-29 11:37:35,576] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 472 +18: [2023-04-29 11:37:35,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +22: [2023-04-29 11:37:35,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 6: [2023-04-29 11:37:35,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +21: [2023-04-29 11:37:35,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +29: [2023-04-29 11:37:35,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +29: [2023-04-29 11:37:35,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 6: [2023-04-29 11:37:35,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 4: [2023-04-29 11:37:35,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +29: [2023-04-29 11:37:35,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 6: [2023-04-29 11:37:35,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +29: [2023-04-29 11:37:35,579] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 6: [2023-04-29 11:37:35,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 6: [2023-04-29 11:37:35,579] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 6: [2023-04-29 11:37:35,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +59: [2023-04-29 11:37:35,581] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 478 +22: [2023-04-29 11:37:35,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +15: [2023-04-29 11:37:35,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 6: [2023-04-29 11:37:35,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 6: [2023-04-29 11:37:35,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +15: [2023-04-29 11:37:35,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +15: [2023-04-29 11:37:35,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +36: [2023-04-29 11:37:35,583] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 290 +22: [2023-04-29 11:37:35,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +22: [2023-04-29 11:37:35,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +19: [2023-04-29 11:37:35,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 6: [2023-04-29 11:37:35,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 6: [2023-04-29 11:37:35,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +26: [2023-04-29 11:37:35,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +59: [2023-04-29 11:37:35,587] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 476 + 2: [2023-04-29 11:37:35,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +52: [2023-04-29 11:37:35,588] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 420 +26: [2023-04-29 11:37:35,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +30: [2023-04-29 11:37:35,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +30: [2023-04-29 11:37:35,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +30: [2023-04-29 11:37:35,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +30: [2023-04-29 11:37:35,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +19: [2023-04-29 11:37:35,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +19: [2023-04-29 11:37:35,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +19: [2023-04-29 11:37:35,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +23: [2023-04-29 11:37:35,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +52: [2023-04-29 11:37:35,592] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 422 +21: [2023-04-29 11:37:35,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +21: [2023-04-29 11:37:35,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +21: [2023-04-29 11:37:35,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +43: [2023-04-29 11:37:35,594] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_44_mp_rank_03_optim_states.pt. +27: [2023-04-29 11:37:35,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +27: [2023-04-29 11:37:35,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +27: [2023-04-29 11:37:35,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +27: [2023-04-29 11:37:35,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +43: [2023-04-29 11:37:35,594] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 345 +26: [2023-04-29 11:37:35,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +56: [2023-04-29 11:37:35,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_96_mp_rank_03_optim_states.pt. + 2: [2023-04-29 11:37:35,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 7: [2023-04-29 11:37:35,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +56: [2023-04-29 11:37:35,595] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 449 +23: [2023-04-29 11:37:35,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +23: [2023-04-29 11:37:35,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +20: [2023-04-29 11:37:35,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +20: [2023-04-29 11:37:35,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +20: [2023-04-29 11:37:35,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +20: [2023-04-29 11:37:35,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... + 2: [2023-04-29 11:37:35,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +23: [2023-04-29 11:37:35,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +26: [2023-04-29 11:37:35,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 8: [2023-04-29 11:37:35,600] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 8: [2023-04-29 11:37:35,600] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 8: [2023-04-29 11:37:35,600] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 8: [2023-04-29 11:37:35,600] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +23: [2023-04-29 11:37:35,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 2: [2023-04-29 11:37:35,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 2: [2023-04-29 11:37:35,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +23: [2023-04-29 11:37:35,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +12: [2023-04-29 11:37:35,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +29: [2023-04-29 11:37:35,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 8: [2023-04-29 11:37:35,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +23: [2023-04-29 11:37:35,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 8: [2023-04-29 11:37:35,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 8: [2023-04-29 11:37:35,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +50: [2023-04-29 11:37:35,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_74_mp_rank_03_optim_states.pt. +50: [2023-04-29 11:37:35,606] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 405 + 8: [2023-04-29 11:37:35,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +28: [2023-04-29 11:37:35,606] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +28: [2023-04-29 11:37:35,606] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +28: [2023-04-29 11:37:35,606] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +29: [2023-04-29 11:37:35,607] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +40: [2023-04-29 11:37:35,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_34_mp_rank_03_optim_states.pt. +40: [2023-04-29 11:37:35,608] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 325 +29: [2023-04-29 11:37:35,608] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +12: [2023-04-29 11:37:35,609] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 0: [2023-04-29 11:37:35,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 0: [2023-04-29 11:37:35,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 0: [2023-04-29 11:37:35,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 0: [2023-04-29 11:37:35,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 7: [2023-04-29 11:37:35,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +23: [2023-04-29 11:37:35,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +29: [2023-04-29 11:37:35,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +19: [2023-04-29 11:37:35,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +36: [2023-04-29 11:37:35,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_17_mp_rank_03_optim_states.pt. +28: [2023-04-29 11:37:35,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +24: [2023-04-29 11:37:35,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +24: [2023-04-29 11:37:35,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +36: [2023-04-29 11:37:35,612] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 291 +12: [2023-04-29 11:37:35,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +24: [2023-04-29 11:37:35,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +24: [2023-04-29 11:37:35,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +24: [2023-04-29 11:37:35,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +24: [2023-04-29 11:37:35,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +28: [2023-04-29 11:37:35,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +28: [2023-04-29 11:37:35,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 7: [2023-04-29 11:37:35,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +24: [2023-04-29 11:37:35,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 7: [2023-04-29 11:37:35,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +24: [2023-04-29 11:37:35,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +28: [2023-04-29 11:37:35,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 0: [2023-04-29 11:37:35,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +12: [2023-04-29 11:37:35,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +24: [2023-04-29 11:37:35,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +19: [2023-04-29 11:37:35,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 0: [2023-04-29 11:37:35,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +53: [2023-04-29 11:37:35,617] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 430 +26: [2023-04-29 11:37:35,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +26: [2023-04-29 11:37:35,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 0: [2023-04-29 11:37:35,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +24: [2023-04-29 11:37:35,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +12: [2023-04-29 11:37:35,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +19: [2023-04-29 11:37:35,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +24: [2023-04-29 11:37:35,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 0: [2023-04-29 11:37:35,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +28: [2023-04-29 11:37:35,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +11: [2023-04-29 11:37:35,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +11: [2023-04-29 11:37:35,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +11: [2023-04-29 11:37:35,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +11: [2023-04-29 11:37:35,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +12: [2023-04-29 11:37:35,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +24: [2023-04-29 11:37:35,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +36: [2023-04-29 11:37:35,621] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 294 +36: [2023-04-29 11:37:35,621] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 292 +19: [2023-04-29 11:37:35,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +11: [2023-04-29 11:37:35,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +12: [2023-04-29 11:37:35,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +13: [2023-04-29 11:37:35,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +13: [2023-04-29 11:37:35,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +10: [2023-04-29 11:37:35,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 4: [2023-04-29 11:37:35,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 4: [2023-04-29 11:37:35,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 4: [2023-04-29 11:37:35,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 4: [2023-04-29 11:37:35,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 7: [2023-04-29 11:37:35,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +12: [2023-04-29 11:37:35,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +11: [2023-04-29 11:37:35,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +11: [2023-04-29 11:37:35,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +11: [2023-04-29 11:37:35,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +26: [2023-04-29 11:37:35,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +10: [2023-04-29 11:37:35,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +13: [2023-04-29 11:37:35,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +13: [2023-04-29 11:37:35,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +26: [2023-04-29 11:37:35,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 7: [2023-04-29 11:37:35,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +20: [2023-04-29 11:37:35,634] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +20: [2023-04-29 11:37:35,634] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +20: [2023-04-29 11:37:35,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +20: [2023-04-29 11:37:35,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +18: [2023-04-29 11:37:35,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 3: [2023-04-29 11:37:35,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 3: [2023-04-29 11:37:35,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 6: [2023-04-29 11:37:35,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 4: [2023-04-29 11:37:35,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 3: [2023-04-29 11:37:35,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 7: [2023-04-29 11:37:35,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 3: [2023-04-29 11:37:35,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 3: [2023-04-29 11:37:35,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +22: [2023-04-29 11:37:35,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +22: [2023-04-29 11:37:35,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +22: [2023-04-29 11:37:35,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +22: [2023-04-29 11:37:35,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 3: [2023-04-29 11:37:35,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 7: [2023-04-29 11:37:35,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +16: [2023-04-29 11:37:35,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +16: [2023-04-29 11:37:35,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 3: [2023-04-29 11:37:35,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 3: [2023-04-29 11:37:35,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +16: [2023-04-29 11:37:35,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +10: [2023-04-29 11:37:35,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 6: [2023-04-29 11:37:35,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 9: [2023-04-29 11:37:35,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +16: [2023-04-29 11:37:35,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 9: [2023-04-29 11:37:35,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 9: [2023-04-29 11:37:35,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 9: [2023-04-29 11:37:35,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +18: [2023-04-29 11:37:35,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +10: [2023-04-29 11:37:35,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +24: [2023-04-29 11:37:35,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +24: [2023-04-29 11:37:35,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +10: [2023-04-29 11:37:35,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +22: [2023-04-29 11:37:35,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +53: [2023-04-29 11:37:35,644] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 428 +21: [2023-04-29 11:37:35,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +21: [2023-04-29 11:37:35,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +21: [2023-04-29 11:37:35,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +21: [2023-04-29 11:37:35,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... + 4: [2023-04-29 11:37:35,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +22: [2023-04-29 11:37:35,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +60: [2023-04-29 11:37:35,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_113_mp_rank_03_optim_states.pt. + 6: [2023-04-29 11:37:35,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 6: [2023-04-29 11:37:35,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +53: [2023-04-29 11:37:35,646] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 426 +60: [2023-04-29 11:37:35,646] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 483 +53: [2023-04-29 11:37:35,646] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 424 + 3: [2023-04-29 11:37:35,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 3: [2023-04-29 11:37:35,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 4: [2023-04-29 11:37:35,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 3: [2023-04-29 11:37:35,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +52: [2023-04-29 11:37:35,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_81_mp_rank_02_optim_states.pt. +52: [2023-04-29 11:37:35,648] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 418 +18: [2023-04-29 11:37:35,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +13: [2023-04-29 11:37:35,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 3: [2023-04-29 11:37:35,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +13: [2023-04-29 11:37:35,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +16: [2023-04-29 11:37:35,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +16: [2023-04-29 11:37:35,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +10: [2023-04-29 11:37:35,650] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 7: [2023-04-29 11:37:35,650] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 7: [2023-04-29 11:37:35,650] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +10: [2023-04-29 11:37:35,650] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +16: [2023-04-29 11:37:35,650] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +24: [2023-04-29 11:37:35,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +24: [2023-04-29 11:37:35,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +16: [2023-04-29 11:37:35,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +18: [2023-04-29 11:37:35,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +18: [2023-04-29 11:37:35,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +10: [2023-04-29 11:37:35,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +16: [2023-04-29 11:37:35,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +22: [2023-04-29 11:37:35,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 4: [2023-04-29 11:37:35,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 7: [2023-04-29 11:37:35,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 7: [2023-04-29 11:37:35,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +16: [2023-04-29 11:37:35,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +52: [2023-04-29 11:37:35,654] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 418 +18: [2023-04-29 11:37:35,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +22: [2023-04-29 11:37:35,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +16: [2023-04-29 11:37:35,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +18: [2023-04-29 11:37:35,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +16: [2023-04-29 11:37:35,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +15: [2023-04-29 11:37:35,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +15: [2023-04-29 11:37:35,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +15: [2023-04-29 11:37:35,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +13: [2023-04-29 11:37:35,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 4: [2023-04-29 11:37:35,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 7: [2023-04-29 11:37:35,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +15: [2023-04-29 11:37:35,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 7: [2023-04-29 11:37:35,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +13: [2023-04-29 11:37:35,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +22: [2023-04-29 11:37:35,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +18: [2023-04-29 11:37:35,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 7: [2023-04-29 11:37:35,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +46: [2023-04-29 11:37:35,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_58_mp_rank_03_optim_states.pt. +46: [2023-04-29 11:37:35,664] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 373 +22: [2023-04-29 11:37:35,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +20: [2023-04-29 11:37:35,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +29: [2023-04-29 11:37:35,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +14: [2023-04-29 11:37:35,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 4: [2023-04-29 11:37:35,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +14: [2023-04-29 11:37:35,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +14: [2023-04-29 11:37:35,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +14: [2023-04-29 11:37:35,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 8: [2023-04-29 11:37:35,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 6: [2023-04-29 11:37:35,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +20: [2023-04-29 11:37:35,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 6: [2023-04-29 11:37:35,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +20: [2023-04-29 11:37:35,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 3: [2023-04-29 11:37:35,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 3: [2023-04-29 11:37:35,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 7: [2023-04-29 11:37:35,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +29: [2023-04-29 11:37:35,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 4: [2023-04-29 11:37:35,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +20: [2023-04-29 11:37:35,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 8: [2023-04-29 11:37:35,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 3: [2023-04-29 11:37:35,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 3: [2023-04-29 11:37:35,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 9: [2023-04-29 11:37:35,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 9: [2023-04-29 11:37:35,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 8: [2023-04-29 11:37:35,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 9: [2023-04-29 11:37:35,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 6: [2023-04-29 11:37:35,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 8: [2023-04-29 11:37:35,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 8: [2023-04-29 11:37:35,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 8: [2023-04-29 11:37:35,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +11: [2023-04-29 11:37:35,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 6: [2023-04-29 11:37:35,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 8: [2023-04-29 11:37:35,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +16: [2023-04-29 11:37:35,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +29: [2023-04-29 11:37:35,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +22: [2023-04-29 11:37:35,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +16: [2023-04-29 11:37:35,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 4: [2023-04-29 11:37:35,677] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 9: [2023-04-29 11:37:35,678] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 0: [2023-04-29 11:37:35,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +60: [2023-04-29 11:37:35,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_115_mp_rank_03_optim_states.pt. +60: [2023-04-29 11:37:35,679] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 487 +29: [2023-04-29 11:37:35,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +29: [2023-04-29 11:37:35,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +29: [2023-04-29 11:37:35,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +24: [2023-04-29 11:37:35,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +57: [2023-04-29 11:37:35,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_102_mp_rank_03_optim_states.pt. +24: [2023-04-29 11:37:35,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +31: [2023-04-29 11:37:35,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +31: [2023-04-29 11:37:35,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +57: [2023-04-29 11:37:35,686] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 461 +15: [2023-04-29 11:37:35,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +15: [2023-04-29 11:37:35,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +31: [2023-04-29 11:37:35,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 8: [2023-04-29 11:37:35,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +23: [2023-04-29 11:37:35,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +23: [2023-04-29 11:37:35,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +23: [2023-04-29 11:37:35,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +31: [2023-04-29 11:37:35,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +23: [2023-04-29 11:37:35,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +15: [2023-04-29 11:37:35,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 0: [2023-04-29 11:37:35,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 0: [2023-04-29 11:37:35,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +22: [2023-04-29 11:37:35,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +29: [2023-04-29 11:37:35,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 0: [2023-04-29 11:37:35,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +29: [2023-04-29 11:37:35,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +24: [2023-04-29 11:37:35,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +11: [2023-04-29 11:37:35,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 5: [2023-04-29 11:37:35,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 5: [2023-04-29 11:37:35,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. + 5: [2023-04-29 11:37:35,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_19-model_01-model_states.pt. +14: [2023-04-29 11:37:35,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +15: [2023-04-29 11:37:35,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +23: [2023-04-29 11:37:35,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +54: [2023-04-29 11:37:35,693] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 438 +23: [2023-04-29 11:37:35,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +23: [2023-04-29 11:37:35,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +23: [2023-04-29 11:37:35,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +16: [2023-04-29 11:37:35,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +11: [2023-04-29 11:37:35,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +54: [2023-04-29 11:37:35,694] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 434 +14: [2023-04-29 11:37:35,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +14: [2023-04-29 11:37:35,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +17: [2023-04-29 11:37:35,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +17: [2023-04-29 11:37:35,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +17: [2023-04-29 11:37:35,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +17: [2023-04-29 11:37:35,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +14: [2023-04-29 11:37:35,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +54: [2023-04-29 11:37:35,697] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 436 +11: [2023-04-29 11:37:35,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +16: [2023-04-29 11:37:35,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +54: [2023-04-29 11:37:35,700] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 432 +17: [2023-04-29 11:37:35,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +17: [2023-04-29 11:37:35,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +17: [2023-04-29 11:37:35,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +17: [2023-04-29 11:37:35,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +24: [2023-04-29 11:37:35,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 8: [2023-04-29 11:37:35,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +17: [2023-04-29 11:37:35,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +17: [2023-04-29 11:37:35,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +17: [2023-04-29 11:37:35,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +17: [2023-04-29 11:37:35,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 3: [2023-04-29 11:37:35,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 8: [2023-04-29 11:37:35,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 8: [2023-04-29 11:37:35,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +24: [2023-04-29 11:37:35,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +43: [2023-04-29 11:37:35,718] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 348 +60: [2023-04-29 11:37:35,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_112_mp_rank_03_optim_states.pt. +60: [2023-04-29 11:37:35,718] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 481 +31: [2023-04-29 11:37:35,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +31: [2023-04-29 11:37:35,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +40: [2023-04-29 11:37:35,719] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 320 +31: [2023-04-29 11:37:35,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 8: [2023-04-29 11:37:35,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 3: [2023-04-29 11:37:35,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +31: [2023-04-29 11:37:35,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +56: [2023-04-29 11:37:35,722] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 448 + 5: [2023-04-29 11:37:35,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 5: [2023-04-29 11:37:35,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 5: [2023-04-29 11:37:35,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... + 5: [2023-04-29 11:37:35,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt... +24: [2023-04-29 11:37:35,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +18: [2023-04-29 11:37:35,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +18: [2023-04-29 11:37:35,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +18: [2023-04-29 11:37:35,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +18: [2023-04-29 11:37:35,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +32: [2023-04-29 11:37:35,724] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 258 + 3: [2023-04-29 11:37:35,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +40: [2023-04-29 11:37:35,725] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 326 +17: [2023-04-29 11:37:35,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 3: [2023-04-29 11:37:35,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +18: [2023-04-29 11:37:35,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +22: [2023-04-29 11:37:35,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +22: [2023-04-29 11:37:35,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +22: [2023-04-29 11:37:35,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +22: [2023-04-29 11:37:35,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +20: [2023-04-29 11:37:35,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 0: > overriding learning rate value to 0.0002 + 0: > overriding minimum learning rate value to 2e-05 + 0: > overriding warmup iterations value to 0 + 0: > overriding total number of iterations value to 1 + 0: > overriding decay style value to cosine +40: [2023-04-29 11:37:35,731] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 324 +17: [2023-04-29 11:37:35,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +17: [2023-04-29 11:37:35,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +18: [2023-04-29 11:37:35,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +56: [2023-04-29 11:37:35,733] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 452 +18: [2023-04-29 11:37:35,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +18: [2023-04-29 11:37:35,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +20: [2023-04-29 11:37:35,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 9: [2023-04-29 11:37:35,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +17: [2023-04-29 11:37:35,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +32: [2023-04-29 11:37:35,737] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 260 + 1: [2023-04-29 11:37:35,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 1: [2023-04-29 11:37:35,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 1: [2023-04-29 11:37:35,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 1: [2023-04-29 11:37:35,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +56: [2023-04-29 11:37:35,739] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 450 +60: [2023-04-29 11:37:35,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_115_mp_rank_02_optim_states.pt. +60: [2023-04-29 11:37:35,739] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 486 +32: [2023-04-29 11:37:35,740] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 262 + 3: [2023-04-29 11:37:35,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 1: [2023-04-29 11:37:35,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 1: [2023-04-29 11:37:35,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +20: [2023-04-29 11:37:35,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +32: [2023-04-29 11:37:35,742] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 256 +24: [2023-04-29 11:37:35,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +43: [2023-04-29 11:37:35,743] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 346 +16: [2023-04-29 11:37:35,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +16: [2023-04-29 11:37:35,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 1: [2023-04-29 11:37:35,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +20: [2023-04-29 11:37:35,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 9: [2023-04-29 11:37:35,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +24: [2023-04-29 11:37:35,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +43: [2023-04-29 11:37:35,744] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 350 +24: [2023-04-29 11:37:35,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 9: [2023-04-29 11:37:35,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +40: [2023-04-29 11:37:35,746] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 322 +20: [2023-04-29 11:37:35,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 1: [2023-04-29 11:37:35,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 3: [2023-04-29 11:37:35,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 3: [2023-04-29 11:37:35,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +20: [2023-04-29 11:37:35,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +16: [2023-04-29 11:37:35,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +16: [2023-04-29 11:37:35,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 9: [2023-04-29 11:37:35,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +11: [2023-04-29 11:37:35,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +11: [2023-04-29 11:37:35,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +11: [2023-04-29 11:37:35,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +11: [2023-04-29 11:37:35,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +20: [2023-04-29 11:37:35,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +24: [2023-04-29 11:37:35,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 3: [2023-04-29 11:37:35,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 3: [2023-04-29 11:37:35,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +56: [2023-04-29 11:37:35,751] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 454 +24: [2023-04-29 11:37:35,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 9: [2023-04-29 11:37:35,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +24: [2023-04-29 11:37:35,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +15: [2023-04-29 11:37:35,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +15: [2023-04-29 11:37:35,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +16: [2023-04-29 11:37:35,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +16: [2023-04-29 11:37:35,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +16: [2023-04-29 11:37:35,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +32: [2023-04-29 11:37:35,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_2_mp_rank_03_optim_states.pt. +32: [2023-04-29 11:37:35,753] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 261 + 3: [2023-04-29 11:37:35,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +20: [2023-04-29 11:37:35,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +16: [2023-04-29 11:37:35,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 9: [2023-04-29 11:37:35,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +14: [2023-04-29 11:37:35,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +24: [2023-04-29 11:37:35,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +24: [2023-04-29 11:37:35,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +24: [2023-04-29 11:37:35,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +24: [2023-04-29 11:37:35,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +63: [2023-04-29 11:37:35,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_124_mp_rank_03_optim_states.pt. + 0: [2023-04-29 11:37:35,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 0: [2023-04-29 11:37:35,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 0: [2023-04-29 11:37:35,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 0: [2023-04-29 11:37:35,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +63: [2023-04-29 11:37:35,756] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 505 +15: [2023-04-29 11:37:35,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 9: [2023-04-29 11:37:35,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +15: [2023-04-29 11:37:35,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +15: [2023-04-29 11:37:35,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +23: [2023-04-29 11:37:35,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 9: [2023-04-29 11:37:35,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 3: [2023-04-29 11:37:35,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 3: [2023-04-29 11:37:35,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +14: [2023-04-29 11:37:35,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +15: [2023-04-29 11:37:35,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 8: [2023-04-29 11:37:35,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 8: [2023-04-29 11:37:35,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 8: [2023-04-29 11:37:35,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 8: [2023-04-29 11:37:35,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +23: [2023-04-29 11:37:35,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +23: [2023-04-29 11:37:35,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +23: [2023-04-29 11:37:35,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +15: [2023-04-29 11:37:35,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +35: [2023-04-29 11:37:35,767] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 284 +41: [2023-04-29 11:37:35,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_39_mp_rank_03_optim_states.pt. +14: [2023-04-29 11:37:35,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +14: [2023-04-29 11:37:35,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +14: [2023-04-29 11:37:35,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +41: [2023-04-29 11:37:35,769] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 335 +15: [2023-04-29 11:37:35,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +50: [2023-04-29 11:37:35,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_72_mp_rank_03_optim_states.pt. +50: [2023-04-29 11:37:35,772] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 401 +35: [2023-04-29 11:37:35,772] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 282 +10: [2023-04-29 11:37:35,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +10: [2023-04-29 11:37:35,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +10: [2023-04-29 11:37:35,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +14: [2023-04-29 11:37:35,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +35: [2023-04-29 11:37:35,774] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 280 +10: [2023-04-29 11:37:35,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +14: [2023-04-29 11:37:35,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +14: [2023-04-29 11:37:35,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +35: [2023-04-29 11:37:35,776] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 286 + 8: [2023-04-29 11:37:35,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +43: [2023-04-29 11:37:35,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_44_mp_rank_02_optim_states.pt. +43: [2023-04-29 11:37:35,778] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 344 +12: [2023-04-29 11:37:35,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +12: [2023-04-29 11:37:35,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +12: [2023-04-29 11:37:35,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +12: [2023-04-29 11:37:35,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +31: [2023-04-29 11:37:35,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +31: [2023-04-29 11:37:35,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +31: [2023-04-29 11:37:35,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +31: [2023-04-29 11:37:35,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +10: [2023-04-29 11:37:35,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +10: [2023-04-29 11:37:35,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +10: [2023-04-29 11:37:35,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +10: [2023-04-29 11:37:35,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 8: [2023-04-29 11:37:35,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +16: [2023-04-29 11:37:35,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +12: [2023-04-29 11:37:35,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +12: [2023-04-29 11:37:35,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +12: [2023-04-29 11:37:35,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +17: [2023-04-29 11:37:35,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +43: [2023-04-29 11:37:35,786] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 344 +12: [2023-04-29 11:37:35,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +17: [2023-04-29 11:37:35,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +31: [2023-04-29 11:37:35,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +31: [2023-04-29 11:37:35,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +31: [2023-04-29 11:37:35,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +31: [2023-04-29 11:37:35,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +17: [2023-04-29 11:37:35,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +31: [2023-04-29 11:37:35,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +18: [2023-04-29 11:37:35,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +17: [2023-04-29 11:37:35,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +17: [2023-04-29 11:37:35,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +17: [2023-04-29 11:37:35,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +16: [2023-04-29 11:37:35,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +16: [2023-04-29 11:37:35,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +16: [2023-04-29 11:37:35,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 5: [2023-04-29 11:37:35,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +17: [2023-04-29 11:37:35,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +16: [2023-04-29 11:37:35,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 5: [2023-04-29 11:37:35,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +17: [2023-04-29 11:37:35,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +31: [2023-04-29 11:37:35,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +31: [2023-04-29 11:37:35,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +16: [2023-04-29 11:37:35,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 8: [2023-04-29 11:37:35,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 3: [2023-04-29 11:37:35,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 3: [2023-04-29 11:37:35,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 3: [2023-04-29 11:37:35,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 3: [2023-04-29 11:37:35,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +34: [2023-04-29 11:37:35,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_9_mp_rank_03_optim_states.pt. +34: [2023-04-29 11:37:35,799] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 275 + 5: [2023-04-29 11:37:35,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 5: [2023-04-29 11:37:35,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +31: [2023-04-29 11:37:35,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... +31: [2023-04-29 11:37:35,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +16: [2023-04-29 11:37:35,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_00-model_states.pt. +55: [2023-04-29 11:37:35,802] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 442 + 8: [2023-04-29 11:37:35,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 8: [2023-04-29 11:37:35,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +31: [2023-04-29 11:37:35,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +36: [2023-04-29 11:37:35,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_16_mp_rank_02_optim_states.pt. +36: [2023-04-29 11:37:35,805] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 288 +31: [2023-04-29 11:37:35,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +18: [2023-04-29 11:37:35,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +18: [2023-04-29 11:37:35,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 1: [2023-04-29 11:37:35,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +18: [2023-04-29 11:37:35,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +16: [2023-04-29 11:37:35,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt... + 8: [2023-04-29 11:37:35,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +55: [2023-04-29 11:37:35,809] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 444 + 2: [2023-04-29 11:37:35,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 1: [2023-04-29 11:37:35,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +31: [2023-04-29 11:37:35,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +55: [2023-04-29 11:37:35,811] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 440 +55: [2023-04-29 11:37:35,813] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 446 +36: [2023-04-29 11:37:35,813] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 288 + 2: [2023-04-29 11:37:35,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 8: [2023-04-29 11:37:35,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 1: [2023-04-29 11:37:35,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +60: [2023-04-29 11:37:35,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_114_mp_rank_03_optim_states.pt. + 1: [2023-04-29 11:37:35,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +60: [2023-04-29 11:37:35,815] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 485 +17: [2023-04-29 11:37:35,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 8: [2023-04-29 11:37:35,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 0: [2023-04-29 11:37:35,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 0: [2023-04-29 11:37:35,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 0: [2023-04-29 11:37:35,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +59: [2023-04-29 11:37:35,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_108_mp_rank_03_optim_states.pt. +59: [2023-04-29 11:37:35,816] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 473 + 2: [2023-04-29 11:37:35,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 0: [2023-04-29 11:37:35,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 2: [2023-04-29 11:37:35,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 2: [2023-04-29 11:37:35,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +17: [2023-04-29 11:37:35,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 9: [2023-04-29 11:37:35,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 9: [2023-04-29 11:37:35,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 9: [2023-04-29 11:37:35,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 9: [2023-04-29 11:37:35,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +17: [2023-04-29 11:37:35,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 9: [2023-04-29 11:37:35,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +51: [2023-04-29 11:37:35,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_77_mp_rank_02_optim_states.pt. +51: [2023-04-29 11:37:35,828] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 410 + 9: [2023-04-29 11:37:35,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 9: [2023-04-29 11:37:35,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 9: [2023-04-29 11:37:35,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +17: [2023-04-29 11:37:35,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +50: [2023-04-29 11:37:35,832] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 404 +49: [2023-04-29 11:37:35,843] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 398 +49: [2023-04-29 11:37:35,844] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 394 + 0: [2023-04-29 11:37:35,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +15: [2023-04-29 11:37:35,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +15: [2023-04-29 11:37:35,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +15: [2023-04-29 11:37:35,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +15: [2023-04-29 11:37:35,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +14: [2023-04-29 11:37:35,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +14: [2023-04-29 11:37:35,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +14: [2023-04-29 11:37:35,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +14: [2023-04-29 11:37:35,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +12: [2023-04-29 11:37:35,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +10: [2023-04-29 11:37:35,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 0: [2023-04-29 11:37:35,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +49: [2023-04-29 11:37:35,848] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 392 +49: [2023-04-29 11:37:35,849] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 396 +23: [2023-04-29 11:37:35,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +23: [2023-04-29 11:37:35,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +23: [2023-04-29 11:37:35,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +23: [2023-04-29 11:37:35,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +10: [2023-04-29 11:37:35,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +10: [2023-04-29 11:37:35,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +10: [2023-04-29 11:37:35,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +35: [2023-04-29 11:37:35,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_14_mp_rank_03_optim_states.pt. +15: [2023-04-29 11:37:35,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +35: [2023-04-29 11:37:35,852] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 285 +15: [2023-04-29 11:37:35,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +15: [2023-04-29 11:37:35,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 0: [2023-04-29 11:37:35,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +15: [2023-04-29 11:37:35,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +14: [2023-04-29 11:37:35,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +14: [2023-04-29 11:37:35,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 0: [2023-04-29 11:37:35,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +33: [2023-04-29 11:37:35,854] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 270 +14: [2023-04-29 11:37:35,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +45: [2023-04-29 11:37:35,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_54_mp_rank_03_optim_states.pt. +45: [2023-04-29 11:37:35,855] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 365 +14: [2023-04-29 11:37:35,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +33: [2023-04-29 11:37:35,855] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 268 +31: [2023-04-29 11:37:35,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +48: [2023-04-29 11:37:35,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_66_mp_rank_03_optim_states.pt. +48: [2023-04-29 11:37:35,859] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 389 +31: [2023-04-29 11:37:35,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +31: [2023-04-29 11:37:35,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +31: [2023-04-29 11:37:35,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +18: [2023-04-29 11:37:35,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... +18: [2023-04-29 11:37:35,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... +18: [2023-04-29 11:37:35,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... +18: [2023-04-29 11:37:35,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... +33: [2023-04-29 11:37:35,863] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 266 +37: [2023-04-29 11:37:35,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_21_mp_rank_03_optim_states.pt. +37: [2023-04-29 11:37:35,865] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 299 +33: [2023-04-29 11:37:35,866] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 264 +12: [2023-04-29 11:37:35,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +12: [2023-04-29 11:37:35,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +50: [2023-04-29 11:37:35,859] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 406 +12: [2023-04-29 11:37:35,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +11: [2023-04-29 11:37:35,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +11: [2023-04-29 11:37:35,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +11: [2023-04-29 11:37:35,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +11: [2023-04-29 11:37:35,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 5: [2023-04-29 11:37:35,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +50: [2023-04-29 11:37:35,869] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 400 +50: [2023-04-29 11:37:35,869] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 402 +17: [2023-04-29 11:37:35,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... +17: [2023-04-29 11:37:35,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... +17: [2023-04-29 11:37:35,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... +52: [2023-04-29 11:37:35,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_83_mp_rank_03_optim_states.pt. +52: [2023-04-29 11:37:35,875] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 423 +25: [2023-04-29 11:37:35,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +25: [2023-04-29 11:37:35,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +25: [2023-04-29 11:37:35,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +25: [2023-04-29 11:37:35,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +17: [2023-04-29 11:37:35,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 9: [2023-04-29 11:37:35,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 5: [2023-04-29 11:37:35,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 5: [2023-04-29 11:37:35,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +13: [2023-04-29 11:37:35,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +13: [2023-04-29 11:37:35,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +13: [2023-04-29 11:37:35,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 5: [2023-04-29 11:37:35,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +25: [2023-04-29 11:37:35,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +13: [2023-04-29 11:37:35,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +25: [2023-04-29 11:37:35,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +25: [2023-04-29 11:37:35,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +28: [2023-04-29 11:37:35,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +28: [2023-04-29 11:37:35,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +28: [2023-04-29 11:37:35,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +28: [2023-04-29 11:37:35,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +58: [2023-04-29 11:37:35,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_104_mp_rank_03_optim_states.pt. +58: [2023-04-29 11:37:35,884] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 465 +25: [2023-04-29 11:37:35,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +28: [2023-04-29 11:37:35,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +28: [2023-04-29 11:37:35,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +28: [2023-04-29 11:37:35,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +28: [2023-04-29 11:37:35,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 2: [2023-04-29 11:37:35,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +44: [2023-04-29 11:37:35,895] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 354 +11: [2023-04-29 11:37:35,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +11: [2023-04-29 11:37:35,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +11: [2023-04-29 11:37:35,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 9: [2023-04-29 11:37:35,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 9: [2023-04-29 11:37:35,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +11: [2023-04-29 11:37:35,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +29: [2023-04-29 11:37:35,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +29: [2023-04-29 11:37:35,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +29: [2023-04-29 11:37:35,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 1: [2023-04-29 11:37:35,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 1: [2023-04-29 11:37:35,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 1: [2023-04-29 11:37:35,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 1: [2023-04-29 11:37:35,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +42: [2023-04-29 11:37:35,900] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 338 +42: [2023-04-29 11:37:35,901] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 342 +29: [2023-04-29 11:37:35,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +44: [2023-04-29 11:37:35,902] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 358 +42: [2023-04-29 11:37:35,903] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 340 +44: [2023-04-29 11:37:35,903] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 352 + 9: [2023-04-29 11:37:35,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +42: [2023-04-29 11:37:35,904] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 336 +13: [2023-04-29 11:37:35,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +44: [2023-04-29 11:37:35,905] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 356 +29: [2023-04-29 11:37:35,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +29: [2023-04-29 11:37:35,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +29: [2023-04-29 11:37:35,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +29: [2023-04-29 11:37:35,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +14: [2023-04-29 11:37:35,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 0: [2023-04-29 11:37:35,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +63: [2023-04-29 11:37:35,911] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 510 +25: [2023-04-29 11:37:35,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +25: [2023-04-29 11:37:35,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +13: [2023-04-29 11:37:35,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +19: [2023-04-29 11:37:35,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +19: [2023-04-29 11:37:35,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +63: [2023-04-29 11:37:35,914] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 506 +19: [2023-04-29 11:37:35,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +19: [2023-04-29 11:37:35,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +25: [2023-04-29 11:37:35,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +14: [2023-04-29 11:37:35,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +25: [2023-04-29 11:37:35,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +13: [2023-04-29 11:37:35,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +13: [2023-04-29 11:37:35,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +15: [2023-04-29 11:37:35,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +13: [2023-04-29 11:37:35,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +13: [2023-04-29 11:37:35,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +26: [2023-04-29 11:37:35,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +26: [2023-04-29 11:37:35,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +26: [2023-04-29 11:37:35,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +26: [2023-04-29 11:37:35,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +63: [2023-04-29 11:37:35,917] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 508 + 7: [2023-04-29 11:37:35,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 7: [2023-04-29 11:37:35,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 7: [2023-04-29 11:37:35,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 0: [2023-04-29 11:37:35,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 7: [2023-04-29 11:37:35,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +63: [2023-04-29 11:37:35,918] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 504 +19: [2023-04-29 11:37:35,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +19: [2023-04-29 11:37:35,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +19: [2023-04-29 11:37:35,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +19: [2023-04-29 11:37:35,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +34: [2023-04-29 11:37:35,921] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 276 +13: [2023-04-29 11:37:35,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +26: [2023-04-29 11:37:35,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +13: [2023-04-29 11:37:35,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +26: [2023-04-29 11:37:35,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +26: [2023-04-29 11:37:35,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +26: [2023-04-29 11:37:35,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +15: [2023-04-29 11:37:35,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +15: [2023-04-29 11:37:35,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +15: [2023-04-29 11:37:35,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 7: [2023-04-29 11:37:35,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 6: [2023-04-29 11:37:35,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 6: [2023-04-29 11:37:35,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +12: [2023-04-29 11:37:35,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +12: [2023-04-29 11:37:35,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +12: [2023-04-29 11:37:35,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +12: [2023-04-29 11:37:35,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 6: [2023-04-29 11:37:35,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 6: [2023-04-29 11:37:35,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 0: [2023-04-29 11:37:35,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 7: [2023-04-29 11:37:35,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +13: [2023-04-29 11:37:35,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +13: [2023-04-29 11:37:35,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 7: [2023-04-29 11:37:35,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 7: [2023-04-29 11:37:35,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 0: [2023-04-29 11:37:35,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +14: [2023-04-29 11:37:35,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +14: [2023-04-29 11:37:35,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +10: [2023-04-29 11:37:35,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +10: [2023-04-29 11:37:35,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +10: [2023-04-29 11:37:35,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +10: [2023-04-29 11:37:35,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 0: [2023-04-29 11:37:35,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 6: [2023-04-29 11:37:35,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 6: [2023-04-29 11:37:35,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 6: [2023-04-29 11:37:35,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 6: [2023-04-29 11:37:35,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +41: [2023-04-29 11:37:35,931] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 332 + 0: [2023-04-29 11:37:35,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +13: [2023-04-29 11:37:35,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +42: [2023-04-29 11:37:35,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_41_mp_rank_03_optim_states.pt. +42: [2023-04-29 11:37:35,935] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 339 +13: [2023-04-29 11:37:35,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 0: [2023-04-29 11:37:35,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 0: [2023-04-29 11:37:35,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +31: [2023-04-29 11:37:35,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +31: [2023-04-29 11:37:35,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +31: [2023-04-29 11:37:35,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +31: [2023-04-29 11:37:35,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +39: [2023-04-29 11:37:35,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_29_mp_rank_03_optim_states.pt. +39: [2023-04-29 11:37:35,938] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 315 +34: [2023-04-29 11:37:35,938] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 274 +25: [2023-04-29 11:37:35,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +25: [2023-04-29 11:37:35,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +39: [2023-04-29 11:37:35,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_28_mp_rank_03_optim_states.pt. +39: [2023-04-29 11:37:35,942] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 313 + 1: [2023-04-29 11:37:35,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 1: [2023-04-29 11:37:35,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +25: [2023-04-29 11:37:35,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 1: [2023-04-29 11:37:35,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +25: [2023-04-29 11:37:35,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 1: [2023-04-29 11:37:35,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +34: [2023-04-29 11:37:35,948] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 272 +34: [2023-04-29 11:37:35,949] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 278 +25: [2023-04-29 11:37:35,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +41: [2023-04-29 11:37:35,950] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 334 +41: [2023-04-29 11:37:35,950] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 328 +26: [2023-04-29 11:37:35,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +26: [2023-04-29 11:37:35,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +28: [2023-04-29 11:37:35,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 2: [2023-04-29 11:37:35,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +26: [2023-04-29 11:37:35,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +26: [2023-04-29 11:37:35,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 5: [2023-04-29 11:37:35,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 5: [2023-04-29 11:37:35,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +34: [2023-04-29 11:37:35,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_11_mp_rank_03_optim_states.pt. +34: [2023-04-29 11:37:35,954] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 279 +28: [2023-04-29 11:37:35,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +28: [2023-04-29 11:37:35,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +28: [2023-04-29 11:37:35,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 2: [2023-04-29 11:37:35,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +25: [2023-04-29 11:37:35,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +41: [2023-04-29 11:37:35,958] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 330 +46: [2023-04-29 11:37:35,959] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 374 +11: [2023-04-29 11:37:35,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +11: [2023-04-29 11:37:35,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +11: [2023-04-29 11:37:35,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +25: [2023-04-29 11:37:35,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +25: [2023-04-29 11:37:35,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +11: [2023-04-29 11:37:35,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +13: [2023-04-29 11:37:35,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +47: [2023-04-29 11:37:35,970] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 378 +40: [2023-04-29 11:37:35,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_32_mp_rank_03_optim_states.pt. +40: [2023-04-29 11:37:35,971] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 321 +47: [2023-04-29 11:37:35,971] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 380 +47: [2023-04-29 11:37:35,971] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 382 +11: [2023-04-29 11:37:35,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +13: [2023-04-29 11:37:35,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +11: [2023-04-29 11:37:35,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +11: [2023-04-29 11:37:35,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +11: [2023-04-29 11:37:35,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +47: [2023-04-29 11:37:35,974] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 376 +46: [2023-04-29 11:37:35,974] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 370 +29: [2023-04-29 11:37:35,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +29: [2023-04-29 11:37:35,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 1: [2023-04-29 11:37:35,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 1: [2023-04-29 11:37:35,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 1: [2023-04-29 11:37:35,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 2: [2023-04-29 11:37:35,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 2: [2023-04-29 11:37:35,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 2: [2023-04-29 11:37:35,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 2: [2023-04-29 11:37:35,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 2: [2023-04-29 11:37:35,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +29: [2023-04-29 11:37:35,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +29: [2023-04-29 11:37:35,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +26: [2023-04-29 11:37:35,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +46: [2023-04-29 11:37:35,979] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 368 + 1: [2023-04-29 11:37:35,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 2: [2023-04-29 11:37:35,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +46: [2023-04-29 11:37:35,982] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 372 +19: [2023-04-29 11:37:35,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +19: [2023-04-29 11:37:35,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +26: [2023-04-29 11:37:35,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +26: [2023-04-29 11:37:35,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +26: [2023-04-29 11:37:35,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +13: [2023-04-29 11:37:35,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 2: [2023-04-29 11:37:35,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 2: [2023-04-29 11:37:35,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +19: [2023-04-29 11:37:35,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +19: [2023-04-29 11:37:35,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +34: [2023-04-29 11:37:35,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_8_mp_rank_03_optim_states.pt. +34: [2023-04-29 11:37:35,989] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 273 + 7: [2023-04-29 11:37:35,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +13: [2023-04-29 11:37:35,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 9: [2023-04-29 11:37:35,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 9: [2023-04-29 11:37:35,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 9: [2023-04-29 11:37:35,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 9: [2023-04-29 11:37:35,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 6: [2023-04-29 11:37:35,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 6: [2023-04-29 11:37:35,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +36: [2023-04-29 11:37:35,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_19_mp_rank_03_optim_states.pt. +36: [2023-04-29 11:37:35,994] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 295 +26: [2023-04-29 11:37:35,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +26: [2023-04-29 11:37:35,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +37: [2023-04-29 11:37:35,997] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 296 + 7: [2023-04-29 11:37:35,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 7: [2023-04-29 11:37:35,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 6: [2023-04-29 11:37:35,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +60: [2023-04-29 11:37:35,998] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 480 + 6: [2023-04-29 11:37:35,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +57: [2023-04-29 11:37:35,999] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 462 +13: [2023-04-29 11:37:35,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +13: [2023-04-29 11:37:35,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 7: [2023-04-29 11:37:35,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +60: [2023-04-29 11:37:36,001] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 482 +37: [2023-04-29 11:37:36,003] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 298 +13: [2023-04-29 11:37:36,003] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +14: [2023-04-29 11:37:36,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +14: [2023-04-29 11:37:36,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +14: [2023-04-29 11:37:36,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +14: [2023-04-29 11:37:36,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +60: [2023-04-29 11:37:36,005] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 486 +57: [2023-04-29 11:37:36,006] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 458 +37: [2023-04-29 11:37:36,006] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 302 +13: [2023-04-29 11:37:36,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +37: [2023-04-29 11:37:36,007] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 300 +13: [2023-04-29 11:37:36,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +60: [2023-04-29 11:37:36,008] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 484 +30: [2023-04-29 11:37:36,010] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +30: [2023-04-29 11:37:36,010] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 242 +13: [2023-04-29 11:37:36,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +26: [2023-04-29 11:37:36,011] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +30: [2023-04-29 11:37:36,012] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +30: [2023-04-29 11:37:36,012] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 240 +30: [2023-04-29 11:37:36,017] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 242 +26: [2023-04-29 11:37:36,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +39: [2023-04-29 11:37:36,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_31_mp_rank_03_optim_states.pt. +39: [2023-04-29 11:37:36,018] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 319 +30: [2023-04-29 11:37:36,019] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 240 +57: [2023-04-29 11:37:36,019] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 460 +61: [2023-04-29 11:37:36,020] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 492 +57: [2023-04-29 11:37:36,021] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 456 +30: [2023-04-29 11:37:36,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +30: [2023-04-29 11:37:36,022] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 246 +61: [2023-04-29 11:37:36,022] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 490 +61: [2023-04-29 11:37:36,022] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 494 +61: [2023-04-29 11:37:36,022] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 488 +43: [2023-04-29 11:37:36,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_45_mp_rank_03_optim_states.pt. +25: [2023-04-29 11:37:36,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +43: [2023-04-29 11:37:36,023] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 347 +13: [2023-04-29 11:37:36,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 4: [2023-04-29 11:37:36,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 4: [2023-04-29 11:37:36,024] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 32 +13: [2023-04-29 11:37:36,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +19: [2023-04-29 11:37:36,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +19: [2023-04-29 11:37:36,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +25: [2023-04-29 11:37:36,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +45: [2023-04-29 11:37:36,029] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 362 +30: [2023-04-29 11:37:36,029] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 246 +19: [2023-04-29 11:37:36,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +51: [2023-04-29 11:37:36,029] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 412 +19: [2023-04-29 11:37:36,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +25: [2023-04-29 11:37:36,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +15: [2023-04-29 11:37:36,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +15: [2023-04-29 11:37:36,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +15: [2023-04-29 11:37:36,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +15: [2023-04-29 11:37:36,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +25: [2023-04-29 11:37:36,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +51: [2023-04-29 11:37:36,031] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 410 +45: [2023-04-29 11:37:36,032] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 364 + 4: [2023-04-29 11:37:36,033] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 32 +51: [2023-04-29 11:37:36,033] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 414 +27: [2023-04-29 11:37:36,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +27: [2023-04-29 11:37:36,033] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 220 +21: [2023-04-29 11:37:36,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +21: [2023-04-29 11:37:36,035] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 170 +25: [2023-04-29 11:37:36,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +20: [2023-04-29 11:37:36,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +51: [2023-04-29 11:37:36,036] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 408 +39: [2023-04-29 11:37:36,036] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 318 +20: [2023-04-29 11:37:36,036] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 164 +30: [2023-04-29 11:37:36,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +25: [2023-04-29 11:37:36,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +30: [2023-04-29 11:37:36,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +25: [2023-04-29 11:37:36,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +38: [2023-04-29 11:37:36,039] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 304 + 2: [2023-04-29 11:37:36,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +58: [2023-04-29 11:37:36,039] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 468 +38: [2023-04-29 11:37:36,040] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 310 +30: [2023-04-29 11:37:36,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +27: [2023-04-29 11:37:36,041] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 220 +30: [2023-04-29 11:37:36,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +20: [2023-04-29 11:37:36,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +20: [2023-04-29 11:37:36,041] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 162 +23: [2023-04-29 11:37:36,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +23: [2023-04-29 11:37:36,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +23: [2023-04-29 11:37:36,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +21: [2023-04-29 11:37:36,042] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 170 +25: [2023-04-29 11:37:36,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 1: [2023-04-29 11:37:36,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 1: [2023-04-29 11:37:36,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +16: [2023-04-29 11:37:36,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +16: [2023-04-29 11:37:36,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +16: [2023-04-29 11:37:36,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +16: [2023-04-29 11:37:36,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +23: [2023-04-29 11:37:36,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +20: [2023-04-29 11:37:36,043] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 164 +25: [2023-04-29 11:37:36,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +25: [2023-04-29 11:37:36,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +25: [2023-04-29 11:37:36,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +28: [2023-04-29 11:37:36,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +25: [2023-04-29 11:37:36,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +28: [2023-04-29 11:37:36,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +28: [2023-04-29 11:37:36,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +28: [2023-04-29 11:37:36,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +39: [2023-04-29 11:37:36,045] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 316 +38: [2023-04-29 11:37:36,046] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 306 +20: [2023-04-29 11:37:36,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +38: [2023-04-29 11:37:36,047] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 308 +20: [2023-04-29 11:37:36,047] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 160 +21: [2023-04-29 11:37:36,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +21: [2023-04-29 11:37:36,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +21: [2023-04-29 11:37:36,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +21: [2023-04-29 11:37:36,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +20: [2023-04-29 11:37:36,048] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 162 +30: [2023-04-29 11:37:36,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +30: [2023-04-29 11:37:36,048] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 244 + 2: [2023-04-29 11:37:36,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +58: [2023-04-29 11:37:36,049] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 466 +39: [2023-04-29 11:37:36,049] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 312 + 1: [2023-04-29 11:37:36,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 1: [2023-04-29 11:37:36,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 1: [2023-04-29 11:37:36,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 1: [2023-04-29 11:37:36,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 2: [2023-04-29 11:37:36,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +39: [2023-04-29 11:37:36,052] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 314 + 5: [2023-04-29 11:37:36,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 5: [2023-04-29 11:37:36,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 5: [2023-04-29 11:37:36,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 5: [2023-04-29 11:37:36,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +16: [2023-04-29 11:37:36,052] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +16: [2023-04-29 11:37:36,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +16: [2023-04-29 11:37:36,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +16: [2023-04-29 11:37:36,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +21: [2023-04-29 11:37:36,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +21: [2023-04-29 11:37:36,053] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 172 +20: [2023-04-29 11:37:36,053] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 160 + 4: [2023-04-29 11:37:36,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 4: [2023-04-29 11:37:36,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 4: [2023-04-29 11:37:36,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 4: [2023-04-29 11:37:36,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 1: [2023-04-29 11:37:36,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 1: [2023-04-29 11:37:36,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 2: [2023-04-29 11:37:36,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +19: [2023-04-29 11:37:36,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +30: [2023-04-29 11:37:36,057] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 244 +29: [2023-04-29 11:37:36,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +29: [2023-04-29 11:37:36,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +29: [2023-04-29 11:37:36,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +29: [2023-04-29 11:37:36,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... + 2: [2023-04-29 11:37:36,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 2: [2023-04-29 11:37:36,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +26: [2023-04-29 11:37:36,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +19: [2023-04-29 11:37:36,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +58: [2023-04-29 11:37:36,064] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 464 + 7: [2023-04-29 11:37:36,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 7: [2023-04-29 11:37:36,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 7: [2023-04-29 11:37:36,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +19: [2023-04-29 11:37:36,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 7: [2023-04-29 11:37:36,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 6: [2023-04-29 11:37:36,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 6: [2023-04-29 11:37:36,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 6: [2023-04-29 11:37:36,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 6: [2023-04-29 11:37:36,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 2: [2023-04-29 11:37:36,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +58: [2023-04-29 11:37:36,066] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 470 +26: [2023-04-29 11:37:36,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +14: [2023-04-29 11:37:36,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +14: [2023-04-29 11:37:36,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 2: [2023-04-29 11:37:36,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +26: [2023-04-29 11:37:36,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +56: [2023-04-29 11:37:36,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_98_mp_rank_03_optim_states.pt. +20: [2023-04-29 11:37:36,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +20: [2023-04-29 11:37:36,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +56: [2023-04-29 11:37:36,067] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 453 +19: [2023-04-29 11:37:36,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +14: [2023-04-29 11:37:36,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +45: [2023-04-29 11:37:36,068] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 360 +14: [2023-04-29 11:37:36,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +20: [2023-04-29 11:37:36,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +27: [2023-04-29 11:37:36,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +27: [2023-04-29 11:37:36,070] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 222 +30: [2023-04-29 11:37:36,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +20: [2023-04-29 11:37:36,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +23: [2023-04-29 11:37:36,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +23: [2023-04-29 11:37:36,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +30: [2023-04-29 11:37:36,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +26: [2023-04-29 11:37:36,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 4: [2023-04-29 11:37:36,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +30: [2023-04-29 11:37:36,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 4: [2023-04-29 11:37:36,074] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 38 +19: [2023-04-29 11:37:36,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... +19: [2023-04-29 11:37:36,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... +19: [2023-04-29 11:37:36,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... +19: [2023-04-29 11:37:36,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... +26: [2023-04-29 11:37:36,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +30: [2023-04-29 11:37:36,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +45: [2023-04-29 11:37:36,076] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 366 +26: [2023-04-29 11:37:36,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +26: [2023-04-29 11:37:36,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +26: [2023-04-29 11:37:36,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +26: [2023-04-29 11:37:36,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +27: [2023-04-29 11:37:36,078] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 222 +21: [2023-04-29 11:37:36,064] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 172 +21: [2023-04-29 11:37:36,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +21: [2023-04-29 11:37:36,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +21: [2023-04-29 11:37:36,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +21: [2023-04-29 11:37:36,078] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 168 +20: [2023-04-29 11:37:36,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +20: [2023-04-29 11:37:36,079] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 166 + 4: [2023-04-29 11:37:36,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +26: [2023-04-29 11:37:36,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +23: [2023-04-29 11:37:36,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +23: [2023-04-29 11:37:36,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +13: [2023-04-29 11:37:36,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +13: [2023-04-29 11:37:36,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +13: [2023-04-29 11:37:36,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +13: [2023-04-29 11:37:36,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +39: [2023-04-29 11:37:36,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_30_mp_rank_03_optim_states.pt. +39: [2023-04-29 11:37:36,082] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 317 + 4: [2023-04-29 11:37:36,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 4: [2023-04-29 11:37:36,086] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 38 +26: [2023-04-29 11:37:36,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +27: [2023-04-29 11:37:36,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +27: [2023-04-29 11:37:36,088] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 218 +21: [2023-04-29 11:37:36,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +21: [2023-04-29 11:37:36,087] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 168 +21: [2023-04-29 11:37:36,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +20: [2023-04-29 11:37:36,089] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 166 + 7: [2023-04-29 11:37:36,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 7: [2023-04-29 11:37:36,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 4: [2023-04-29 11:37:36,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 4: [2023-04-29 11:37:36,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 7: [2023-04-29 11:37:36,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 7: [2023-04-29 11:37:36,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +26: [2023-04-29 11:37:36,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +14: [2023-04-29 11:37:36,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +22: [2023-04-29 11:37:36,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +22: [2023-04-29 11:37:36,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +22: [2023-04-29 11:37:36,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +22: [2023-04-29 11:37:36,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 6: [2023-04-29 11:37:36,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 6: [2023-04-29 11:37:36,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 6: [2023-04-29 11:37:36,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 6: [2023-04-29 11:37:36,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +12: [2023-04-29 11:37:36,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +27: [2023-04-29 11:37:36,095] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 218 +12: [2023-04-29 11:37:36,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +12: [2023-04-29 11:37:36,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +12: [2023-04-29 11:37:36,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +20: [2023-04-29 11:37:36,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +20: [2023-04-29 11:37:36,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 8: [2023-04-29 11:37:36,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 8: [2023-04-29 11:37:36,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 8: [2023-04-29 11:37:36,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +29: [2023-04-29 11:37:36,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +29: [2023-04-29 11:37:36,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +27: [2023-04-29 11:37:36,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +29: [2023-04-29 11:37:36,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +27: [2023-04-29 11:37:36,101] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 216 + 8: [2023-04-29 11:37:36,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +29: [2023-04-29 11:37:36,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +14: [2023-04-29 11:37:36,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +14: [2023-04-29 11:37:36,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +14: [2023-04-29 11:37:36,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +20: [2023-04-29 11:37:36,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +20: [2023-04-29 11:37:36,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 4: [2023-04-29 11:37:36,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 4: [2023-04-29 11:37:36,107] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 34 +27: [2023-04-29 11:37:36,108] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 216 + 4: [2023-04-29 11:37:36,114] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 34 + 7: [2023-04-29 11:37:36,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +31: [2023-04-29 11:37:36,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +31: [2023-04-29 11:37:36,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +31: [2023-04-29 11:37:36,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 7: [2023-04-29 11:37:36,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 7: [2023-04-29 11:37:36,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +31: [2023-04-29 11:37:36,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +19: [2023-04-29 11:37:36,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +16: [2023-04-29 11:37:36,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +10: [2023-04-29 11:37:36,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +10: [2023-04-29 11:37:36,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +10: [2023-04-29 11:37:36,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +12: [2023-04-29 11:37:36,123] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +10: [2023-04-29 11:37:36,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 7: [2023-04-29 11:37:36,123] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +16: [2023-04-29 11:37:36,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +16: [2023-04-29 11:37:36,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +16: [2023-04-29 11:37:36,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +11: [2023-04-29 11:37:36,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 6: [2023-04-29 11:37:36,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +11: [2023-04-29 11:37:36,124] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 92 + 6: [2023-04-29 11:37:36,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +22: [2023-04-29 11:37:36,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +22: [2023-04-29 11:37:36,126] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 180 + 6: [2023-04-29 11:37:36,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 8: [2023-04-29 11:37:36,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +22: [2023-04-29 11:37:36,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 6: [2023-04-29 11:37:36,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +29: [2023-04-29 11:37:36,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +19: [2023-04-29 11:37:36,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +11: [2023-04-29 11:37:36,131] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 92 +29: [2023-04-29 11:37:36,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 9: [2023-04-29 11:37:36,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 9: [2023-04-29 11:37:36,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 9: [2023-04-29 11:37:36,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 9: [2023-04-29 11:37:36,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +29: [2023-04-29 11:37:36,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +29: [2023-04-29 11:37:36,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +19: [2023-04-29 11:37:36,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +12: [2023-04-29 11:37:36,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +21: [2023-04-29 11:37:36,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +12: [2023-04-29 11:37:36,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +12: [2023-04-29 11:37:36,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 8: [2023-04-29 11:37:36,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +21: [2023-04-29 11:37:36,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +19: [2023-04-29 11:37:36,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +22: [2023-04-29 11:37:36,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +22: [2023-04-29 11:37:36,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 8: [2023-04-29 11:37:36,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 4: [2023-04-29 11:37:36,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +22: [2023-04-29 11:37:36,138] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 180 + 4: [2023-04-29 11:37:36,138] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 36 +30: [2023-04-29 11:37:36,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 8: [2023-04-29 11:37:36,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +19: [2023-04-29 11:37:36,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +28: [2023-04-29 11:37:36,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +28: [2023-04-29 11:37:36,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +28: [2023-04-29 11:37:36,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +28: [2023-04-29 11:37:36,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +30: [2023-04-29 11:37:36,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +19: [2023-04-29 11:37:36,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +23: [2023-04-29 11:37:36,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +23: [2023-04-29 11:37:36,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +30: [2023-04-29 11:37:36,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 4: [2023-04-29 11:37:36,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +19: [2023-04-29 11:37:36,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +30: [2023-04-29 11:37:36,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +22: [2023-04-29 11:37:36,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +30: [2023-04-29 11:37:36,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 4: [2023-04-29 11:37:36,147] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 36 +10: [2023-04-29 11:37:36,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +27: [2023-04-29 11:37:36,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +27: [2023-04-29 11:37:36,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +27: [2023-04-29 11:37:36,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 4: [2023-04-29 11:37:36,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +27: [2023-04-29 11:37:36,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +21: [2023-04-29 11:37:36,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +30: [2023-04-29 11:37:36,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +30: [2023-04-29 11:37:36,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +19: [2023-04-29 11:37:36,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +30: [2023-04-29 11:37:36,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +31: [2023-04-29 11:37:36,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +31: [2023-04-29 11:37:36,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +10: [2023-04-29 11:37:36,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +31: [2023-04-29 11:37:36,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +21: [2023-04-29 11:37:36,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +31: [2023-04-29 11:37:36,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +23: [2023-04-29 11:37:36,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 4: [2023-04-29 11:37:36,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +23: [2023-04-29 11:37:36,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +23: [2023-04-29 11:37:36,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +10: [2023-04-29 11:37:36,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +10: [2023-04-29 11:37:36,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +14: [2023-04-29 11:37:36,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +23: [2023-04-29 11:37:36,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +21: [2023-04-29 11:37:36,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +17: [2023-04-29 11:37:36,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +17: [2023-04-29 11:37:36,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +17: [2023-04-29 11:37:36,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +17: [2023-04-29 11:37:36,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 4: [2023-04-29 11:37:36,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +23: [2023-04-29 11:37:36,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 9: [2023-04-29 11:37:36,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +20: [2023-04-29 11:37:36,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 9: [2023-04-29 11:37:36,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +24: [2023-04-29 11:37:36,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +24: [2023-04-29 11:37:36,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 4: [2023-04-29 11:37:36,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 4: [2023-04-29 11:37:36,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +14: [2023-04-29 11:37:36,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 9: [2023-04-29 11:37:36,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +21: [2023-04-29 11:37:36,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +23: [2023-04-29 11:37:36,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +24: [2023-04-29 11:37:36,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +24: [2023-04-29 11:37:36,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 9: [2023-04-29 11:37:36,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +21: [2023-04-29 11:37:36,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +20: [2023-04-29 11:37:36,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +20: [2023-04-29 11:37:36,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 4: [2023-04-29 11:37:36,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 4: [2023-04-29 11:37:36,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +28: [2023-04-29 11:37:36,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +20: [2023-04-29 11:37:36,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +14: [2023-04-29 11:37:36,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +28: [2023-04-29 11:37:36,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +28: [2023-04-29 11:37:36,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +48: [2023-04-29 11:37:36,174] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 388 +48: [2023-04-29 11:37:36,176] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 390 +14: [2023-04-29 11:37:36,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +20: [2023-04-29 11:37:36,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +28: [2023-04-29 11:37:36,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +14: [2023-04-29 11:37:36,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +21: [2023-04-29 11:37:36,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +27: [2023-04-29 11:37:36,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +27: [2023-04-29 11:37:36,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +27: [2023-04-29 11:37:36,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +48: [2023-04-29 11:37:36,178] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 384 +27: [2023-04-29 11:37:36,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +20: [2023-04-29 11:37:36,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 7: [2023-04-29 11:37:36,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +20: [2023-04-29 11:37:36,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +48: [2023-04-29 11:37:36,181] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 386 +14: [2023-04-29 11:37:36,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +14: [2023-04-29 11:37:36,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +17: [2023-04-29 11:37:36,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +14: [2023-04-29 11:37:36,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 7: [2023-04-29 11:37:36,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 5: [2023-04-29 11:37:36,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 5: [2023-04-29 11:37:36,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 5: [2023-04-29 11:37:36,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 5: [2023-04-29 11:37:36,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +20: [2023-04-29 11:37:36,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +17: [2023-04-29 11:37:36,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 0: [2023-04-29 11:37:36,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2023-04-29 11:37:36,189] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 6 +12: [2023-04-29 11:37:36,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +15: [2023-04-29 11:37:36,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +15: [2023-04-29 11:37:36,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +15: [2023-04-29 11:37:36,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 7: [2023-04-29 11:37:36,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 7: [2023-04-29 11:37:36,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +15: [2023-04-29 11:37:36,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 6: [2023-04-29 11:37:36,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +17: [2023-04-29 11:37:36,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +17: [2023-04-29 11:37:36,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +29: [2023-04-29 11:37:36,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +22: [2023-04-29 11:37:36,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +12: [2023-04-29 11:37:36,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 0: [2023-04-29 11:37:36,196] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 6 + 7: [2023-04-29 11:37:36,197] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +24: [2023-04-29 11:37:36,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +24: [2023-04-29 11:37:36,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +24: [2023-04-29 11:37:36,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +24: [2023-04-29 11:37:36,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 7: [2023-04-29 11:37:36,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 6: [2023-04-29 11:37:36,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 6: [2023-04-29 11:37:36,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 7: [2023-04-29 11:37:36,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 8: [2023-04-29 11:37:36,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +29: [2023-04-29 11:37:36,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 6: [2023-04-29 11:37:36,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +29: [2023-04-29 11:37:36,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +10: [2023-04-29 11:37:36,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +12: [2023-04-29 11:37:36,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +12: [2023-04-29 11:37:36,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 7: [2023-04-29 11:37:36,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +12: [2023-04-29 11:37:36,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +22: [2023-04-29 11:37:36,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +22: [2023-04-29 11:37:36,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 6: [2023-04-29 11:37:36,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +29: [2023-04-29 11:37:36,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +10: [2023-04-29 11:37:36,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 6: [2023-04-29 11:37:36,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +29: [2023-04-29 11:37:36,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +29: [2023-04-29 11:37:36,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 6: [2023-04-29 11:37:36,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 8: [2023-04-29 11:37:36,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 6: [2023-04-29 11:37:36,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +12: [2023-04-29 11:37:36,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +12: [2023-04-29 11:37:36,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +12: [2023-04-29 11:37:36,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 8: [2023-04-29 11:37:36,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +24: [2023-04-29 11:37:36,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +24: [2023-04-29 11:37:36,213] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 196 + 5: [2023-04-29 11:37:36,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +29: [2023-04-29 11:37:36,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 3: [2023-04-29 11:37:36,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 3: [2023-04-29 11:37:36,214] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 26 +29: [2023-04-29 11:37:36,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 5: [2023-04-29 11:37:36,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 5: [2023-04-29 11:37:36,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 8: [2023-04-29 11:37:36,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +22: [2023-04-29 11:37:36,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 5: [2023-04-29 11:37:36,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +31: [2023-04-29 11:37:36,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 8: [2023-04-29 11:37:36,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 8: [2023-04-29 11:37:36,219] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 68 +22: [2023-04-29 11:37:36,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +22: [2023-04-29 11:37:36,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +22: [2023-04-29 11:37:36,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +24: [2023-04-29 11:37:36,220] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 196 + 8: [2023-04-29 11:37:36,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 8: [2023-04-29 11:37:36,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 3: [2023-04-29 11:37:36,221] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 26 +21: [2023-04-29 11:37:36,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +21: [2023-04-29 11:37:36,223] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 174 +15: [2023-04-29 11:37:36,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 8: [2023-04-29 11:37:36,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +22: [2023-04-29 11:37:36,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 3: [2023-04-29 11:37:36,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 3: [2023-04-29 11:37:36,226] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 24 +15: [2023-04-29 11:37:36,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +10: [2023-04-29 11:37:36,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +31: [2023-04-29 11:37:36,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +16: [2023-04-29 11:37:36,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... +16: [2023-04-29 11:37:36,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... +16: [2023-04-29 11:37:36,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... +16: [2023-04-29 11:37:36,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... + 8: [2023-04-29 11:37:36,227] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 68 +10: [2023-04-29 11:37:36,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +15: [2023-04-29 11:37:36,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +15: [2023-04-29 11:37:36,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +10: [2023-04-29 11:37:36,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +21: [2023-04-29 11:37:36,229] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 174 + 8: [2023-04-29 11:37:36,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +31: [2023-04-29 11:37:36,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 9: [2023-04-29 11:37:36,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 3: [2023-04-29 11:37:36,232] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 24 + 9: [2023-04-29 11:37:36,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +31: [2023-04-29 11:37:36,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +31: [2023-04-29 11:37:36,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +10: [2023-04-29 11:37:36,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +10: [2023-04-29 11:37:36,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +18: [2023-04-29 11:37:36,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +18: [2023-04-29 11:37:36,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +18: [2023-04-29 11:37:36,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +27: [2023-04-29 11:37:36,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +10: [2023-04-29 11:37:36,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 8: [2023-04-29 11:37:36,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 8: [2023-04-29 11:37:36,237] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 64 + 9: [2023-04-29 11:37:36,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +31: [2023-04-29 11:37:36,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 9: [2023-04-29 11:37:36,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +24: [2023-04-29 11:37:36,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +24: [2023-04-29 11:37:36,239] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 194 +18: [2023-04-29 11:37:36,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +28: [2023-04-29 11:37:36,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +31: [2023-04-29 11:37:36,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 9: [2023-04-29 11:37:36,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 9: [2023-04-29 11:37:36,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +31: [2023-04-29 11:37:36,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +27: [2023-04-29 11:37:36,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +28: [2023-04-29 11:37:36,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 8: [2023-04-29 11:37:36,244] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 64 +24: [2023-04-29 11:37:36,245] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 194 +27: [2023-04-29 11:37:36,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +17: [2023-04-29 11:37:36,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +28: [2023-04-29 11:37:36,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 9: [2023-04-29 11:37:36,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 9: [2023-04-29 11:37:36,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +28: [2023-04-29 11:37:36,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +27: [2023-04-29 11:37:36,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +27: [2023-04-29 11:37:36,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +22: [2023-04-29 11:37:36,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +22: [2023-04-29 11:37:36,250] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 176 +27: [2023-04-29 11:37:36,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 3: [2023-04-29 11:37:36,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 3: [2023-04-29 11:37:36,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +17: [2023-04-29 11:37:36,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +22: [2023-04-29 11:37:36,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +17: [2023-04-29 11:37:36,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +28: [2023-04-29 11:37:36,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +28: [2023-04-29 11:37:36,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +22: [2023-04-29 11:37:36,253] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 182 + 3: [2023-04-29 11:37:36,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 3: [2023-04-29 11:37:36,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +27: [2023-04-29 11:37:36,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +27: [2023-04-29 11:37:36,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +17: [2023-04-29 11:37:36,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +28: [2023-04-29 11:37:36,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +28: [2023-04-29 11:37:36,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +22: [2023-04-29 11:37:36,261] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 176 +18: [2023-04-29 11:37:36,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +17: [2023-04-29 11:37:36,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +22: [2023-04-29 11:37:36,263] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 182 + 0: [2023-04-29 11:37:36,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 0: [2023-04-29 11:37:36,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 0: [2023-04-29 11:37:36,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 0: [2023-04-29 11:37:36,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +18: [2023-04-29 11:37:36,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +24: [2023-04-29 11:37:36,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +24: [2023-04-29 11:37:36,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +24: [2023-04-29 11:37:36,268] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 192 +24: [2023-04-29 11:37:36,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +17: [2023-04-29 11:37:36,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +17: [2023-04-29 11:37:36,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +18: [2023-04-29 11:37:36,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +18: [2023-04-29 11:37:36,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +24: [2023-04-29 11:37:36,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +24: [2023-04-29 11:37:36,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +24: [2023-04-29 11:37:36,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 3: [2023-04-29 11:37:36,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 3: [2023-04-29 11:37:36,274] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 28 +11: [2023-04-29 11:37:36,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +11: [2023-04-29 11:37:36,274] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 88 +24: [2023-04-29 11:37:36,275] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 192 +24: [2023-04-29 11:37:36,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +13: [2023-04-29 11:37:36,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +13: [2023-04-29 11:37:36,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +13: [2023-04-29 11:37:36,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +17: [2023-04-29 11:37:36,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +13: [2023-04-29 11:37:36,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +16: [2023-04-29 11:37:36,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +16: [2023-04-29 11:37:36,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +24: [2023-04-29 11:37:36,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 3: [2023-04-29 11:37:36,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... + 3: [2023-04-29 11:37:36,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +24: [2023-04-29 11:37:36,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 5: [2023-04-29 11:37:36,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 3: [2023-04-29 11:37:36,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +11: [2023-04-29 11:37:36,281] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 88 + 0: [2023-04-29 11:37:36,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2023-04-29 11:37:36,282] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 4 + 8: [2023-04-29 11:37:36,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 8: [2023-04-29 11:37:36,282] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 70 + 3: [2023-04-29 11:37:36,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +18: [2023-04-29 11:37:36,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. +18: [2023-04-29 11:37:36,283] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 148 +11: [2023-04-29 11:37:36,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +11: [2023-04-29 11:37:36,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +11: [2023-04-29 11:37:36,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +11: [2023-04-29 11:37:36,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 3: [2023-04-29 11:37:36,284] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 28 +16: [2023-04-29 11:37:36,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. + 5: [2023-04-29 11:37:36,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 3: [2023-04-29 11:37:36,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 3: [2023-04-29 11:37:36,288] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 30 + 8: [2023-04-29 11:37:36,289] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 70 +18: [2023-04-29 11:37:36,289] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 148 + 5: [2023-04-29 11:37:36,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 5: [2023-04-29 11:37:36,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 5: [2023-04-29 11:37:36,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +25: [2023-04-29 11:37:36,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +25: [2023-04-29 11:37:36,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +25: [2023-04-29 11:37:36,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +25: [2023-04-29 11:37:36,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 0: [2023-04-29 11:37:36,291] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 4 +16: [2023-04-29 11:37:36,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_20-model_01-model_states.pt. +22: [2023-04-29 11:37:36,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. + 3: [2023-04-29 11:37:36,295] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 30 +15: [2023-04-29 11:37:36,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +22: [2023-04-29 11:37:36,296] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 178 + 5: [2023-04-29 11:37:36,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 5: [2023-04-29 11:37:36,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 5: [2023-04-29 11:37:36,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +23: [2023-04-29 11:37:36,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +23: [2023-04-29 11:37:36,298] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 190 +23: [2023-04-29 11:37:36,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +15: [2023-04-29 11:37:36,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 0: [2023-04-29 11:37:36,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +23: [2023-04-29 11:37:36,298] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 186 + 0: [2023-04-29 11:37:36,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 0: [2023-04-29 11:37:36,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 0: [2023-04-29 11:37:36,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +13: [2023-04-29 11:37:36,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 8: [2023-04-29 11:37:36,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 8: [2023-04-29 11:37:36,302] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 66 +15: [2023-04-29 11:37:36,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +23: [2023-04-29 11:37:36,305] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 186 +23: [2023-04-29 11:37:36,306] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 190 +16: [2023-04-29 11:37:36,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +16: [2023-04-29 11:37:36,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +22: [2023-04-29 11:37:36,307] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 178 +17: [2023-04-29 11:37:36,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. +17: [2023-04-29 11:37:36,309] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 138 +15: [2023-04-29 11:37:36,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +15: [2023-04-29 11:37:36,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +15: [2023-04-29 11:37:36,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +13: [2023-04-29 11:37:36,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +13: [2023-04-29 11:37:36,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 8: [2023-04-29 11:37:36,311] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 66 +15: [2023-04-29 11:37:36,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 0: [2023-04-29 11:37:36,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. + 0: [2023-04-29 11:37:36,312] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 0 +11: [2023-04-29 11:37:36,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +13: [2023-04-29 11:37:36,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +11: [2023-04-29 11:37:36,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +15: [2023-04-29 11:37:36,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +11: [2023-04-29 11:37:36,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +17: [2023-04-29 11:37:36,316] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 138 +11: [2023-04-29 11:37:36,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +25: [2023-04-29 11:37:36,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +16: [2023-04-29 11:37:36,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +25: [2023-04-29 11:37:36,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +25: [2023-04-29 11:37:36,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +18: [2023-04-29 11:37:36,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +25: [2023-04-29 11:37:36,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 0: [2023-04-29 11:37:36,321] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 0 +16: [2023-04-29 11:37:36,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt... +18: [2023-04-29 11:37:36,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +11: [2023-04-29 11:37:36,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +11: [2023-04-29 11:37:36,326] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 90 + 0: could not find arguments in the checkpoint ... + 0: checkpoint version 3.0 +31: [2023-04-29 11:37:36,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +31: [2023-04-29 11:37:36,328] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 254 +18: [2023-04-29 11:37:36,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 2: [2023-04-29 11:37:36,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 2: [2023-04-29 11:37:36,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +11: [2023-04-29 11:37:36,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 2: [2023-04-29 11:37:36,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +18: [2023-04-29 11:37:36,330] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 146 +11: [2023-04-29 11:37:36,330] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 94 + 2: [2023-04-29 11:37:36,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +11: [2023-04-29 11:37:36,333] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 90 +18: [2023-04-29 11:37:36,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +31: [2023-04-29 11:37:36,336] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 254 + 0: [2023-04-29 11:37:36,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 0: [2023-04-29 11:37:36,336] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 2 +18: [2023-04-29 11:37:36,337] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 146 +11: [2023-04-29 11:37:36,338] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 94 +17: [2023-04-29 11:37:36,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. +12: [2023-04-29 11:37:36,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +17: [2023-04-29 11:37:36,340] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 136 +12: [2023-04-29 11:37:36,340] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 96 +18: [2023-04-29 11:37:36,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +23: [2023-04-29 11:37:36,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +23: [2023-04-29 11:37:36,342] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 184 + 0: [2023-04-29 11:37:36,345] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 2 +18: [2023-04-29 11:37:36,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +18: [2023-04-29 11:37:36,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 3: [2023-04-29 11:37:36,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +12: [2023-04-29 11:37:36,347] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 96 +18: [2023-04-29 11:37:36,349] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. +18: [2023-04-29 11:37:36,349] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 144 +23: [2023-04-29 11:37:36,349] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 184 +17: [2023-04-29 11:37:36,350] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 136 + 3: [2023-04-29 11:37:36,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 3: [2023-04-29 11:37:36,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +18: [2023-04-29 11:37:36,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +18: [2023-04-29 11:37:36,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 3: [2023-04-29 11:37:36,354] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 2: [2023-04-29 11:37:36,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 3: [2023-04-29 11:37:36,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 1: [2023-04-29 11:37:36,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 1: [2023-04-29 11:37:36,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +18: [2023-04-29 11:37:36,357] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 144 + 3: [2023-04-29 11:37:36,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 1: [2023-04-29 11:37:36,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 3: [2023-04-29 11:37:36,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 0: [2023-04-29 11:37:36,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 2: [2023-04-29 11:37:36,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 2: [2023-04-29 11:37:36,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 3: [2023-04-29 11:37:36,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 2: [2023-04-29 11:37:36,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 1: [2023-04-29 11:37:36,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 0: [2023-04-29 11:37:36,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +18: [2023-04-29 11:37:36,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. +18: [2023-04-29 11:37:36,364] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 150 + 0: [2023-04-29 11:37:36,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +17: [2023-04-29 11:37:36,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. +17: [2023-04-29 11:37:36,367] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 142 + 1: [2023-04-29 11:37:36,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 1: [2023-04-29 11:37:36,369] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 14 +13: [2023-04-29 11:37:36,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +18: [2023-04-29 11:37:36,372] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 150 + 0: [2023-04-29 11:37:36,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +16: [2023-04-29 11:37:36,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +25: [2023-04-29 11:37:36,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +17: [2023-04-29 11:37:36,375] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 142 +13: [2023-04-29 11:37:36,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 1: [2023-04-29 11:37:36,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 1: [2023-04-29 11:37:36,376] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 8 +11: [2023-04-29 11:37:36,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +14: [2023-04-29 11:37:36,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +14: [2023-04-29 11:37:36,378] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 114 +16: [2023-04-29 11:37:36,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. + 1: [2023-04-29 11:37:36,378] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 14 +25: [2023-04-29 11:37:36,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +16: [2023-04-29 11:37:36,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +25: [2023-04-29 11:37:36,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 0: [2023-04-29 11:37:36,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 0: [2023-04-29 11:37:36,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +11: [2023-04-29 11:37:36,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +16: [2023-04-29 11:37:36,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +12: [2023-04-29 11:37:36,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +11: [2023-04-29 11:37:36,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +12: [2023-04-29 11:37:36,385] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 102 +14: [2023-04-29 11:37:36,385] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 114 +25: [2023-04-29 11:37:36,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +25: [2023-04-29 11:37:36,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 1: [2023-04-29 11:37:36,387] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 8 + 1: [2023-04-29 11:37:36,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 1: [2023-04-29 11:37:36,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 1: [2023-04-29 11:37:36,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 0: [2023-04-29 11:37:36,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 0: [2023-04-29 11:37:36,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +13: [2023-04-29 11:37:36,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +13: [2023-04-29 11:37:36,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +13: [2023-04-29 11:37:36,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +11: [2023-04-29 11:37:36,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +11: [2023-04-29 11:37:36,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +25: [2023-04-29 11:37:36,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +30: [2023-04-29 11:37:36,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +30: [2023-04-29 11:37:36,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +12: [2023-04-29 11:37:36,392] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 102 +11: [2023-04-29 11:37:36,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 1: [2023-04-29 11:37:36,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +30: [2023-04-29 11:37:36,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +30: [2023-04-29 11:37:36,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +16: [2023-04-29 11:37:36,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +16: [2023-04-29 11:37:36,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_00-model_states.pt. +13: [2023-04-29 11:37:36,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +13: [2023-04-29 11:37:36,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +13: [2023-04-29 11:37:36,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 1: [2023-04-29 11:37:36,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 1: [2023-04-29 11:37:36,397] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 12 +11: [2023-04-29 11:37:36,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +25: [2023-04-29 11:37:36,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +11: [2023-04-29 11:37:36,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +26: [2023-04-29 11:37:36,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +26: [2023-04-29 11:37:36,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +26: [2023-04-29 11:37:36,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +26: [2023-04-29 11:37:36,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +10: [2023-04-29 11:37:36,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +10: [2023-04-29 11:37:36,402] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 84 +16: [2023-04-29 11:37:36,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... +12: [2023-04-29 11:37:36,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +12: [2023-04-29 11:37:36,403] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 98 +16: [2023-04-29 11:37:36,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt... + 1: [2023-04-29 11:37:36,404] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 12 + 2: [2023-04-29 11:37:36,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +25: [2023-04-29 11:37:36,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 2: [2023-04-29 11:37:36,404] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 18 +10: [2023-04-29 11:37:36,409] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 84 + 9: [2023-04-29 11:37:36,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 9: [2023-04-29 11:37:36,409] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 72 + 1: [2023-04-29 11:37:36,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 1: [2023-04-29 11:37:36,410] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 10 +12: [2023-04-29 11:37:36,410] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 98 + 2: [2023-04-29 11:37:36,412] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 18 + 9: [2023-04-29 11:37:36,417] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 72 + 1: [2023-04-29 11:37:36,418] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 10 +31: [2023-04-29 11:37:36,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +31: [2023-04-29 11:37:36,419] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 250 + 2: [2023-04-29 11:37:36,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +30: [2023-04-29 11:37:36,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +30: [2023-04-29 11:37:36,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +30: [2023-04-29 11:37:36,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +31: [2023-04-29 11:37:36,426] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 250 +26: [2023-04-29 11:37:36,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +30: [2023-04-29 11:37:36,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +19: [2023-04-29 11:37:36,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +19: [2023-04-29 11:37:36,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +10: [2023-04-29 11:37:36,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 2: [2023-04-29 11:37:36,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +23: [2023-04-29 11:37:36,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +23: [2023-04-29 11:37:36,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +21: [2023-04-29 11:37:36,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +10: [2023-04-29 11:37:36,429] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 82 +26: [2023-04-29 11:37:36,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +21: [2023-04-29 11:37:36,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +21: [2023-04-29 11:37:36,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +21: [2023-04-29 11:37:36,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +23: [2023-04-29 11:37:36,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +23: [2023-04-29 11:37:36,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +26: [2023-04-29 11:37:36,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +19: [2023-04-29 11:37:36,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 2: [2023-04-29 11:37:36,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 2: [2023-04-29 11:37:36,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +19: [2023-04-29 11:37:36,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +26: [2023-04-29 11:37:36,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 2: [2023-04-29 11:37:36,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +10: [2023-04-29 11:37:36,437] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 82 + 2: [2023-04-29 11:37:36,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 2: [2023-04-29 11:37:36,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 2: [2023-04-29 11:37:36,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +31: [2023-04-29 11:37:36,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +31: [2023-04-29 11:37:36,442] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 248 +15: [2023-04-29 11:37:36,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +15: [2023-04-29 11:37:36,445] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 126 +31: [2023-04-29 11:37:36,449] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 248 +15: [2023-04-29 11:37:36,452] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 126 +10: [2023-04-29 11:37:36,453] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +10: [2023-04-29 11:37:36,453] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 80 + 1: [2023-04-29 11:37:36,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +21: [2023-04-29 11:37:36,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +21: [2023-04-29 11:37:36,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +23: [2023-04-29 11:37:36,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 1: [2023-04-29 11:37:36,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +23: [2023-04-29 11:37:36,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 1: [2023-04-29 11:37:36,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +10: [2023-04-29 11:37:36,462] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 80 + 1: [2023-04-29 11:37:36,462] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +19: [2023-04-29 11:37:36,462] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +19: [2023-04-29 11:37:36,462] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +19: [2023-04-29 11:37:36,462] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +21: [2023-04-29 11:37:36,463] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 1: [2023-04-29 11:37:36,463] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +14: [2023-04-29 11:37:36,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +14: [2023-04-29 11:37:36,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +23: [2023-04-29 11:37:36,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +14: [2023-04-29 11:37:36,465] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 118 +14: [2023-04-29 11:37:36,465] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 112 + 1: [2023-04-29 11:37:36,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +23: [2023-04-29 11:37:36,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +21: [2023-04-29 11:37:36,466] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 1: [2023-04-29 11:37:36,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 2: [2023-04-29 11:37:36,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 2: [2023-04-29 11:37:36,467] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 16 +19: [2023-04-29 11:37:36,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 5: [2023-04-29 11:37:36,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 5: [2023-04-29 11:37:36,468] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 40 +28: [2023-04-29 11:37:36,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +28: [2023-04-29 11:37:36,470] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 228 + 9: [2023-04-29 11:37:36,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 9: [2023-04-29 11:37:36,471] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 74 +14: [2023-04-29 11:37:36,473] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 112 +14: [2023-04-29 11:37:36,473] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 118 + 1: [2023-04-29 11:37:36,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 9: [2023-04-29 11:37:36,473] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 9: [2023-04-29 11:37:36,474] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 76 +10: [2023-04-29 11:37:36,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +10: [2023-04-29 11:37:36,475] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 86 + 5: [2023-04-29 11:37:36,476] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 40 + 2: [2023-04-29 11:37:36,476] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 16 +28: [2023-04-29 11:37:36,477] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 228 +25: [2023-04-29 11:37:36,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +25: [2023-04-29 11:37:36,477] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 200 +15: [2023-04-29 11:37:36,479] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 9: [2023-04-29 11:37:36,479] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 74 +15: [2023-04-29 11:37:36,479] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 124 + 7: [2023-04-29 11:37:36,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 7: [2023-04-29 11:37:36,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 7: [2023-04-29 11:37:36,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 7: [2023-04-29 11:37:36,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 9: [2023-04-29 11:37:36,481] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 76 +10: [2023-04-29 11:37:36,481] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 86 +19: [2023-04-29 11:37:36,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. +19: [2023-04-29 11:37:36,483] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 154 + 7: [2023-04-29 11:37:36,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 7: [2023-04-29 11:37:36,485] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 58 +12: [2023-04-29 11:37:36,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +12: [2023-04-29 11:37:36,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +25: [2023-04-29 11:37:36,485] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 200 +12: [2023-04-29 11:37:36,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +12: [2023-04-29 11:37:36,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +14: [2023-04-29 11:37:36,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +14: [2023-04-29 11:37:36,488] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 116 +15: [2023-04-29 11:37:36,489] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 124 +19: [2023-04-29 11:37:36,489] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 154 +30: [2023-04-29 11:37:36,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +30: [2023-04-29 11:37:36,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +26: [2023-04-29 11:37:36,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 7: [2023-04-29 11:37:36,493] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 58 + 7: [2023-04-29 11:37:36,495] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 7: [2023-04-29 11:37:36,495] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 60 +14: [2023-04-29 11:37:36,495] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 116 +30: [2023-04-29 11:37:36,497] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +30: [2023-04-29 11:37:36,497] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 2: [2023-04-29 11:37:36,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +30: [2023-04-29 11:37:36,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +30: [2023-04-29 11:37:36,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 2: [2023-04-29 11:37:36,498] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 22 + 2: [2023-04-29 11:37:36,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +26: [2023-04-29 11:37:36,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 2: [2023-04-29 11:37:36,500] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 20 +26: [2023-04-29 11:37:36,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 6: [2023-04-29 11:37:36,502] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 5: [2023-04-29 11:37:36,502] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +30: [2023-04-29 11:37:36,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +30: [2023-04-29 11:37:36,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 6: [2023-04-29 11:37:36,502] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 48 + 5: [2023-04-29 11:37:36,502] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 44 + 7: [2023-04-29 11:37:36,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 6: [2023-04-29 11:37:36,505] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 6: [2023-04-29 11:37:36,505] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 54 +26: [2023-04-29 11:37:36,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +26: [2023-04-29 11:37:36,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 7: [2023-04-29 11:37:36,506] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 60 +15: [2023-04-29 11:37:36,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +15: [2023-04-29 11:37:36,507] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 122 + 2: [2023-04-29 11:37:36,507] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 22 + 9: [2023-04-29 11:37:36,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 9: [2023-04-29 11:37:36,508] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 78 + 2: [2023-04-29 11:37:36,509] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 20 +26: [2023-04-29 11:37:36,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +13: [2023-04-29 11:37:36,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +13: [2023-04-29 11:37:36,510] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 108 + 5: [2023-04-29 11:37:36,510] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 44 + 7: [2023-04-29 11:37:36,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +12: [2023-04-29 11:37:36,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 6: [2023-04-29 11:37:36,511] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 48 + 7: [2023-04-29 11:37:36,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +26: [2023-04-29 11:37:36,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 7: [2023-04-29 11:37:36,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 6: [2023-04-29 11:37:36,514] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 54 +15: [2023-04-29 11:37:36,515] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 122 +26: [2023-04-29 11:37:36,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +21: [2023-04-29 11:37:36,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 9: [2023-04-29 11:37:36,516] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 78 +13: [2023-04-29 11:37:36,516] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 108 +12: [2023-04-29 11:37:36,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 6: [2023-04-29 11:37:36,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 6: [2023-04-29 11:37:36,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +12: [2023-04-29 11:37:36,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +29: [2023-04-29 11:37:36,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +29: [2023-04-29 11:37:36,518] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 234 +29: [2023-04-29 11:37:36,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. + 5: [2023-04-29 11:37:36,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +29: [2023-04-29 11:37:36,519] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 238 + 5: [2023-04-29 11:37:36,520] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 42 +23: [2023-04-29 11:37:36,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +23: [2023-04-29 11:37:36,520] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 188 +21: [2023-04-29 11:37:36,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +12: [2023-04-29 11:37:36,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 6: [2023-04-29 11:37:36,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 6: [2023-04-29 11:37:36,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +29: [2023-04-29 11:37:36,525] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 234 +21: [2023-04-29 11:37:36,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +29: [2023-04-29 11:37:36,526] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 238 +23: [2023-04-29 11:37:36,527] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 188 + 5: [2023-04-29 11:37:36,527] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 42 +23: [2023-04-29 11:37:36,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +23: [2023-04-29 11:37:36,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +19: [2023-04-29 11:37:36,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +15: [2023-04-29 11:37:36,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +15: [2023-04-29 11:37:36,530] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 120 +21: [2023-04-29 11:37:36,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +19: [2023-04-29 11:37:36,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +21: [2023-04-29 11:37:36,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +23: [2023-04-29 11:37:36,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +23: [2023-04-29 11:37:36,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +26: [2023-04-29 11:37:36,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +26: [2023-04-29 11:37:36,535] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 210 +23: [2023-04-29 11:37:36,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 6: [2023-04-29 11:37:36,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +27: [2023-04-29 11:37:36,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +27: [2023-04-29 11:37:36,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +27: [2023-04-29 11:37:36,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 6: [2023-04-29 11:37:36,536] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 52 +27: [2023-04-29 11:37:36,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 4: [2023-04-29 11:37:36,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 4: [2023-04-29 11:37:36,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 4: [2023-04-29 11:37:36,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 4: [2023-04-29 11:37:36,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +19: [2023-04-29 11:37:36,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +29: [2023-04-29 11:37:36,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +29: [2023-04-29 11:37:36,538] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 236 +15: [2023-04-29 11:37:36,538] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 120 +19: [2023-04-29 11:37:36,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +23: [2023-04-29 11:37:36,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +21: [2023-04-29 11:37:36,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +20: [2023-04-29 11:37:36,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +20: [2023-04-29 11:37:36,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +21: [2023-04-29 11:37:36,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +20: [2023-04-29 11:37:36,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +20: [2023-04-29 11:37:36,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +26: [2023-04-29 11:37:36,542] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 210 +23: [2023-04-29 11:37:36,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +19: [2023-04-29 11:37:36,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 6: [2023-04-29 11:37:36,544] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 52 +29: [2023-04-29 11:37:36,545] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 236 +19: [2023-04-29 11:37:36,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +23: [2023-04-29 11:37:36,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 6: [2023-04-29 11:37:36,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 6: [2023-04-29 11:37:36,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +24: [2023-04-29 11:37:36,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +24: [2023-04-29 11:37:36,548] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 198 +21: [2023-04-29 11:37:36,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 7: [2023-04-29 11:37:36,551] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 7: [2023-04-29 11:37:36,551] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 56 +19: [2023-04-29 11:37:36,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +25: [2023-04-29 11:37:36,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +25: [2023-04-29 11:37:36,553] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 204 +28: [2023-04-29 11:37:36,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +28: [2023-04-29 11:37:36,553] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 224 +26: [2023-04-29 11:37:36,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. + 6: [2023-04-29 11:37:36,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +26: [2023-04-29 11:37:36,554] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 212 +19: [2023-04-29 11:37:36,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 6: [2023-04-29 11:37:36,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +24: [2023-04-29 11:37:36,558] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 198 +25: [2023-04-29 11:37:36,560] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 204 +28: [2023-04-29 11:37:36,560] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 224 + 4: [2023-04-29 11:37:36,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +26: [2023-04-29 11:37:36,561] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 212 + 7: [2023-04-29 11:37:36,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 7: [2023-04-29 11:37:36,562] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 56 +22: [2023-04-29 11:37:36,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +22: [2023-04-29 11:37:36,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 4: [2023-04-29 11:37:36,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +10: [2023-04-29 11:37:36,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +10: [2023-04-29 11:37:36,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +10: [2023-04-29 11:37:36,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +10: [2023-04-29 11:37:36,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +27: [2023-04-29 11:37:36,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +27: [2023-04-29 11:37:36,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +27: [2023-04-29 11:37:36,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 7: [2023-04-29 11:37:36,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +22: [2023-04-29 11:37:36,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +25: [2023-04-29 11:37:36,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +25: [2023-04-29 11:37:36,566] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 202 +22: [2023-04-29 11:37:36,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +24: [2023-04-29 11:37:36,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +24: [2023-04-29 11:37:36,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +24: [2023-04-29 11:37:36,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +24: [2023-04-29 11:37:36,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +27: [2023-04-29 11:37:36,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +26: [2023-04-29 11:37:36,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +26: [2023-04-29 11:37:36,568] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 214 +12: [2023-04-29 11:37:36,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 4: [2023-04-29 11:37:36,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 4: [2023-04-29 11:37:36,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +19: [2023-04-29 11:37:36,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. +19: [2023-04-29 11:37:36,569] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 152 +12: [2023-04-29 11:37:36,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +25: [2023-04-29 11:37:36,572] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 202 +20: [2023-04-29 11:37:36,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +20: [2023-04-29 11:37:36,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +28: [2023-04-29 11:37:36,574] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +28: [2023-04-29 11:37:36,574] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +20: [2023-04-29 11:37:36,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +20: [2023-04-29 11:37:36,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +28: [2023-04-29 11:37:36,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +26: [2023-04-29 11:37:36,575] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 214 +28: [2023-04-29 11:37:36,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +29: [2023-04-29 11:37:36,577] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +29: [2023-04-29 11:37:36,578] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 232 +19: [2023-04-29 11:37:36,578] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 152 +13: [2023-04-29 11:37:36,579] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +13: [2023-04-29 11:37:36,579] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 106 +17: [2023-04-29 11:37:36,579] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. +17: [2023-04-29 11:37:36,580] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 140 +12: [2023-04-29 11:37:36,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 7: [2023-04-29 11:37:36,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 7: [2023-04-29 11:37:36,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +25: [2023-04-29 11:37:36,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. + 9: [2023-04-29 11:37:36,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 9: [2023-04-29 11:37:36,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 9: [2023-04-29 11:37:36,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +25: [2023-04-29 11:37:36,584] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 206 + 9: [2023-04-29 11:37:36,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 5: [2023-04-29 11:37:36,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 5: [2023-04-29 11:37:36,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +12: [2023-04-29 11:37:36,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +29: [2023-04-29 11:37:36,586] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 232 + 5: [2023-04-29 11:37:36,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 5: [2023-04-29 11:37:36,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 7: [2023-04-29 11:37:36,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +17: [2023-04-29 11:37:36,587] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 140 +13: [2023-04-29 11:37:36,588] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 106 + 7: [2023-04-29 11:37:36,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +22: [2023-04-29 11:37:36,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +10: [2023-04-29 11:37:36,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +12: [2023-04-29 11:37:36,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 7: [2023-04-29 11:37:36,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +12: [2023-04-29 11:37:36,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +25: [2023-04-29 11:37:36,594] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 206 + 7: [2023-04-29 11:37:36,594] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +24: [2023-04-29 11:37:36,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +10: [2023-04-29 11:37:36,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 7: [2023-04-29 11:37:36,595] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 62 +10: [2023-04-29 11:37:36,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 7: [2023-04-29 11:37:36,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +22: [2023-04-29 11:37:36,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +22: [2023-04-29 11:37:36,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +10: [2023-04-29 11:37:36,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +12: [2023-04-29 11:37:36,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +24: [2023-04-29 11:37:36,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +12: [2023-04-29 11:37:36,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +24: [2023-04-29 11:37:36,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +24: [2023-04-29 11:37:36,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 7: [2023-04-29 11:37:36,602] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 62 +22: [2023-04-29 11:37:36,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +28: [2023-04-29 11:37:36,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +28: [2023-04-29 11:37:36,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +28: [2023-04-29 11:37:36,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +28: [2023-04-29 11:37:36,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +19: [2023-04-29 11:37:36,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. +29: [2023-04-29 11:37:36,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +19: [2023-04-29 11:37:36,607] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 156 +29: [2023-04-29 11:37:36,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +29: [2023-04-29 11:37:36,608] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +29: [2023-04-29 11:37:36,608] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 6: [2023-04-29 11:37:36,610] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +28: [2023-04-29 11:37:36,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +28: [2023-04-29 11:37:36,612] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 230 +18: [2023-04-29 11:37:36,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +18: [2023-04-29 11:37:36,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 3: [2023-04-29 11:37:36,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 3: [2023-04-29 11:37:36,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 3: [2023-04-29 11:37:36,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 3: [2023-04-29 11:37:36,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +26: [2023-04-29 11:37:36,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +26: [2023-04-29 11:37:36,613] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 208 +18: [2023-04-29 11:37:36,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +18: [2023-04-29 11:37:36,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +19: [2023-04-29 11:37:36,614] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 156 + 9: [2023-04-29 11:37:36,614] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 5: [2023-04-29 11:37:36,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 9: [2023-04-29 11:37:36,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 9: [2023-04-29 11:37:36,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 9: [2023-04-29 11:37:36,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 5: [2023-04-29 11:37:36,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 5: [2023-04-29 11:37:36,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 5: [2023-04-29 11:37:36,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 6: [2023-04-29 11:37:36,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +15: [2023-04-29 11:37:36,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +15: [2023-04-29 11:37:36,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +15: [2023-04-29 11:37:36,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +15: [2023-04-29 11:37:36,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +28: [2023-04-29 11:37:36,620] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 230 +26: [2023-04-29 11:37:36,621] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 208 +27: [2023-04-29 11:37:36,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 4: [2023-04-29 11:37:36,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 6: [2023-04-29 11:37:36,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 6: [2023-04-29 11:37:36,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +13: [2023-04-29 11:37:36,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +13: [2023-04-29 11:37:36,624] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 104 +27: [2023-04-29 11:37:36,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 4: [2023-04-29 11:37:36,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 4: [2023-04-29 11:37:36,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 6: [2023-04-29 11:37:36,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 6: [2023-04-29 11:37:36,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +13: [2023-04-29 11:37:36,631] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 104 + 6: [2023-04-29 11:37:36,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +27: [2023-04-29 11:37:36,633] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 4: [2023-04-29 11:37:36,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +29: [2023-04-29 11:37:36,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +29: [2023-04-29 11:37:36,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +29: [2023-04-29 11:37:36,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +29: [2023-04-29 11:37:36,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 4: [2023-04-29 11:37:36,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +27: [2023-04-29 11:37:36,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 6: [2023-04-29 11:37:36,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +20: [2023-04-29 11:37:36,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +27: [2023-04-29 11:37:36,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +27: [2023-04-29 11:37:36,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 3: [2023-04-29 11:37:36,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +20: [2023-04-29 11:37:36,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 3: [2023-04-29 11:37:36,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 3: [2023-04-29 11:37:36,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 3: [2023-04-29 11:37:36,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 4: [2023-04-29 11:37:36,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 8: [2023-04-29 11:37:36,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 8: [2023-04-29 11:37:36,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 8: [2023-04-29 11:37:36,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 8: [2023-04-29 11:37:36,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +18: [2023-04-29 11:37:36,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +27: [2023-04-29 11:37:36,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +18: [2023-04-29 11:37:36,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 4: [2023-04-29 11:37:36,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +20: [2023-04-29 11:37:36,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +20: [2023-04-29 11:37:36,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +27: [2023-04-29 11:37:36,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 4: [2023-04-29 11:37:36,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +12: [2023-04-29 11:37:36,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +12: [2023-04-29 11:37:36,649] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 100 +15: [2023-04-29 11:37:36,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +20: [2023-04-29 11:37:36,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +20: [2023-04-29 11:37:36,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +18: [2023-04-29 11:37:36,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +18: [2023-04-29 11:37:36,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +16: [2023-04-29 11:37:36,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. +15: [2023-04-29 11:37:36,650] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +16: [2023-04-29 11:37:36,650] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 130 +15: [2023-04-29 11:37:36,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +15: [2023-04-29 11:37:36,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +10: [2023-04-29 11:37:36,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +22: [2023-04-29 11:37:36,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 5: [2023-04-29 11:37:36,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 5: [2023-04-29 11:37:36,653] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 46 +12: [2023-04-29 11:37:36,656] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 100 +10: [2023-04-29 11:37:36,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +22: [2023-04-29 11:37:36,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +20: [2023-04-29 11:37:36,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +20: [2023-04-29 11:37:36,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +16: [2023-04-29 11:37:36,658] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 130 +10: [2023-04-29 11:37:36,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +24: [2023-04-29 11:37:36,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 5: [2023-04-29 11:37:36,662] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 46 +22: [2023-04-29 11:37:36,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +14: [2023-04-29 11:37:36,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +14: [2023-04-29 11:37:36,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +10: [2023-04-29 11:37:36,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +14: [2023-04-29 11:37:36,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +14: [2023-04-29 11:37:36,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +22: [2023-04-29 11:37:36,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +10: [2023-04-29 11:37:36,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +24: [2023-04-29 11:37:36,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +10: [2023-04-29 11:37:36,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +24: [2023-04-29 11:37:36,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 8: [2023-04-29 11:37:36,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +28: [2023-04-29 11:37:36,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +22: [2023-04-29 11:37:36,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +10: [2023-04-29 11:37:36,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +22: [2023-04-29 11:37:36,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +24: [2023-04-29 11:37:36,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +24: [2023-04-29 11:37:36,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +22: [2023-04-29 11:37:36,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +10: [2023-04-29 11:37:36,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 8: [2023-04-29 11:37:36,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +28: [2023-04-29 11:37:36,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 8: [2023-04-29 11:37:36,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +24: [2023-04-29 11:37:36,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 5: [2023-04-29 11:37:36,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +28: [2023-04-29 11:37:36,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +28: [2023-04-29 11:37:36,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +28: [2023-04-29 11:37:36,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 8: [2023-04-29 11:37:36,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +22: [2023-04-29 11:37:36,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +24: [2023-04-29 11:37:36,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +24: [2023-04-29 11:37:36,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 5: [2023-04-29 11:37:36,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 5: [2023-04-29 11:37:36,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 9: [2023-04-29 11:37:36,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +28: [2023-04-29 11:37:36,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +28: [2023-04-29 11:37:36,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 9: [2023-04-29 11:37:36,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +28: [2023-04-29 11:37:36,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 5: [2023-04-29 11:37:36,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +25: [2023-04-29 11:37:36,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +25: [2023-04-29 11:37:36,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +25: [2023-04-29 11:37:36,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +25: [2023-04-29 11:37:36,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 9: [2023-04-29 11:37:36,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 9: [2023-04-29 11:37:36,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +14: [2023-04-29 11:37:36,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 9: [2023-04-29 11:37:36,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 9: [2023-04-29 11:37:36,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +14: [2023-04-29 11:37:36,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +11: [2023-04-29 11:37:36,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +11: [2023-04-29 11:37:36,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +11: [2023-04-29 11:37:36,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 5: [2023-04-29 11:37:36,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 5: [2023-04-29 11:37:36,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +11: [2023-04-29 11:37:36,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +17: [2023-04-29 11:37:36,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +14: [2023-04-29 11:37:36,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +17: [2023-04-29 11:37:36,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +17: [2023-04-29 11:37:36,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 0: [2023-04-29 11:37:36,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 0: [2023-04-29 11:37:36,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 0: [2023-04-29 11:37:36,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 0: [2023-04-29 11:37:36,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +17: [2023-04-29 11:37:36,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +14: [2023-04-29 11:37:36,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +13: [2023-04-29 11:37:36,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +13: [2023-04-29 11:37:36,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +13: [2023-04-29 11:37:36,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 9: [2023-04-29 11:37:36,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +13: [2023-04-29 11:37:36,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 9: [2023-04-29 11:37:36,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 5: [2023-04-29 11:37:36,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 5: [2023-04-29 11:37:36,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +29: [2023-04-29 11:37:36,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +15: [2023-04-29 11:37:36,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +29: [2023-04-29 11:37:36,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 3: [2023-04-29 11:37:36,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +29: [2023-04-29 11:37:36,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +15: [2023-04-29 11:37:36,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +29: [2023-04-29 11:37:36,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +29: [2023-04-29 11:37:36,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +29: [2023-04-29 11:37:36,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 3: [2023-04-29 11:37:36,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 3: [2023-04-29 11:37:36,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 3: [2023-04-29 11:37:36,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +29: [2023-04-29 11:37:36,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +18: [2023-04-29 11:37:36,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +18: [2023-04-29 11:37:36,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 3: [2023-04-29 11:37:36,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +29: [2023-04-29 11:37:36,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +16: [2023-04-29 11:37:36,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. +16: [2023-04-29 11:37:36,714] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 128 +17: [2023-04-29 11:37:36,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +15: [2023-04-29 11:37:36,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 3: [2023-04-29 11:37:36,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +25: [2023-04-29 11:37:36,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +25: [2023-04-29 11:37:36,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +25: [2023-04-29 11:37:36,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 3: [2023-04-29 11:37:36,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 3: [2023-04-29 11:37:36,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +18: [2023-04-29 11:37:36,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +18: [2023-04-29 11:37:36,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +18: [2023-04-29 11:37:36,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +13: [2023-04-29 11:37:36,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +25: [2023-04-29 11:37:36,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +15: [2023-04-29 11:37:36,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +11: [2023-04-29 11:37:36,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +11: [2023-04-29 11:37:36,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +18: [2023-04-29 11:37:36,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +15: [2023-04-29 11:37:36,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +16: [2023-04-29 11:37:36,723] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 128 +16: [2023-04-29 11:37:36,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +16: [2023-04-29 11:37:36,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. +11: [2023-04-29 11:37:36,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 0: [2023-04-29 11:37:36,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +17: [2023-04-29 11:37:36,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +13: [2023-04-29 11:37:36,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +13: [2023-04-29 11:37:36,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +18: [2023-04-29 11:37:36,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +15: [2023-04-29 11:37:36,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +11: [2023-04-29 11:37:36,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 0: [2023-04-29 11:37:36,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +17: [2023-04-29 11:37:36,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +13: [2023-04-29 11:37:36,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +18: [2023-04-29 11:37:36,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 0: [2023-04-29 11:37:36,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 0: [2023-04-29 11:37:36,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +17: [2023-04-29 11:37:36,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +15: [2023-04-29 11:37:36,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +16: [2023-04-29 11:37:36,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 2: [2023-04-29 11:37:36,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 2: [2023-04-29 11:37:36,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +16: [2023-04-29 11:37:36,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_21-model_01-model_states.pt. + 2: [2023-04-29 11:37:36,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 2: [2023-04-29 11:37:36,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +15: [2023-04-29 11:37:36,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 8: [2023-04-29 11:37:36,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 8: [2023-04-29 11:37:36,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 8: [2023-04-29 11:37:36,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 8: [2023-04-29 11:37:36,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +16: [2023-04-29 11:37:36,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... + 8: [2023-04-29 11:37:36,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +16: [2023-04-29 11:37:36,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +14: [2023-04-29 11:37:36,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 2: [2023-04-29 11:37:36,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 8: [2023-04-29 11:37:36,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +14: [2023-04-29 11:37:36,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 8: [2023-04-29 11:37:36,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 2: [2023-04-29 11:37:36,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 2: [2023-04-29 11:37:36,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +14: [2023-04-29 11:37:36,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 8: [2023-04-29 11:37:36,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 2: [2023-04-29 11:37:36,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +16: [2023-04-29 11:37:36,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +16: [2023-04-29 11:37:36,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt... +14: [2023-04-29 11:37:36,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +14: [2023-04-29 11:37:36,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +14: [2023-04-29 11:37:36,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +14: [2023-04-29 11:37:36,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +14: [2023-04-29 11:37:36,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +13: [2023-04-29 11:37:36,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +17: [2023-04-29 11:37:36,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +25: [2023-04-29 11:37:36,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +13: [2023-04-29 11:37:36,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +25: [2023-04-29 11:37:36,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +31: [2023-04-29 11:37:36,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +31: [2023-04-29 11:37:36,784] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 252 +17: [2023-04-29 11:37:36,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +25: [2023-04-29 11:37:36,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +25: [2023-04-29 11:37:36,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +16: [2023-04-29 11:37:36,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. +16: [2023-04-29 11:37:36,788] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 132 +25: [2023-04-29 11:37:36,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +25: [2023-04-29 11:37:36,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +11: [2023-04-29 11:37:36,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +11: [2023-04-29 11:37:36,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +31: [2023-04-29 11:37:36,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +31: [2023-04-29 11:37:36,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +31: [2023-04-29 11:37:36,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +31: [2023-04-29 11:37:36,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +25: [2023-04-29 11:37:36,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +31: [2023-04-29 11:37:36,792] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 252 + 0: [2023-04-29 11:37:36,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +25: [2023-04-29 11:37:36,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +11: [2023-04-29 11:37:36,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +17: [2023-04-29 11:37:36,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +13: [2023-04-29 11:37:36,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +13: [2023-04-29 11:37:36,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +11: [2023-04-29 11:37:36,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +11: [2023-04-29 11:37:36,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 0: [2023-04-29 11:37:36,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 0: [2023-04-29 11:37:36,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 0: [2023-04-29 11:37:36,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +11: [2023-04-29 11:37:36,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +16: [2023-04-29 11:37:36,797] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 132 +17: [2023-04-29 11:37:36,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +13: [2023-04-29 11:37:36,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 0: [2023-04-29 11:37:36,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +11: [2023-04-29 11:37:36,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +17: [2023-04-29 11:37:36,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +17: [2023-04-29 11:37:36,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +11: [2023-04-29 11:37:36,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +13: [2023-04-29 11:37:36,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 0: [2023-04-29 11:37:36,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +13: [2023-04-29 11:37:36,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 0: [2023-04-29 11:37:36,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 0: [2023-04-29 11:37:36,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +17: [2023-04-29 11:37:36,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +13: [2023-04-29 11:37:36,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +17: [2023-04-29 11:37:36,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +26: [2023-04-29 11:37:36,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +26: [2023-04-29 11:37:36,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +26: [2023-04-29 11:37:36,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +26: [2023-04-29 11:37:36,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 2: [2023-04-29 11:37:36,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +30: [2023-04-29 11:37:36,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +30: [2023-04-29 11:37:36,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +31: [2023-04-29 11:37:36,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +30: [2023-04-29 11:37:36,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +16: [2023-04-29 11:37:36,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +30: [2023-04-29 11:37:36,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 2: [2023-04-29 11:37:36,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 2: [2023-04-29 11:37:36,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +16: [2023-04-29 11:37:36,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +31: [2023-04-29 11:37:36,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 2: [2023-04-29 11:37:36,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +31: [2023-04-29 11:37:36,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +31: [2023-04-29 11:37:36,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +16: [2023-04-29 11:37:36,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +16: [2023-04-29 11:37:36,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... + 2: [2023-04-29 11:37:36,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 2: [2023-04-29 11:37:36,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 2: [2023-04-29 11:37:36,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +16: [2023-04-29 11:37:36,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. + 2: [2023-04-29 11:37:36,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +26: [2023-04-29 11:37:36,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +26: [2023-04-29 11:37:36,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +26: [2023-04-29 11:37:36,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +16: [2023-04-29 11:37:36,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +30: [2023-04-29 11:37:36,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +16: [2023-04-29 11:37:36,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_00-model_states.pt. +26: [2023-04-29 11:37:36,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +30: [2023-04-29 11:37:36,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +30: [2023-04-29 11:37:36,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +30: [2023-04-29 11:37:36,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +21: [2023-04-29 11:37:36,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +21: [2023-04-29 11:37:36,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +21: [2023-04-29 11:37:36,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +21: [2023-04-29 11:37:36,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +16: [2023-04-29 11:37:36,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt... +16: [2023-04-29 11:37:36,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. +16: [2023-04-29 11:37:36,853] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 134 +28: [2023-04-29 11:37:36,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +28: [2023-04-29 11:37:36,862] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 226 +16: [2023-04-29 11:37:36,862] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 134 +23: [2023-04-29 11:37:36,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +23: [2023-04-29 11:37:36,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +23: [2023-04-29 11:37:36,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +23: [2023-04-29 11:37:36,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +28: [2023-04-29 11:37:36,870] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 226 +21: [2023-04-29 11:37:36,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 7: [2023-04-29 11:37:36,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 7: [2023-04-29 11:37:36,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 7: [2023-04-29 11:37:36,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 7: [2023-04-29 11:37:36,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +21: [2023-04-29 11:37:36,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +21: [2023-04-29 11:37:36,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +21: [2023-04-29 11:37:36,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 4: [2023-04-29 11:37:36,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 4: [2023-04-29 11:37:36,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 4: [2023-04-29 11:37:36,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 4: [2023-04-29 11:37:36,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +31: [2023-04-29 11:37:36,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +12: [2023-04-29 11:37:36,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +12: [2023-04-29 11:37:36,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +12: [2023-04-29 11:37:36,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +12: [2023-04-29 11:37:36,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +31: [2023-04-29 11:37:36,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +31: [2023-04-29 11:37:36,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +31: [2023-04-29 11:37:36,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +31: [2023-04-29 11:37:36,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 7: [2023-04-29 11:37:36,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +23: [2023-04-29 11:37:36,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +23: [2023-04-29 11:37:36,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +26: [2023-04-29 11:37:36,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +31: [2023-04-29 11:37:36,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +23: [2023-04-29 11:37:36,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 7: [2023-04-29 11:37:36,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +23: [2023-04-29 11:37:36,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +30: [2023-04-29 11:37:36,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 7: [2023-04-29 11:37:36,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +31: [2023-04-29 11:37:36,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +26: [2023-04-29 11:37:36,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +26: [2023-04-29 11:37:36,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +30: [2023-04-29 11:37:36,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +31: [2023-04-29 11:37:36,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +26: [2023-04-29 11:37:36,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 7: [2023-04-29 11:37:36,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +26: [2023-04-29 11:37:36,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +26: [2023-04-29 11:37:36,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +26: [2023-04-29 11:37:36,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +26: [2023-04-29 11:37:36,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +30: [2023-04-29 11:37:36,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +30: [2023-04-29 11:37:36,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +30: [2023-04-29 11:37:36,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +12: [2023-04-29 11:37:36,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +30: [2023-04-29 11:37:36,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +30: [2023-04-29 11:37:36,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +30: [2023-04-29 11:37:36,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +19: [2023-04-29 11:37:36,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +19: [2023-04-29 11:37:36,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +19: [2023-04-29 11:37:36,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +19: [2023-04-29 11:37:36,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +12: [2023-04-29 11:37:36,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +36: [2023-04-29 11:37:36,931] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 295 +12: [2023-04-29 11:37:36,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +36: [2023-04-29 11:37:36,932] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 289 +21: [2023-04-29 11:37:36,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +12: [2023-04-29 11:37:36,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +20: [2023-04-29 11:37:36,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +20: [2023-04-29 11:37:36,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +36: [2023-04-29 11:37:36,936] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 291 +20: [2023-04-29 11:37:36,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +20: [2023-04-29 11:37:36,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +21: [2023-04-29 11:37:36,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +36: [2023-04-29 11:37:36,939] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 293 +21: [2023-04-29 11:37:36,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +21: [2023-04-29 11:37:36,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 4: [2023-04-29 11:37:36,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt... + 4: [2023-04-29 11:37:36,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt... + 4: [2023-04-29 11:37:36,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt... + 4: [2023-04-29 11:37:36,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt... +21: [2023-04-29 11:37:36,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +21: [2023-04-29 11:37:36,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +19: [2023-04-29 11:37:36,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +22: [2023-04-29 11:37:36,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +22: [2023-04-29 11:37:36,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +22: [2023-04-29 11:37:36,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 6: [2023-04-29 11:37:36,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 6: [2023-04-29 11:37:36,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +22: [2023-04-29 11:37:36,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 1: [2023-04-29 11:37:36,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 1: [2023-04-29 11:37:36,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 1: [2023-04-29 11:37:36,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 1: [2023-04-29 11:37:36,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 6: [2023-04-29 11:37:36,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 6: [2023-04-29 11:37:36,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +19: [2023-04-29 11:37:36,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 7: [2023-04-29 11:37:36,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +28: [2023-04-29 11:37:36,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +19: [2023-04-29 11:37:36,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +28: [2023-04-29 11:37:36,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +23: [2023-04-29 11:37:36,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +28: [2023-04-29 11:37:36,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +28: [2023-04-29 11:37:36,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +21: [2023-04-29 11:37:36,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +21: [2023-04-29 11:37:36,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +19: [2023-04-29 11:37:36,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 7: [2023-04-29 11:37:36,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +23: [2023-04-29 11:37:36,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +24: [2023-04-29 11:37:36,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +24: [2023-04-29 11:37:36,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +23: [2023-04-29 11:37:36,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +24: [2023-04-29 11:37:36,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +19: [2023-04-29 11:37:36,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. +24: [2023-04-29 11:37:36,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +19: [2023-04-29 11:37:36,969] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 158 +23: [2023-04-29 11:37:36,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 7: [2023-04-29 11:37:36,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 7: [2023-04-29 11:37:36,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +23: [2023-04-29 11:37:36,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +23: [2023-04-29 11:37:36,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +19: [2023-04-29 11:37:36,976] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 158 + 7: [2023-04-29 11:37:36,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 7: [2023-04-29 11:37:36,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 7: [2023-04-29 11:37:36,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +10: [2023-04-29 11:37:36,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +10: [2023-04-29 11:37:36,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +10: [2023-04-29 11:37:36,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +10: [2023-04-29 11:37:36,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +22: [2023-04-29 11:37:36,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +23: [2023-04-29 11:37:36,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +23: [2023-04-29 11:37:36,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 7: [2023-04-29 11:37:36,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +12: [2023-04-29 11:37:36,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +52: [2023-04-29 11:37:36,984] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 417 + 1: [2023-04-29 11:37:36,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +52: [2023-04-29 11:37:36,987] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 421 + 1: [2023-04-29 11:37:36,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 1: [2023-04-29 11:37:36,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +15: [2023-04-29 11:37:36,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +15: [2023-04-29 11:37:36,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +15: [2023-04-29 11:37:36,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +15: [2023-04-29 11:37:36,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 1: [2023-04-29 11:37:36,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +12: [2023-04-29 11:37:36,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +18: [2023-04-29 11:37:36,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +18: [2023-04-29 11:37:36,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +18: [2023-04-29 11:37:36,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +18: [2023-04-29 11:37:36,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +12: [2023-04-29 11:37:36,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +28: [2023-04-29 11:37:36,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +28: [2023-04-29 11:37:36,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +28: [2023-04-29 11:37:36,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +52: [2023-04-29 11:37:36,991] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 423 +22: [2023-04-29 11:37:36,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 6: [2023-04-29 11:37:36,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 6: [2023-04-29 11:37:36,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +52: [2023-04-29 11:37:36,993] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 419 +28: [2023-04-29 11:37:36,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 6: [2023-04-29 11:37:36,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +22: [2023-04-29 11:37:36,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +12: [2023-04-29 11:37:36,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +24: [2023-04-29 11:37:36,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +22: [2023-04-29 11:37:36,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 6: [2023-04-29 11:37:36,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +12: [2023-04-29 11:37:36,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +24: [2023-04-29 11:37:36,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +12: [2023-04-29 11:37:36,998] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +24: [2023-04-29 11:37:36,999] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +24: [2023-04-29 11:37:36,999] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +12: [2023-04-29 11:37:37,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +13: [2023-04-29 11:37:37,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +10: [2023-04-29 11:37:37,004] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +12: [2023-04-29 11:37:37,004] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +13: [2023-04-29 11:37:37,004] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 110 + 6: [2023-04-29 11:37:37,006] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 6: [2023-04-29 11:37:37,006] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 50 +10: [2023-04-29 11:37:37,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +27: [2023-04-29 11:37:37,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +27: [2023-04-29 11:37:37,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +27: [2023-04-29 11:37:37,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +27: [2023-04-29 11:37:37,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +10: [2023-04-29 11:37:37,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +20: [2023-04-29 11:37:37,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt... +20: [2023-04-29 11:37:37,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt... +20: [2023-04-29 11:37:37,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt... +20: [2023-04-29 11:37:37,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt... +10: [2023-04-29 11:37:37,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +18: [2023-04-29 11:37:37,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +13: [2023-04-29 11:37:37,013] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 110 + 6: [2023-04-29 11:37:37,014] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 50 +18: [2023-04-29 11:37:37,016] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 9: [2023-04-29 11:37:37,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 9: [2023-04-29 11:37:37,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 9: [2023-04-29 11:37:37,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 9: [2023-04-29 11:37:37,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +18: [2023-04-29 11:37:37,019] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +18: [2023-04-29 11:37:37,019] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +15: [2023-04-29 11:37:37,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +15: [2023-04-29 11:37:37,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +15: [2023-04-29 11:37:37,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +15: [2023-04-29 11:37:37,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +19: [2023-04-29 11:37:37,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +29: [2023-04-29 11:37:37,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +29: [2023-04-29 11:37:37,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +29: [2023-04-29 11:37:37,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +29: [2023-04-29 11:37:37,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +19: [2023-04-29 11:37:37,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +19: [2023-04-29 11:37:37,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +27: [2023-04-29 11:37:37,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +19: [2023-04-29 11:37:37,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +27: [2023-04-29 11:37:37,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +19: [2023-04-29 11:37:37,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +27: [2023-04-29 11:37:37,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +27: [2023-04-29 11:37:37,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +19: [2023-04-29 11:37:37,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 1: [2023-04-29 11:37:37,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 5: [2023-04-29 11:37:37,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 5: [2023-04-29 11:37:37,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 5: [2023-04-29 11:37:37,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 5: [2023-04-29 11:37:37,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +19: [2023-04-29 11:37:37,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +22: [2023-04-29 11:37:37,044] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +19: [2023-04-29 11:37:37,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 1: [2023-04-29 11:37:37,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +22: [2023-04-29 11:37:37,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 3: [2023-04-29 11:37:37,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 3: [2023-04-29 11:37:37,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 3: [2023-04-29 11:37:37,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 3: [2023-04-29 11:37:37,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. + 9: [2023-04-29 11:37:37,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 9: [2023-04-29 11:37:37,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 9: [2023-04-29 11:37:37,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +28: [2023-04-29 11:37:37,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 9: [2023-04-29 11:37:37,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 1: [2023-04-29 11:37:37,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 1: [2023-04-29 11:37:37,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 1: [2023-04-29 11:37:37,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 8: [2023-04-29 11:37:37,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 8: [2023-04-29 11:37:37,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 8: [2023-04-29 11:37:37,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 8: [2023-04-29 11:37:37,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 6: [2023-04-29 11:37:37,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +24: [2023-04-29 11:37:37,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +10: [2023-04-29 11:37:37,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +22: [2023-04-29 11:37:37,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +29: [2023-04-29 11:37:37,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +29: [2023-04-29 11:37:37,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 1: [2023-04-29 11:37:37,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +10: [2023-04-29 11:37:37,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +28: [2023-04-29 11:37:37,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 1: [2023-04-29 11:37:37,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 1: [2023-04-29 11:37:37,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +24: [2023-04-29 11:37:37,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 6: [2023-04-29 11:37:37,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +29: [2023-04-29 11:37:37,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +29: [2023-04-29 11:37:37,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +22: [2023-04-29 11:37:37,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 6: [2023-04-29 11:37:37,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 6: [2023-04-29 11:37:37,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +28: [2023-04-29 11:37:37,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +28: [2023-04-29 11:37:37,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +28: [2023-04-29 11:37:37,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +22: [2023-04-29 11:37:37,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +22: [2023-04-29 11:37:37,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +24: [2023-04-29 11:37:37,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +24: [2023-04-29 11:37:37,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +24: [2023-04-29 11:37:37,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +10: [2023-04-29 11:37:37,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +22: [2023-04-29 11:37:37,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +18: [2023-04-29 11:37:37,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +28: [2023-04-29 11:37:37,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 5: [2023-04-29 11:37:37,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 6: [2023-04-29 11:37:37,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +28: [2023-04-29 11:37:37,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 6: [2023-04-29 11:37:37,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +28: [2023-04-29 11:37:37,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +22: [2023-04-29 11:37:37,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +10: [2023-04-29 11:37:37,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 6: [2023-04-29 11:37:37,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +24: [2023-04-29 11:37:37,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 5: [2023-04-29 11:37:37,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 5: [2023-04-29 11:37:37,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 5: [2023-04-29 11:37:37,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +18: [2023-04-29 11:37:37,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +24: [2023-04-29 11:37:37,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +24: [2023-04-29 11:37:37,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 3: [2023-04-29 11:37:37,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 6: [2023-04-29 11:37:37,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +10: [2023-04-29 11:37:37,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +10: [2023-04-29 11:37:37,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 3: [2023-04-29 11:37:37,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 3: [2023-04-29 11:37:37,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... + 3: [2023-04-29 11:37:37,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +18: [2023-04-29 11:37:37,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +18: [2023-04-29 11:37:37,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +16: [2023-04-29 11:37:37,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +16: [2023-04-29 11:37:37,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +10: [2023-04-29 11:37:37,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +18: [2023-04-29 11:37:37,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +18: [2023-04-29 11:37:37,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +10: [2023-04-29 11:37:37,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +15: [2023-04-29 11:37:37,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +15: [2023-04-29 11:37:37,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +16: [2023-04-29 11:37:37,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +15: [2023-04-29 11:37:37,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +18: [2023-04-29 11:37:37,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +16: [2023-04-29 11:37:37,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_22-model_01-model_states.pt. +15: [2023-04-29 11:37:37,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +15: [2023-04-29 11:37:37,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +15: [2023-04-29 11:37:37,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +15: [2023-04-29 11:37:37,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +18: [2023-04-29 11:37:37,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +15: [2023-04-29 11:37:37,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +27: [2023-04-29 11:37:37,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +40: [2023-04-29 11:37:37,101] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 321 +27: [2023-04-29 11:37:37,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +27: [2023-04-29 11:37:37,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +27: [2023-04-29 11:37:37,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +27: [2023-04-29 11:37:37,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +40: [2023-04-29 11:37:37,110] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 325 +40: [2023-04-29 11:37:37,111] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 323 +27: [2023-04-29 11:37:37,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +27: [2023-04-29 11:37:37,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +27: [2023-04-29 11:37:37,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +17: [2023-04-29 11:37:37,112] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +16: [2023-04-29 11:37:37,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +16: [2023-04-29 11:37:37,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +17: [2023-04-29 11:37:37,112] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +17: [2023-04-29 11:37:37,112] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +17: [2023-04-29 11:37:37,112] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +40: [2023-04-29 11:37:37,117] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 327 + 9: [2023-04-29 11:37:37,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 9: [2023-04-29 11:37:37,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 9: [2023-04-29 11:37:37,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +29: [2023-04-29 11:37:37,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 9: [2023-04-29 11:37:37,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +16: [2023-04-29 11:37:37,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +29: [2023-04-29 11:37:37,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +16: [2023-04-29 11:37:37,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt... +29: [2023-04-29 11:37:37,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 9: [2023-04-29 11:37:37,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 9: [2023-04-29 11:37:37,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 9: [2023-04-29 11:37:37,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +13: [2023-04-29 11:37:37,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +13: [2023-04-29 11:37:37,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +13: [2023-04-29 11:37:37,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +13: [2023-04-29 11:37:37,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 8: [2023-04-29 11:37:37,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt... + 8: [2023-04-29 11:37:37,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt... + 8: [2023-04-29 11:37:37,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt... + 8: [2023-04-29 11:37:37,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt... + 9: [2023-04-29 11:37:37,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +29: [2023-04-29 11:37:37,133] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +11: [2023-04-29 11:37:37,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +11: [2023-04-29 11:37:37,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +11: [2023-04-29 11:37:37,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +11: [2023-04-29 11:37:37,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 5: [2023-04-29 11:37:37,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 3: [2023-04-29 11:37:37,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +29: [2023-04-29 11:37:37,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +29: [2023-04-29 11:37:37,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 3: [2023-04-29 11:37:37,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 5: [2023-04-29 11:37:37,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 5: [2023-04-29 11:37:37,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 3: [2023-04-29 11:37:37,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 3: [2023-04-29 11:37:37,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +29: [2023-04-29 11:37:37,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 5: [2023-04-29 11:37:37,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 5: [2023-04-29 11:37:37,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +29: [2023-04-29 11:37:37,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 3: [2023-04-29 11:37:37,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. + 3: [2023-04-29 11:37:37,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 3: [2023-04-29 11:37:37,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 5: [2023-04-29 11:37:37,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 5: [2023-04-29 11:37:37,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 5: [2023-04-29 11:37:37,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +49: [2023-04-29 11:37:37,154] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 399 + 3: [2023-04-29 11:37:37,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... + 0: [2023-04-29 11:37:37,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 0: [2023-04-29 11:37:37,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 0: [2023-04-29 11:37:37,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 0: [2023-04-29 11:37:37,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +49: [2023-04-29 11:37:37,163] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 395 +49: [2023-04-29 11:37:37,163] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 393 +49: [2023-04-29 11:37:37,166] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 397 +45: [2023-04-29 11:37:37,169] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 365 +17: [2023-04-29 11:37:37,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt... +17: [2023-04-29 11:37:37,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt... +17: [2023-04-29 11:37:37,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt... +17: [2023-04-29 11:37:37,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt... +45: [2023-04-29 11:37:37,177] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 367 +45: [2023-04-29 11:37:37,177] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 361 +43: [2023-04-29 11:37:37,179] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 349 +43: [2023-04-29 11:37:37,179] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 351 +45: [2023-04-29 11:37:37,179] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 363 +43: [2023-04-29 11:37:37,180] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 345 +16: [2023-04-29 11:37:37,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +16: [2023-04-29 11:37:37,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +43: [2023-04-29 11:37:37,183] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 347 +16: [2023-04-29 11:37:37,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +16: [2023-04-29 11:37:37,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +16: [2023-04-29 11:37:37,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +13: [2023-04-29 11:37:37,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt... +13: [2023-04-29 11:37:37,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt... +13: [2023-04-29 11:37:37,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt... +13: [2023-04-29 11:37:37,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt... +16: [2023-04-29 11:37:37,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +16: [2023-04-29 11:37:37,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_00-model_states.pt. +11: [2023-04-29 11:37:37,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt... +11: [2023-04-29 11:37:37,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt... +11: [2023-04-29 11:37:37,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt... +11: [2023-04-29 11:37:37,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt... +16: [2023-04-29 11:37:37,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt... +32: [2023-04-29 11:37:37,204] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 257 +32: [2023-04-29 11:37:37,210] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 259 +32: [2023-04-29 11:37:37,212] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 261 +32: [2023-04-29 11:37:37,215] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 263 + 2: [2023-04-29 11:37:37,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 2: [2023-04-29 11:37:37,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 2: [2023-04-29 11:37:37,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 2: [2023-04-29 11:37:37,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 0: [2023-04-29 11:37:37,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt... + 0: [2023-04-29 11:37:37,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt... + 0: [2023-04-29 11:37:37,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt... + 0: [2023-04-29 11:37:37,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt... +34: [2023-04-29 11:37:37,267] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 279 +34: [2023-04-29 11:37:37,271] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 275 +34: [2023-04-29 11:37:37,271] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 273 +14: [2023-04-29 11:37:37,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +14: [2023-04-29 11:37:37,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +14: [2023-04-29 11:37:37,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +34: [2023-04-29 11:37:37,273] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 277 +14: [2023-04-29 11:37:37,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 2: [2023-04-29 11:37:37,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt... + 2: [2023-04-29 11:37:37,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt... + 2: [2023-04-29 11:37:37,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt... + 2: [2023-04-29 11:37:37,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt... +30: [2023-04-29 11:37:37,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +30: [2023-04-29 11:37:37,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +25: [2023-04-29 11:37:37,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +25: [2023-04-29 11:37:37,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +25: [2023-04-29 11:37:37,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +25: [2023-04-29 11:37:37,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +30: [2023-04-29 11:37:37,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +30: [2023-04-29 11:37:37,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +46: [2023-04-29 11:37:37,314] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 369 +46: [2023-04-29 11:37:37,321] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 371 + 7: [2023-04-29 11:37:37,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 7: [2023-04-29 11:37:37,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 7: [2023-04-29 11:37:37,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 7: [2023-04-29 11:37:37,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +46: [2023-04-29 11:37:37,323] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 373 + 4: [2023-04-29 11:37:37,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt. + 4: [2023-04-29 11:37:37,324] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 35 +46: [2023-04-29 11:37:37,325] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 375 +57: [2023-04-29 11:37:37,329] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 457 +62: [2023-04-29 11:37:37,330] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 497 +62: [2023-04-29 11:37:37,330] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 499 +57: [2023-04-29 11:37:37,331] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 461 + 4: [2023-04-29 11:37:37,332] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 35 +62: [2023-04-29 11:37:37,333] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 503 +57: [2023-04-29 11:37:37,335] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 463 +62: [2023-04-29 11:37:37,335] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 501 +57: [2023-04-29 11:37:37,337] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 459 +14: [2023-04-29 11:37:37,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt... +14: [2023-04-29 11:37:37,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt... +14: [2023-04-29 11:37:37,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt... +14: [2023-04-29 11:37:37,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt... + 4: [2023-04-29 11:37:37,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt. + 4: [2023-04-29 11:37:37,346] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 37 +25: [2023-04-29 11:37:37,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt... +25: [2023-04-29 11:37:37,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt... +25: [2023-04-29 11:37:37,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt... +25: [2023-04-29 11:37:37,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt... + 4: [2023-04-29 11:37:37,354] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 37 +30: [2023-04-29 11:37:37,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt... +30: [2023-04-29 11:37:37,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt... +30: [2023-04-29 11:37:37,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt... +30: [2023-04-29 11:37:37,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt... + 4: [2023-04-29 11:37:37,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt. + 4: [2023-04-29 11:37:37,362] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 33 +39: [2023-04-29 11:37:37,365] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 317 +21: [2023-04-29 11:37:37,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +21: [2023-04-29 11:37:37,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +21: [2023-04-29 11:37:37,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 4: [2023-04-29 11:37:37,368] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 33 +21: [2023-04-29 11:37:37,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +39: [2023-04-29 11:37:37,370] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 319 +39: [2023-04-29 11:37:37,373] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 313 +39: [2023-04-29 11:37:37,374] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 315 + 7: [2023-04-29 11:37:37,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt... + 7: [2023-04-29 11:37:37,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt... + 7: [2023-04-29 11:37:37,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt... + 7: [2023-04-29 11:37:37,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt... +20: [2023-04-29 11:37:37,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt. +20: [2023-04-29 11:37:37,384] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 167 +20: [2023-04-29 11:37:37,392] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 167 +28: [2023-04-29 11:37:37,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +28: [2023-04-29 11:37:37,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +28: [2023-04-29 11:37:37,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +28: [2023-04-29 11:37:37,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 1: [2023-04-29 11:37:37,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 1: [2023-04-29 11:37:37,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 1: [2023-04-29 11:37:37,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 1: [2023-04-29 11:37:37,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +31: [2023-04-29 11:37:37,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +31: [2023-04-29 11:37:37,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +31: [2023-04-29 11:37:37,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +31: [2023-04-29 11:37:37,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +15: [2023-04-29 11:37:37,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +15: [2023-04-29 11:37:37,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +15: [2023-04-29 11:37:37,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +15: [2023-04-29 11:37:37,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 4: [2023-04-29 11:37:37,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt. + 4: [2023-04-29 11:37:37,401] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 39 + 4: [2023-04-29 11:37:37,407] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 39 +20: [2023-04-29 11:37:37,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt. +20: [2023-04-29 11:37:37,409] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 161 +53: [2023-04-29 11:37:37,410] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 431 +20: [2023-04-29 11:37:37,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt. +20: [2023-04-29 11:37:37,415] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 165 + 6: [2023-04-29 11:37:37,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 6: [2023-04-29 11:37:37,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +20: [2023-04-29 11:37:37,416] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 161 + 6: [2023-04-29 11:37:37,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 6: [2023-04-29 11:37:37,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +53: [2023-04-29 11:37:37,419] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 427 +53: [2023-04-29 11:37:37,422] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 425 +20: [2023-04-29 11:37:37,422] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 165 +53: [2023-04-29 11:37:37,427] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 429 +19: [2023-04-29 11:37:37,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +19: [2023-04-29 11:37:37,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +19: [2023-04-29 11:37:37,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +19: [2023-04-29 11:37:37,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +33: [2023-04-29 11:37:37,438] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 265 +22: [2023-04-29 11:37:37,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +22: [2023-04-29 11:37:37,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +22: [2023-04-29 11:37:37,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +22: [2023-04-29 11:37:37,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +21: [2023-04-29 11:37:37,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt... +21: [2023-04-29 11:37:37,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt... +21: [2023-04-29 11:37:37,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt... +21: [2023-04-29 11:37:37,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt... +60: [2023-04-29 11:37:37,444] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 481 +60: [2023-04-29 11:37:37,444] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 485 +60: [2023-04-29 11:37:37,444] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 487 +60: [2023-04-29 11:37:37,445] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 483 +63: [2023-04-29 11:37:37,446] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 505 +63: [2023-04-29 11:37:37,446] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 507 +33: [2023-04-29 11:37:37,446] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 269 +47: [2023-04-29 11:37:37,447] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 381 +47: [2023-04-29 11:37:37,447] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 377 +63: [2023-04-29 11:37:37,447] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 509 +63: [2023-04-29 11:37:37,448] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 511 +33: [2023-04-29 11:37:37,448] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 267 +47: [2023-04-29 11:37:37,450] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 383 +47: [2023-04-29 11:37:37,450] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 379 +18: [2023-04-29 11:37:37,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +18: [2023-04-29 11:37:37,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +18: [2023-04-29 11:37:37,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +18: [2023-04-29 11:37:37,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +33: [2023-04-29 11:37:37,458] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 271 + 1: [2023-04-29 11:37:37,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt... +24: [2023-04-29 11:37:37,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 1: [2023-04-29 11:37:37,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt... + 1: [2023-04-29 11:37:37,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt... + 1: [2023-04-29 11:37:37,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt... +28: [2023-04-29 11:37:37,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt... +28: [2023-04-29 11:37:37,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt... +28: [2023-04-29 11:37:37,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt... +28: [2023-04-29 11:37:37,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt... +24: [2023-04-29 11:37:37,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +24: [2023-04-29 11:37:37,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +24: [2023-04-29 11:37:37,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +38: [2023-04-29 11:37:37,467] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 309 +38: [2023-04-29 11:37:37,469] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 307 +38: [2023-04-29 11:37:37,469] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 311 +38: [2023-04-29 11:37:37,470] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 305 +31: [2023-04-29 11:37:37,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt... +31: [2023-04-29 11:37:37,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt... +31: [2023-04-29 11:37:37,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt... +31: [2023-04-29 11:37:37,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt... + 8: [2023-04-29 11:37:37,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt. + 8: [2023-04-29 11:37:37,471] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 69 +15: [2023-04-29 11:37:37,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt... +15: [2023-04-29 11:37:37,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt... +15: [2023-04-29 11:37:37,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt... +15: [2023-04-29 11:37:37,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt... + 8: [2023-04-29 11:37:37,480] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 69 +51: [2023-04-29 11:37:37,480] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 415 +54: [2023-04-29 11:37:37,484] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 435 +54: [2023-04-29 11:37:37,486] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 437 +51: [2023-04-29 11:37:37,487] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 413 + 6: [2023-04-29 11:37:37,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt... + 6: [2023-04-29 11:37:37,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt... + 6: [2023-04-29 11:37:37,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt... + 6: [2023-04-29 11:37:37,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt... +54: [2023-04-29 11:37:37,489] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 439 +51: [2023-04-29 11:37:37,491] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 411 +54: [2023-04-29 11:37:37,491] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 433 +51: [2023-04-29 11:37:37,491] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 409 +50: [2023-04-29 11:37:37,499] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 401 +50: [2023-04-29 11:37:37,502] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 403 +19: [2023-04-29 11:37:37,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt... +19: [2023-04-29 11:37:37,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt... +19: [2023-04-29 11:37:37,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt... +19: [2023-04-29 11:37:37,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt... +22: [2023-04-29 11:37:37,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt... +22: [2023-04-29 11:37:37,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt... +22: [2023-04-29 11:37:37,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt... +22: [2023-04-29 11:37:37,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt... +50: [2023-04-29 11:37:37,504] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 407 +50: [2023-04-29 11:37:37,510] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 405 +27: [2023-04-29 11:37:37,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +27: [2023-04-29 11:37:37,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +27: [2023-04-29 11:37:37,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +27: [2023-04-29 11:37:37,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +56: [2023-04-29 11:37:37,512] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 451 +56: [2023-04-29 11:37:37,512] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 449 +56: [2023-04-29 11:37:37,513] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 453 +56: [2023-04-29 11:37:37,515] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 455 +26: [2023-04-29 11:37:37,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +26: [2023-04-29 11:37:37,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +26: [2023-04-29 11:37:37,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +26: [2023-04-29 11:37:37,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +12: [2023-04-29 11:37:37,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +12: [2023-04-29 11:37:37,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +18: [2023-04-29 11:37:37,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt... +18: [2023-04-29 11:37:37,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt... +18: [2023-04-29 11:37:37,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt... +18: [2023-04-29 11:37:37,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt... +12: [2023-04-29 11:37:37,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +12: [2023-04-29 11:37:37,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +11: [2023-04-29 11:37:37,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt. +11: [2023-04-29 11:37:37,522] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 91 +24: [2023-04-29 11:37:37,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt... +24: [2023-04-29 11:37:37,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt... +24: [2023-04-29 11:37:37,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt... +24: [2023-04-29 11:37:37,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt... + 5: [2023-04-29 11:37:37,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 5: [2023-04-29 11:37:37,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 5: [2023-04-29 11:37:37,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 9: [2023-04-29 11:37:37,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 9: [2023-04-29 11:37:37,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 9: [2023-04-29 11:37:37,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 5: [2023-04-29 11:37:37,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 9: [2023-04-29 11:37:37,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +11: [2023-04-29 11:37:37,530] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 91 +23: [2023-04-29 11:37:37,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +23: [2023-04-29 11:37:37,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +23: [2023-04-29 11:37:37,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +23: [2023-04-29 11:37:37,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 3: [2023-04-29 11:37:37,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 3: [2023-04-29 11:37:37,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 3: [2023-04-29 11:37:37,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +29: [2023-04-29 11:37:37,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +29: [2023-04-29 11:37:37,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +29: [2023-04-29 11:37:37,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 3: [2023-04-29 11:37:37,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +29: [2023-04-29 11:37:37,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +10: [2023-04-29 11:37:37,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +10: [2023-04-29 11:37:37,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +10: [2023-04-29 11:37:37,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +10: [2023-04-29 11:37:37,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. + 8: [2023-04-29 11:37:37,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt. + 8: [2023-04-29 11:37:37,548] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 67 + 8: [2023-04-29 11:37:37,556] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 67 +59: [2023-04-29 11:37:37,556] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 477 +59: [2023-04-29 11:37:37,557] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 473 +59: [2023-04-29 11:37:37,558] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 475 +58: [2023-04-29 11:37:37,561] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 471 +59: [2023-04-29 11:37:37,562] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 479 +58: [2023-04-29 11:37:37,565] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 465 +44: [2023-04-29 11:37:37,567] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 355 +17: [2023-04-29 11:37:37,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt. +16: [2023-04-29 11:37:37,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +16: [2023-04-29 11:37:37,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +17: [2023-04-29 11:37:37,564] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 143 +16: [2023-04-29 11:37:37,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +17: [2023-04-29 11:37:37,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt. +16: [2023-04-29 11:37:37,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/layer_23-model_01-model_states.pt. +17: [2023-04-29 11:37:37,567] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 139 +44: [2023-04-29 11:37:37,569] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 353 +58: [2023-04-29 11:37:37,570] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 467 +17: [2023-04-29 11:37:37,571] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 143 +44: [2023-04-29 11:37:37,571] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 357 +44: [2023-04-29 11:37:37,571] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 359 +58: [2023-04-29 11:37:37,571] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 469 +37: [2023-04-29 11:37:37,572] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 297 +13: [2023-04-29 11:37:37,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt. +13: [2023-04-29 11:37:37,572] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 107 +17: [2023-04-29 11:37:37,574] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 139 +37: [2023-04-29 11:37:37,575] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 303 +37: [2023-04-29 11:37:37,576] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 301 +37: [2023-04-29 11:37:37,576] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 299 +41: [2023-04-29 11:37:37,577] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 329 +11: [2023-04-29 11:37:37,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt. +11: [2023-04-29 11:37:37,578] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 93 +55: [2023-04-29 11:37:37,579] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 443 +41: [2023-04-29 11:37:37,580] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 333 +13: [2023-04-29 11:37:37,580] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 107 +27: [2023-04-29 11:37:37,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt... +27: [2023-04-29 11:37:37,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt... +27: [2023-04-29 11:37:37,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt... +27: [2023-04-29 11:37:37,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt... +41: [2023-04-29 11:37:37,582] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 335 +55: [2023-04-29 11:37:37,582] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 445 +41: [2023-04-29 11:37:37,583] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 331 + 8: [2023-04-29 11:37:37,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt. + 8: [2023-04-29 11:37:37,584] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 65 +11: [2023-04-29 11:37:37,585] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 93 +17: [2023-04-29 11:37:37,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt. +17: [2023-04-29 11:37:37,584] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 141 +55: [2023-04-29 11:37:37,586] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 441 +35: [2023-04-29 11:37:37,589] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 287 +61: [2023-04-29 11:37:37,589] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 495 +42: [2023-04-29 11:37:37,589] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 337 +42: [2023-04-29 11:37:37,589] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 343 +55: [2023-04-29 11:37:37,590] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 447 + 8: [2023-04-29 11:37:37,590] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 65 +35: [2023-04-29 11:37:37,590] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 281 +17: [2023-04-29 11:37:37,591] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 141 +12: [2023-04-29 11:37:37,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt... +12: [2023-04-29 11:37:37,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt... +12: [2023-04-29 11:37:37,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt... +12: [2023-04-29 11:37:37,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt... +61: [2023-04-29 11:37:37,592] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 491 +61: [2023-04-29 11:37:37,592] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 489 +26: [2023-04-29 11:37:37,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt... +26: [2023-04-29 11:37:37,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt... +26: [2023-04-29 11:37:37,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt... +26: [2023-04-29 11:37:37,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt... +35: [2023-04-29 11:37:37,594] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 285 +61: [2023-04-29 11:37:37,595] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 493 +42: [2023-04-29 11:37:37,596] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 339 +35: [2023-04-29 11:37:37,596] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 283 +11: [2023-04-29 11:37:37,597] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt. +11: [2023-04-29 11:37:37,598] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 95 +42: [2023-04-29 11:37:37,598] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 341 + 5: [2023-04-29 11:37:37,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt... + 5: [2023-04-29 11:37:37,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt... + 5: [2023-04-29 11:37:37,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt... + 5: [2023-04-29 11:37:37,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt... + 9: [2023-04-29 11:37:37,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt... + 9: [2023-04-29 11:37:37,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt... + 9: [2023-04-29 11:37:37,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt... + 9: [2023-04-29 11:37:37,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt... +23: [2023-04-29 11:37:37,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt... +23: [2023-04-29 11:37:37,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt... +23: [2023-04-29 11:37:37,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt... +23: [2023-04-29 11:37:37,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt... +11: [2023-04-29 11:37:37,605] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 95 +10: [2023-04-29 11:37:37,609] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt... +10: [2023-04-29 11:37:37,609] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt... +10: [2023-04-29 11:37:37,609] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt... +10: [2023-04-29 11:37:37,609] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt... +48: [2023-04-29 11:37:37,610] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 391 + 8: [2023-04-29 11:37:37,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt. + 8: [2023-04-29 11:37:37,614] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 71 +13: [2023-04-29 11:37:37,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt. +13: [2023-04-29 11:37:37,614] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 111 +48: [2023-04-29 11:37:37,614] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 387 + 3: [2023-04-29 11:37:37,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt... + 3: [2023-04-29 11:37:37,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt... + 3: [2023-04-29 11:37:37,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt... + 3: [2023-04-29 11:37:37,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt... +29: [2023-04-29 11:37:37,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt... +29: [2023-04-29 11:37:37,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt... +29: [2023-04-29 11:37:37,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt... +29: [2023-04-29 11:37:37,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt... + 8: [2023-04-29 11:37:37,622] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 71 +13: [2023-04-29 11:37:37,623] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 111 +48: [2023-04-29 11:37:37,625] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 389 +48: [2023-04-29 11:37:37,628] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 385 +16: [2023-04-29 11:37:37,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt... +16: [2023-04-29 11:37:37,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt... +16: [2023-04-29 11:37:37,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt... +16: [2023-04-29 11:37:37,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt... +17: [2023-04-29 11:37:37,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt. +17: [2023-04-29 11:37:37,636] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 137 + 0: [2023-04-29 11:37:37,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt. + 0: [2023-04-29 11:37:37,637] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 3 +13: [2023-04-29 11:37:37,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt. +13: [2023-04-29 11:37:37,641] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 109 +17: [2023-04-29 11:37:37,645] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 137 + 0: [2023-04-29 11:37:37,646] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 3 +13: [2023-04-29 11:37:37,648] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 109 +13: [2023-04-29 11:37:37,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt. +13: [2023-04-29 11:37:37,655] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 105 + 0: [2023-04-29 11:37:37,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt. + 2: [2023-04-29 11:37:37,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt. + 0: [2023-04-29 11:37:37,662] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 7 + 2: [2023-04-29 11:37:37,662] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 23 +13: [2023-04-29 11:37:37,665] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 105 + 2: [2023-04-29 11:37:37,669] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 23 + 0: [2023-04-29 11:37:37,671] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 7 + 2: [2023-04-29 11:37:37,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt. + 2: [2023-04-29 11:37:37,697] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 17 + 2: [2023-04-29 11:37:37,704] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 17 +14: [2023-04-29 11:37:37,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt. +14: [2023-04-29 11:37:37,709] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 115 +14: [2023-04-29 11:37:37,717] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 115 + 2: [2023-04-29 11:37:37,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt. + 2: [2023-04-29 11:37:37,718] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 21 + 2: [2023-04-29 11:37:37,725] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 21 + 2: [2023-04-29 11:37:37,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt. + 2: [2023-04-29 11:37:37,734] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 19 +30: [2023-04-29 11:37:37,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt. +30: [2023-04-29 11:37:37,737] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 241 +14: [2023-04-29 11:37:37,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt. +14: [2023-04-29 11:37:37,739] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 117 + 2: [2023-04-29 11:37:37,741] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 19 + 0: [2023-04-29 11:37:37,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt. + 0: [2023-04-29 11:37:37,743] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 5 + 7: [2023-04-29 11:37:37,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt. + 7: [2023-04-29 11:37:37,743] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 63 +30: [2023-04-29 11:37:37,744] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 241 +14: [2023-04-29 11:37:37,746] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 117 +11: [2023-04-29 11:37:37,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt. +11: [2023-04-29 11:37:37,747] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 89 + 7: [2023-04-29 11:37:37,751] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 63 + 0: [2023-04-29 11:37:37,754] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 5 +11: [2023-04-29 11:37:37,756] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 89 + 0: [2023-04-29 11:37:37,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt. + 0: [2023-04-29 11:37:37,760] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 1 + 0: [2023-04-29 11:37:37,768] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 1 + 7: [2023-04-29 11:37:37,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt. +25: [2023-04-29 11:37:37,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt. +25: [2023-04-29 11:37:37,784] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 205 + 7: [2023-04-29 11:37:37,784] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 61 +30: [2023-04-29 11:37:37,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt. +30: [2023-04-29 11:37:37,788] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 243 +30: [2023-04-29 11:37:37,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt. +14: [2023-04-29 11:37:37,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt. +30: [2023-04-29 11:37:37,790] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 245 +14: [2023-04-29 11:37:37,790] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 113 +25: [2023-04-29 11:37:37,790] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 205 + 7: [2023-04-29 11:37:37,790] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 61 +25: [2023-04-29 11:37:37,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt. +25: [2023-04-29 11:37:37,793] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 207 +30: [2023-04-29 11:37:37,795] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 243 + 7: [2023-04-29 11:37:37,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt. + 7: [2023-04-29 11:37:37,795] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 57 +14: [2023-04-29 11:37:37,796] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 113 +14: [2023-04-29 11:37:37,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt. +14: [2023-04-29 11:37:37,798] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 119 +30: [2023-04-29 11:37:37,798] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 245 +25: [2023-04-29 11:37:37,800] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 207 + 7: [2023-04-29 11:37:37,803] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 57 +30: [2023-04-29 11:37:37,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt. +30: [2023-04-29 11:37:37,804] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 247 +14: [2023-04-29 11:37:37,807] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 119 +30: [2023-04-29 11:37:37,810] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 247 + 7: [2023-04-29 11:37:37,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt. + 7: [2023-04-29 11:37:37,812] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 59 + 7: [2023-04-29 11:37:37,821] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 59 +25: [2023-04-29 11:37:37,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt. +25: [2023-04-29 11:37:37,848] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 203 +25: [2023-04-29 11:37:37,855] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 203 + 1: [2023-04-29 11:37:37,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt. + 1: [2023-04-29 11:37:37,859] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 11 +20: [2023-04-29 11:37:37,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt. + 1: [2023-04-29 11:37:37,867] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 11 +20: [2023-04-29 11:37:37,867] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 163 +24: [2023-04-29 11:37:37,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt. +24: [2023-04-29 11:37:37,872] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 199 +20: [2023-04-29 11:37:37,874] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 163 +28: [2023-04-29 11:37:37,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt. +28: [2023-04-29 11:37:37,876] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 231 +24: [2023-04-29 11:37:37,879] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 199 + 6: [2023-04-29 11:37:37,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt. + 6: [2023-04-29 11:37:37,881] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 51 +28: [2023-04-29 11:37:37,882] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 231 + 1: [2023-04-29 11:37:37,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt. + 1: [2023-04-29 11:37:37,885] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 15 + 6: [2023-04-29 11:37:37,889] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 51 + 1: [2023-04-29 11:37:37,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt. + 1: [2023-04-29 11:37:37,890] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 13 + 6: [2023-04-29 11:37:37,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt. +21: [2023-04-29 11:37:37,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt. + 6: [2023-04-29 11:37:37,891] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 55 +21: [2023-04-29 11:37:37,891] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 173 + 1: [2023-04-29 11:37:37,892] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 15 + 1: [2023-04-29 11:37:37,897] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 13 + 6: [2023-04-29 11:37:37,898] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 55 +21: [2023-04-29 11:37:37,899] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 173 +19: [2023-04-29 11:37:37,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt. +19: [2023-04-29 11:37:37,900] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 153 +22: [2023-04-29 11:37:37,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt. +22: [2023-04-29 11:37:37,901] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 183 +18: [2023-04-29 11:37:37,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt. +18: [2023-04-29 11:37:37,908] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 149 +22: [2023-04-29 11:37:37,909] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 183 +31: [2023-04-29 11:37:37,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt. +31: [2023-04-29 11:37:37,910] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 249 +21: [2023-04-29 11:37:37,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt. +31: [2023-04-29 11:37:37,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt. +31: [2023-04-29 11:37:37,910] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 255 +21: [2023-04-29 11:37:37,910] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 171 +19: [2023-04-29 11:37:37,910] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 153 +15: [2023-04-29 11:37:37,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt. +15: [2023-04-29 11:37:37,914] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 125 +21: [2023-04-29 11:37:37,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt. +21: [2023-04-29 11:37:37,914] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 169 +18: [2023-04-29 11:37:37,916] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 149 +21: [2023-04-29 11:37:37,917] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 171 +25: [2023-04-29 11:37:37,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt. +25: [2023-04-29 11:37:37,917] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 201 +31: [2023-04-29 11:37:37,918] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 249 +31: [2023-04-29 11:37:37,918] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 255 +31: [2023-04-29 11:37:37,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt. +31: [2023-04-29 11:37:37,918] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 251 +28: [2023-04-29 11:37:37,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt. +28: [2023-04-29 11:37:37,919] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 225 + 6: [2023-04-29 11:37:37,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt. + 6: [2023-04-29 11:37:37,920] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 53 +15: [2023-04-29 11:37:37,921] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 125 +22: [2023-04-29 11:37:37,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt. +22: [2023-04-29 11:37:37,923] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 181 +21: [2023-04-29 11:37:37,924] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 169 +28: [2023-04-29 11:37:37,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt. +25: [2023-04-29 11:37:37,926] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 201 +28: [2023-04-29 11:37:37,926] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 227 +31: [2023-04-29 11:37:37,926] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 251 +28: [2023-04-29 11:37:37,927] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 225 + 6: [2023-04-29 11:37:37,928] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 53 +22: [2023-04-29 11:37:37,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt. +22: [2023-04-29 11:37:37,931] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 177 +22: [2023-04-29 11:37:37,931] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 181 +28: [2023-04-29 11:37:37,933] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 227 +15: [2023-04-29 11:37:37,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt. +15: [2023-04-29 11:37:37,934] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 121 +19: [2023-04-29 11:37:37,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt. +19: [2023-04-29 11:37:37,935] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 157 +15: [2023-04-29 11:37:37,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt. +15: [2023-04-29 11:37:37,937] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 127 +22: [2023-04-29 11:37:37,938] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 177 + 1: [2023-04-29 11:37:37,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt. + 1: [2023-04-29 11:37:37,939] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 9 +31: [2023-04-29 11:37:37,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt. +31: [2023-04-29 11:37:37,939] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 253 +15: [2023-04-29 11:37:37,942] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 121 +18: [2023-04-29 11:37:37,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt. +18: [2023-04-29 11:37:37,943] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 145 +19: [2023-04-29 11:37:37,943] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 157 +28: [2023-04-29 11:37:37,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt. +28: [2023-04-29 11:37:37,943] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 229 + 1: [2023-04-29 11:37:37,945] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 9 +15: [2023-04-29 11:37:37,945] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 127 +31: [2023-04-29 11:37:37,946] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 253 +21: [2023-04-29 11:37:37,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt. +21: [2023-04-29 11:37:37,948] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 175 +18: [2023-04-29 11:37:37,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt. +18: [2023-04-29 11:37:37,948] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 151 +18: [2023-04-29 11:37:37,949] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 145 +22: [2023-04-29 11:37:37,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt. +28: [2023-04-29 11:37:37,950] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 229 +26: [2023-04-29 11:37:37,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt. +22: [2023-04-29 11:37:37,951] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 179 +26: [2023-04-29 11:37:37,951] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 209 +27: [2023-04-29 11:37:37,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt. +27: [2023-04-29 11:37:37,951] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 217 +21: [2023-04-29 11:37:37,954] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 175 +22: [2023-04-29 11:37:37,957] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 179 +18: [2023-04-29 11:37:37,957] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 151 +27: [2023-04-29 11:37:37,959] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 217 +26: [2023-04-29 11:37:37,959] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 209 + 6: [2023-04-29 11:37:37,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt. + 6: [2023-04-29 11:37:37,966] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 49 +18: [2023-04-29 11:37:37,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt. +18: [2023-04-29 11:37:37,968] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 147 +19: [2023-04-29 11:37:37,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt. +19: [2023-04-29 11:37:37,968] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 159 +18: [2023-04-29 11:37:37,974] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 147 +19: [2023-04-29 11:37:37,974] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 159 + 6: [2023-04-29 11:37:37,975] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 49 +23: [2023-04-29 11:37:37,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt. +23: [2023-04-29 11:37:37,975] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 191 +24: [2023-04-29 11:37:37,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt. +24: [2023-04-29 11:37:37,975] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 193 +24: [2023-04-29 11:37:37,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt. +24: [2023-04-29 11:37:37,977] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 195 +15: [2023-04-29 11:37:37,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt. +26: [2023-04-29 11:37:37,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt. +26: [2023-04-29 11:37:37,979] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 213 +15: [2023-04-29 11:37:37,979] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 123 +23: [2023-04-29 11:37:37,982] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 191 +19: [2023-04-29 11:37:37,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt. +19: [2023-04-29 11:37:37,983] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 155 +24: [2023-04-29 11:37:37,984] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 195 +24: [2023-04-29 11:37:37,984] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 193 +26: [2023-04-29 11:37:37,987] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 213 +15: [2023-04-29 11:37:37,988] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 123 +10: [2023-04-29 11:37:37,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt. +10: [2023-04-29 11:37:37,989] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 83 + 9: [2023-04-29 11:37:37,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt. + 9: [2023-04-29 11:37:37,990] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 75 +19: [2023-04-29 11:37:37,992] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 155 +27: [2023-04-29 11:37:37,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt. +27: [2023-04-29 11:37:37,996] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 221 +10: [2023-04-29 11:37:37,996] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 83 + 9: [2023-04-29 11:37:37,998] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 75 +24: [2023-04-29 11:37:38,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt. +24: [2023-04-29 11:37:38,001] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 197 + 3: [2023-04-29 11:37:38,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt. + 3: [2023-04-29 11:37:38,002] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 25 +12: [2023-04-29 11:37:38,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt. +12: [2023-04-29 11:37:38,003] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 103 +27: [2023-04-29 11:37:38,005] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 221 +26: [2023-04-29 11:37:38,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt. +26: [2023-04-29 11:37:38,008] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 211 + 3: [2023-04-29 11:37:38,009] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 25 +24: [2023-04-29 11:37:38,009] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 197 +12: [2023-04-29 11:37:38,010] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 103 +10: [2023-04-29 11:37:38,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt. +10: [2023-04-29 11:37:38,015] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 81 +26: [2023-04-29 11:37:38,017] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 211 + 9: [2023-04-29 11:37:38,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt. + 9: [2023-04-29 11:37:38,019] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 79 +10: [2023-04-29 11:37:38,022] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 81 +26: [2023-04-29 11:37:38,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt. +26: [2023-04-29 11:37:38,026] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 215 +29: [2023-04-29 11:37:38,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt. +29: [2023-04-29 11:37:38,027] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 235 + 9: [2023-04-29 11:37:38,027] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 79 +26: [2023-04-29 11:37:38,033] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 215 +29: [2023-04-29 11:37:38,035] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 235 + 9: [2023-04-29 11:37:38,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt. +27: [2023-04-29 11:37:38,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt. +27: [2023-04-29 11:37:38,035] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 223 + 9: [2023-04-29 11:37:38,035] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 73 +12: [2023-04-29 11:37:38,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt. +12: [2023-04-29 11:37:38,036] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 101 +12: [2023-04-29 11:37:38,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt. +12: [2023-04-29 11:37:38,040] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 97 +23: [2023-04-29 11:37:38,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt. +23: [2023-04-29 11:37:38,040] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 185 + 9: [2023-04-29 11:37:38,042] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 73 +27: [2023-04-29 11:37:38,043] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 223 +12: [2023-04-29 11:37:38,044] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 101 +27: [2023-04-29 11:37:38,044] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt. +27: [2023-04-29 11:37:38,044] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 219 + 3: [2023-04-29 11:37:38,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt. + 3: [2023-04-29 11:37:38,046] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 27 +12: [2023-04-29 11:37:38,047] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 97 +16: [2023-04-29 11:37:38,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt. +16: [2023-04-29 11:37:38,048] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 135 + 9: [2023-04-29 11:37:38,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt. + 9: [2023-04-29 11:37:38,048] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 77 +23: [2023-04-29 11:37:38,048] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 185 +27: [2023-04-29 11:37:38,052] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 219 + 3: [2023-04-29 11:37:38,054] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 27 +16: [2023-04-29 11:37:38,054] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 135 + 9: [2023-04-29 11:37:38,056] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 77 +23: [2023-04-29 11:37:38,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt. +23: [2023-04-29 11:37:38,057] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 189 +23: [2023-04-29 11:37:38,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt. +23: [2023-04-29 11:37:38,061] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 187 + 3: [2023-04-29 11:37:38,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt. + 3: [2023-04-29 11:37:38,064] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 29 +23: [2023-04-29 11:37:38,064] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 189 +10: [2023-04-29 11:37:38,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt. +10: [2023-04-29 11:37:38,066] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 87 +16: [2023-04-29 11:37:38,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt. +16: [2023-04-29 11:37:38,067] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 131 +23: [2023-04-29 11:37:38,068] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 187 + 3: [2023-04-29 11:37:38,071] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 29 +10: [2023-04-29 11:37:38,073] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 87 +10: [2023-04-29 11:37:38,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt. +16: [2023-04-29 11:37:38,074] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 131 +10: [2023-04-29 11:37:38,074] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 85 + 5: [2023-04-29 11:37:38,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt. + 5: [2023-04-29 11:37:38,082] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 47 +10: [2023-04-29 11:37:38,083] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 85 + 3: [2023-04-29 11:37:38,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt. + 3: [2023-04-29 11:37:38,084] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 31 +16: [2023-04-29 11:37:38,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt. +16: [2023-04-29 11:37:38,087] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 129 +12: [2023-04-29 11:37:38,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt. +12: [2023-04-29 11:37:38,088] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 99 + 5: [2023-04-29 11:37:38,089] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 47 + 3: [2023-04-29 11:37:38,091] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 31 +16: [2023-04-29 11:37:38,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt. +16: [2023-04-29 11:37:38,093] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 133 +16: [2023-04-29 11:37:38,095] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 129 +12: [2023-04-29 11:37:38,096] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 99 + 5: [2023-04-29 11:37:38,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt. + 5: [2023-04-29 11:37:38,098] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 41 +16: [2023-04-29 11:37:38,101] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 133 +29: [2023-04-29 11:37:38,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt. +29: [2023-04-29 11:37:38,104] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 239 + 5: [2023-04-29 11:37:38,106] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 41 +29: [2023-04-29 11:37:38,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt. +29: [2023-04-29 11:37:38,107] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 237 +29: [2023-04-29 11:37:38,112] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 239 +29: [2023-04-29 11:37:38,114] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 237 + 5: [2023-04-29 11:37:38,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt. + 5: [2023-04-29 11:37:38,122] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 45 +29: [2023-04-29 11:37:38,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt. +29: [2023-04-29 11:37:38,129] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 233 + 5: [2023-04-29 11:37:38,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b/global_step84877/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt. + 5: [2023-04-29 11:37:38,129] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 128 ZeRO state_dicts for rank 43 + 5: [2023-04-29 11:37:38,130] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 45 +29: [2023-04-29 11:37:38,136] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 233 + 5: [2023-04-29 11:37:38,137] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 128 zero partition checkpoints for rank 43 + 0: successfully loaded checkpoint from lm1-8b7-178b-c4-repetitions/8b7178b35b at iteration 0 +63: time (ms) | load-checkpoint: 14847.25 + 0: estimated model parameters: 8.905678848 + 0: estimated model parameters without embeddings: 8.458985472 + 0: [after model, optimizer, and learning rate scheduler are built] datetime: 2023-04-29 11:37:39 + 0: > building train, validation, and test datasets ... + 0: > datasets target sizes (minimum size): + 0: train: 1 + 0: validation: 51200 + 0: test: 51200 + 0: > building train, validation, and test datasets for GPT ... + 0: > building dataset index ... + 0: reading sizes... + 0: reading pointers... + 0: reading document index... + 0: creating numpy buffer of mmap... + 0: creating memory view of numpy buffer... + 0: > finished creating indexed dataset in 0.038546 seconds + 0: number of documents: 835726 + 0: > dataset split: + 0: train: + 0: document indices in [0, 835726) total of 835726 documents + 0: > loading doc-idx mapping from /scratch/project_462000119/data/c4_subsampled/gpt2tok_c4_en_400M_text_document_train_indexmap_1ns_2048sl_1234s_doc_idx.npy + 0: > loading sample-idx mapping from /scratch/project_462000119/data/c4_subsampled/gpt2tok_c4_en_400M_text_document_train_indexmap_1ns_2048sl_1234s_sample_idx.npy + 0: > loading shuffle-idx mapping from /scratch/project_462000119/data/c4_subsampled/gpt2tok_c4_en_400M_text_document_train_indexmap_1ns_2048sl_1234s_shuffle_idx.npy + 0: loaded indexed file in 0.074 seconds + 0: total number of samples: 195101 + 0: total number of epochs: 1 + 0: > building dataset index ... + 0: reading sizes... + 0: reading pointers... + 0: reading document index... + 0: creating numpy buffer of mmap... + 0: creating memory view of numpy buffer... + 0: > finished creating indexed dataset in 0.024757 seconds + 0: number of documents: 364608 + 0: > dataset split: + 0: validation: + 0: document indices in [0, 364608) total of 364608 documents + 0: > loading doc-idx mapping from /scratch/project_462000119/data/c4_validation/gpt2tok_c4validation_rerun_text_document_validation_indexmap_51200ns_2048sl_1234s_doc_idx.npy + 0: > loading sample-idx mapping from /scratch/project_462000119/data/c4_validation/gpt2tok_c4validation_rerun_text_document_validation_indexmap_51200ns_2048sl_1234s_sample_idx.npy + 0: > loading shuffle-idx mapping from /scratch/project_462000119/data/c4_validation/gpt2tok_c4validation_rerun_text_document_validation_indexmap_51200ns_2048sl_1234s_shuffle_idx.npy + 0: loaded indexed file in 0.080 seconds + 0: total number of samples: 84978 + 0: total number of epochs: 1 + 0: > finished creating GPT datasets ... + 0: [after dataloaders are built] datetime: 2023-04-29 11:37:46 + 0: done with setup ... + 0: training ... +63: time (ms) | model-and-optimizer-setup: 35649.09 | train/valid/test-data-iterators-setup: 4412.36 + 0: [after training is done] datetime: 2023-04-29 11:37:46 +63: ----------------------------------------------------------------------------------------------------------------- +63: validation loss at the end of training for val data | lm loss value: 2.360029E+00 | lm loss PPL: 1.059126E+01 | +63: ----------------------------------------------------------------------------------------------------------------- +END 3430973: Sat 29 Apr 2023 11:39:19 AM EEST